CN114594467B

CN114594467B - A method, device, electronic device and storage medium for determining heading angle

Info

Publication number: CN114594467B
Application number: CN202210185678.6A
Authority: CN
Inventors: 赵加友; 朱奇峰; 方勇军
Original assignee: Zhejiang Dahua Technology Co Ltd
Current assignee: Zhejiang Dahua Technology Co Ltd
Priority date: 2022-02-28
Filing date: 2022-02-28
Publication date: 2025-05-09
Anticipated expiration: 2042-02-28
Also published as: CN114594467A

Abstract

The application discloses a course angle determining method, a course angle determining device, electronic equipment and a storage medium, which are used for improving accuracy of determining a course angle of a moving vehicle. The method comprises the steps of firstly continuously detecting a target scene by adopting a millimeter wave radar and a laser radar to obtain a first detection point cluster and a second detection point cloud, then carrying out time synchronization processing and space synchronization processing on the first detection point cluster and the second detection point cloud, carrying out area expansion on coordinates of each first detection point after the synchronization processing to obtain an expansion area of the first detection point, determining a second detection point falling in the expansion area, then associating the second detection point with the first detection point, carrying out information fusion on the first detection point and the second detection point to obtain fusion detection points, finally carrying out segmentation processing on fusion detection point cloud formed by the fusion detection points to obtain fusion detection point cloud corresponding to each vehicle in the target scene, and determining a course angle of each vehicle based on the fusion detection point cloud.

Description

Course angle determining method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of radar technologies, and in particular, to a method and apparatus for determining a heading angle, an electronic device, and a storage medium.

Background

The heading angle of a moving vehicle is a very important parameter when estimating the motion state of the moving vehicle at the next moment.

In the related art, a millimeter wave radar or a laser radar is mostly adopted to estimate the course angle of a moving vehicle, when the millimeter wave radar is adopted to estimate the course angle of the moving vehicle, the millimeter wave radar is adopted to measure the position of the vehicle and Doppler information of the vehicle, then a corresponding course angle estimation model is established by combining a selected tracking model, but the measurement precision of the method is limited by the error of the millimeter wave radar in measuring the position of the moving vehicle, the error of Doppler measurement and the error of the course angle estimation model, when the laser radar is adopted to estimate the course angle of the moving vehicle, firstly, the detected point cloud is subjected to segmentation processing, and then the shape of the point cloud is estimated based on the point cloud, so that the course angle of the moving vehicle is obtained, but the measurement precision of the course angle of the method is limited by the precision of the detected point cloud.

Disclosure of Invention

The application aims to provide a course angle determining method, a course angle determining device, electronic equipment and a storage medium, which are used for improving accuracy of determining a course angle of a moving vehicle.

In a first aspect, an embodiment of the present application provides a method for determining a heading angle, where the method includes:

Continuously detecting a target scene by adopting a millimeter wave radar to obtain a continuous multi-frame first detection point cluster, and continuously detecting the target scene by adopting a laser radar to obtain a continuous multi-frame second detection point cloud, wherein the target scene comprises at least one vehicle;

Performing time synchronization processing and space synchronization processing on the first detection point cluster and the second detection point cloud to obtain a first detection point cluster and a second detection point cloud which have association relations in time and space;

performing area expansion on the coordinates of each first detection point in the first detection point cluster after synchronous processing according to standard deviation to obtain an expansion area of the first detection point, and determining a second detection point falling in the expansion area according to the coordinates of a second detection point, wherein the standard deviation is the standard deviation of physical parameters related to the first detection point;

associating a second detection point falling in the expansion area with the first detection point, and carrying out information fusion on the first detection point and the second detection point which are mutually associated to obtain a fusion detection point;

and carrying out segmentation processing on the fusion detection point cloud formed by the fusion detection points to obtain fusion detection point cloud corresponding to each vehicle in the target scene, and determining the course angle of each vehicle based on the fusion detection point cloud.

In the application, the millimeter wave radar and the laser radar are adopted to detect the moving vehicle together, the first detection point cluster and the second detection point cloud obtained by detection are associated, and the first detection point and the corresponding second detection point are subjected to information fusion, so that the fusion detection point has the information obtained by the detection of the millimeter wave radar and the information obtained by the detection of the laser radar, and finally the course angle estimation is carried out on the basis of the fusion detection point.

In some possible embodiments, the time synchronization processing for the first detection point cluster and the second detection point cloud includes:

Determining a first calculation time stamp and a second calculation time stamp corresponding to each second time stamp according to each second time stamp, wherein the first time stamp is obtained by marking a first detection point cluster of each frame obtained by continuously detecting the target scene by the millimeter wave radar according to a first preset frequency, and the second time stamp is obtained by marking a second detection point cloud of each frame obtained by continuously detecting the target scene by the laser radar according to a second preset frequency;

And determining an associated first detection point cluster with an association relationship with a second detection point cloud corresponding to the second timestamp based on the first calculation timestamp, the second calculation timestamp and the second timestamp.

In the application, the first detection point cluster and the second detection point cloud are time-synchronized based on the marked time stamp, and the first detection point cluster and the second detection point cloud which have an association relation in time are determined, so that the accuracy of the subsequent course angle determination is further improved.

In some possible embodiments, the determining, based on the first calculated timestamp, the second calculated timestamp, and the second timestamp, an associated first detection point cluster having an association relationship with a second detection point cloud corresponding to the second timestamp includes:

obtaining a third time stamp, wherein the third time stamp is obtained by marking a first time interval with a second preset frequency after determining a first time stamp of the laser radar marking a second time stamp, and the first time interval is obtained according to the second preset frequency;

for each third timestamp, determining a target second timestamp that is least in time sequence different from and preceding the third timestamp;

Acquiring a first calculation time stamp and a second calculation time stamp corresponding to the target second time stamp;

determining an associated first detection point cluster based on the first detection point cluster corresponding to the first calculated timestamp and the first detection point cluster corresponding to the second calculated timestamp;

and taking the associated first detection point cluster as a first detection point cluster with an association relationship in time of a second detection point cloud corresponding to the target second timestamp.

In the application, the third timestamp is adopted to ensure that when the first detection point cluster and the second detection point cloud with the association relation are calculated, the data of the first detection point cluster and the second detection point cloud are detected, and the timeliness of calculation is ensured.

In some possible embodiments, the determining the associated first detection point cluster based on the first detection point cluster corresponding to the first calculated timestamp and the first detection point cluster corresponding to the second calculated timestamp includes:

Performing linear interpolation processing on the detection point cluster corresponding to the first calculated timestamp and the first detection point cluster corresponding to the second calculated timestamp to obtain the associated first detection point cluster, or

And carrying out mean value processing on coordinates of a first detection point in the detection point cluster corresponding to the first calculation timestamp and the first detection point cluster corresponding to the second calculation timestamp to obtain the associated first detection point cluster.

In the application, in order to ensure the accuracy of the finally obtained course angle, the first detection point cluster corresponding to the first calculation time stamp and the second detection point cluster corresponding to the second calculation time stamp are combined to obtain the associated detection point cluster, so that the course angle is more accurate.

In some possible embodiments, performing spatial synchronization processing on the first detection point cluster and the second detection point cloud includes:

And carrying out coordinate conversion on the first detection point based on the rotation parameter and the translation parameter, and carrying out coordinate conversion on the second detection point based on the rotation parameter and the translation parameter to obtain the coordinates of the first detection point and the coordinates of the second detection point after spatial synchronization, wherein the rotation parameter is used for rotating each coordinate axis in a coordinate system corresponding to the first detection point and a coordinate system corresponding to the second detection point leftwards to coincide with the coordinate axis of the spatial synchronization coordinate system, and the translation parameter is used for determining coordinate components of an origin of the spatial synchronization coordinate system in the coordinate system corresponding to the first detection point and the coordinate system corresponding to the second detection point.

In the application, the first detection point cloud and the second detection point cluster are spatially synchronized, so that the coordinates of the first detection point in the first detection point cluster and the coordinates of the second detection point in the second detection point cloud can be expressed based on the same coordinate system.

In some possible embodiments, the rotation parameter and the translation parameter are obtained according to the following method:

Measuring a target object by adopting a laser radar to obtain at least one measuring point of the target object and coordinates corresponding to the measuring point;

Measuring the target object by adopting a millimeter wave radar to obtain a first coordinate of the target object;

And determining a rotation parameter and a translation parameter based on the mean value of the coordinates and the first coordinates.

According to the method, the translation parameters and the rotation parameters are determined based on the measured values of the millimeter wave radar and the laser radar on the target object, so that the spatial synchronization of the first detection point cluster and the second detection point cloud is more accurate.

In some possible embodiments, the coordinates of the first detection point include radial distance, azimuth angle, and pitch angle;

The area expansion is performed on the coordinates of each first detection point in the first detection point cluster after the synchronization processing according to the standard deviation, and the area expansion comprises the following steps:

Performing the following procedure for each first detection point in the first detection point cluster:

Determining a radial distance standard deviation, an azimuth angle standard deviation and a pitch angle standard deviation of the first detection point according to the signal-to-noise ratio of the first detection point;

determining a first difference between the radial distance of the first detection point and the radial distance standard deviation, and determining a first sum of the radial distance of the first detection point and the radial distance standard deviation;

Determining an expansion area of the radial distance according to the first difference value and the first sum value;

Determining a second difference between the azimuth of the first detection point and the azimuth standard deviation, and determining a second sum between the azimuth of the first detection point and the azimuth standard deviation;

Determining an extension region of the azimuth angle based on the second difference value and the second sum value;

Determining a third difference between the pitch angle of the first detection point and the pitch angle standard deviation, and determining a third sum between the pitch angle of the first detection point and the pitch angle standard deviation;

Determining an expansion area of the pitch angle according to the third sum value;

And determining the expansion area of the first detection point according to the expansion area of the radial distance, the expansion area of the azimuth angle and the expansion area of the pitch angle.

In the embodiment of the application, a method for performing area expansion on the first detection points is adopted to ensure that each second detection point has a corresponding first detection point.

In some possible embodiments, the associating the second detection point falling in the corresponding area of the first detection point with the first detection point includes:

if the plurality of second detection points fall in the expansion area of the first detection point, determining the second detection point with the maximum signal-to-noise ratio in the expansion area;

And taking the second detection point with the maximum signal-to-noise ratio as a second detection point which is associated with the first detection point.

In some possible embodiments, the first detection point cluster includes a plurality of first detection points, the second detection point cloud includes a plurality of second detection points, the information fusion between the first detection points and the second detection points, which are associated with each other, is performed to obtain a fused detection point, including:

The following procedure is performed for each second detection point:

Taking the physical parameter information of the first detection point associated with the second detection point as the physical parameter information of a fusion detection point corresponding to the second detection point;

taking the coordinates of the second detection point after the spatial synchronization as the coordinates of a fusion detection point corresponding to the second detection point;

and forming the fusion detection point based on the physical parameter information of the fusion detection point and the coordinates of the fusion detection point.

In the application, the physical parameter information of the first detection point and the coordinates of the second detection point are adopted, so that the fusion detection point can have the advantages of a laser radar and a millimeter wave radar at the same time.

In some possible embodiments, determining the heading angle of each vehicle based on the fusion detection point cloud includes:

Performing, for each frame of fusion detection point cloud of each vehicle:

determining an initial course angle of the vehicle based on the fusion detection point cloud;

screening out a target fusion detection point according to the signal-to-noise ratio of each fusion detection point in the fusion detection point cloud;

determining a wheel position difference of the vehicle based on the fusion detection point cloud of the previous frame;

And inputting the initial course angle, the target fusion detection point and the wheel position difference into a pre-trained motion model to obtain the course angle of the vehicle.

According to the application, the course angle of the vehicle is obtained based on the fusion detection point cloud, so that the accuracy of estimating the course angle of the vehicle is improved.

In a second aspect, the present application also provides a heading angle determining apparatus, including:

The detection module is used for continuously detecting a target scene by adopting a millimeter wave radar to obtain a continuous multi-frame first detection point cluster, and continuously detecting the target scene by adopting a laser radar to obtain a continuous multi-frame second detection point cloud, wherein the target scene comprises at least one vehicle;

The synchronization module is used for carrying out time synchronization processing and space synchronization processing on the first detection point cluster and the second detection point cloud to obtain the first detection point cluster and the second detection point cloud which have association relations in time and space;

The expansion module is used for carrying out area expansion on the coordinates of each first detection point in the first detection point cluster after synchronous processing according to standard deviation to obtain an expansion area of the first detection point, and determining a second detection point falling in the expansion area according to the coordinates of a second detection point, wherein the standard deviation is the standard deviation of physical parameters related to the first detection point;

The fusion module is used for associating a second detection point falling in the expansion area with the first detection point and carrying out information fusion on the first detection point and the second detection point which are mutually associated to obtain a fusion detection point;

The course angle determining module is used for carrying out segmentation processing on the fusion detection point cloud formed by the fusion detection points to obtain fusion detection point cloud corresponding to each vehicle in the target scene, and determining the course angle of each vehicle based on the fusion detection point cloud.

In some possible embodiments, the synchronization module, when performing time synchronization processing on the first detection point cluster and the second detection point cloud, is configured to:

In some possible embodiments, the synchronization module, when executing an associated first detection point cluster that determines that a second detection point cloud corresponding to the second timestamp has an association relationship based on the first calculated timestamp, the second calculated timestamp, and the second timestamp, is configured to:

In some possible embodiments, the synchronization module, when executing the determination of the associated first detection point cluster based on the first detection point cluster corresponding to the first calculated timestamp and the first detection point cluster corresponding to the second calculated timestamp, is configured to:

In some possible embodiments, the synchronization module, when performing spatial synchronization processing on the first detection point cluster and the second detection point cloud, is configured to:

The expansion module is configured to, when performing area expansion on coordinates of each first detection point in the first detection point cluster after synchronization processing according to a standard deviation:

In some possible embodiments, the fusion module, when executing associating a second detection point falling in a corresponding area of the first detection point with the first detection point, is configured to:

The following procedure is performed for each second detection point:

In some possible embodiments, the course angle determination module, when executing the determination of the course angle of each vehicle based on the fusion detection point cloud, is configured to:

Performing, for each frame of fusion detection point cloud of each vehicle:

In a third aspect, another embodiment of the present application also provides an electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any one of the methods provided by the embodiments of the first aspect of the present application.

In a fourth aspect, another embodiment of the present application further provides a computer readable storage medium, where the computer readable storage medium stores a computer program for causing a computer to perform any one of the methods provided by the embodiments of the first aspect of the present application.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is an application scene diagram of a course angle determining method provided by an embodiment of the application;

Fig. 2 is an overall flow chart of a course angle determining method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a timestamp marking of a course angle determining method according to an embodiment of the present application;

fig. 4 is a schematic diagram of a first detection point cluster associated with determination of a course angle determination method according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a third timestamp of a course angle determining method according to an embodiment of the present application;

fig. 6 is a schematic diagram of a first detection point cluster associated with determination of a course angle determination method according to an embodiment of the present application;

FIG. 7 is a schematic diagram of parameter determination of a course angle determination method according to an embodiment of the present application;

FIG. 8A is a schematic view of an area expansion of a course angle determination method according to an embodiment of the present application;

FIG. 8B is a schematic diagram of an extended area of a course angle determination method according to an embodiment of the present application;

fig. 9 is an information fusion schematic diagram of a course angle determining method according to an embodiment of the present application;

fig. 10 is a schematic diagram of a course angle determination method according to an embodiment of the present application;

FIG. 11 is a schematic diagram of a method for determining an initial heading angle according to an embodiment of the present application;

Fig. 12 is an overall flow chart of a course angle determining method according to an embodiment of the present application;

FIG. 13 is a schematic diagram of a device for determining a heading angle according to an embodiment of the present application;

fig. 14 is a schematic diagram of an electronic device according to a heading angle determining method provided by an embodiment of the present application.

Detailed Description

In order to enable a person skilled in the art to better understand the technical solutions of the present application, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and in the claims are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.

The inventor researches and discovers that the course angle of the moving vehicle is a very important parameter when the moving state of the moving vehicle at the next moment is estimated.

In view of the above, the present application proposes a heading angle determining method, apparatus, electronic device and storage medium for solving the above-mentioned problems. The method comprises the steps of continuously detecting a target scene by adopting a millimeter wave radar and a laser radar to obtain a continuous multi-frame first detection point cluster and a continuous multi-frame second detection point cloud, performing time synchronization processing and space synchronization processing on the first detection point cluster and the second detection point cloud, performing region expansion on coordinates of each first detection point in the first detection point cluster after the synchronization processing according to standard deviation to obtain an expansion region of the first detection point, determining a second detection point falling in the expansion region according to the coordinates of the second detection point, wherein the standard deviation is a standard deviation of physical parameters associated with the first detection point, then associating the second detection point falling in the expansion region with the first detection point, and performing information fusion on the associated first detection point and the second detection point to obtain a fusion detection point cloud, and finally performing segmentation processing on the fusion detection point cloud formed by the fusion detection points to obtain a fusion detection point cloud corresponding to each vehicle in the target scene, and determining a heading angle of each vehicle based on the fusion detection point cloud.

In order to facilitate understanding of a method for determining a heading angle provided by an embodiment of the present application, the following details are described with reference to the accompanying drawings:

Fig. 1 is an application scenario diagram of a course angle determining method according to an embodiment of the present application. The image comprises a laser radar 10, a millimeter wave radar 20, a server 30 and a memory 40, wherein the millimeter wave radar 20 is adopted to continuously detect a target scene to obtain a continuous multi-frame first detection point cluster, the laser radar 10 is adopted to continuously detect the target scene to obtain a continuous multi-frame second detection point cloud, the target scene comprises at least one vehicle, the laser radar and the millimeter wave radar respectively report the first detection point cluster and the second detection point cloud which are obtained by self-collection to the server, the server 30 carries out time synchronization processing and space synchronization processing on the first detection point cluster and the second detection point cloud to obtain a first detection point cluster and a second detection point cloud which have association relations in time and space, then the coordinates of each first detection point in the first detection point cluster after the synchronization processing are subjected to area expansion to obtain an expansion area of the first detection point, and the second detection point which falls in the expansion area is determined according to the coordinates of the second detection point, the standard deviation is the standard deviation of physical parameters associated with the first detection point, the second detection point cluster is associated with the first detection point cloud, the first detection point cloud is subjected to the time synchronization processing and the first detection point cloud is associated with the first detection point cloud, and the first detection point cloud is fused with the first detection point cloud, and the cloud is fused with the first detection point cloud is divided into the first detection point cloud, and the second detection point cloud is fused with the first detection point cloud, the second detection point cloud is fused.

Only a single server or memory is detailed in the description of the present application, but it should be understood by those skilled in the art that the illustrated lidar 10, millimeter wave radar 20, server 30, memory 40 are intended to represent the operation of the lidar 10, millimeter wave radar 20, server 30, memory 40 in relation to the technical solution of the present application. The details of individual lidar 10, millimeter-wave radar 20, server 30, memory 40 are provided for ease of illustration at least and are not meant to imply limitations on the number, type, location, etc. of lidar 10, millimeter-wave radar 20, server 30, memory 40. It should be noted that the underlying concepts of the exemplary embodiments of the present application are not altered if additional modules are added to or individual modules are removed from the environment shown in FIG. 1.

It should be noted that, the memory in the embodiment of the present application may be, for example, a cache system, or may be hard disk storage, memory storage, or the like. In addition, the course angle determining method provided by the application is not only suitable for the application scene shown in fig. 1, but also suitable for any device with a course angle determining requirement.

Fig. 2 is a schematic flow chart of a course angle determining method according to an embodiment of the present application, where:

in step 201, continuously detecting a target scene by adopting a millimeter wave radar to obtain a continuous multi-frame first detection point cluster, and continuously detecting the target scene by adopting a laser radar to obtain a continuous multi-frame second detection point cloud, wherein the target scene comprises at least one vehicle;

Step 202, performing time synchronization processing and space synchronization processing on a first detection point cluster and a second detection point cloud to obtain the first detection point cluster and the second detection point cloud which have association relations in time and space;

In step 203, performing area expansion on the coordinates of each first detection point in the first detection point cluster after the synchronization processing according to the standard deviation to obtain an expansion area of the first detection point, and determining a second detection point falling in the expansion area according to the coordinates of the second detection point, wherein the standard deviation is the standard deviation of the physical parameter associated with the first detection point;

In step 204, associating the second detection point falling in the expansion area with the first detection point, and carrying out information fusion on the first detection point and the second detection point which are associated with each other to obtain a fusion detection point;

In step 205, a fusion detection point cloud formed by fusion detection points is subjected to segmentation processing to obtain a fusion detection point cloud corresponding to each vehicle in a target scene, and a course angle of each vehicle is determined based on the fusion detection point cloud.

For ease of understanding, the steps shown in fig. 2 are described in detail below:

The method comprises the steps of firstly, carrying out information explanation on a first detection point cluster and a second detection point cloud, wherein a high-performance millimeter wave radar continuously detects a target scene, each frame of the first detection point cluster comprises a first detection point, radial distance, doppler speed information, azimuth angle, pitch angle information, radar reflection sectional area (Radar Cross Section, RCS), spot quality, a first timestamp, signal-to-noise ratio and other information, and a laser radar continuously detects the target scene, and each frame of the second detection point cloud comprises a second detection point and a second timestamp.

The following describes a course angle determining method provided by the embodiment of the application in detail by combining a first detection point cluster and a second detection point cloud:

1. Time synchronization

In order to ensure that the finally obtained course angle of the moving vehicle is more accurate, time synchronization needs to be carried out on the first detection point cluster and the second detection point cloud, the method can be implemented in such a way that for each second timestamp, a first calculation timestamp and a second calculation timestamp corresponding to the second timestamp are determined, and an associated first detection point cluster with an association relationship with the second detection point cloud corresponding to the second timestamp is determined based on the first calculation timestamp, the second calculation timestamp and the second timestamp.

The first time stamp is obtained by marking a first detection point cluster of each frame obtained by continuously detecting a target scene by the millimeter wave radar according to a first preset frequency, the second time stamp is obtained by marking a second detection point cloud of each frame obtained by continuously detecting the target scene by the laser radar according to a second preset frequency, the first calculation time stamp is a first time stamp which is positioned in front of the second time stamp in time sequence and has the smallest time interval with the second time stamp, and the second calculation time stamp is a first time stamp which is positioned behind the second time stamp in time sequence and has the smallest time interval with the second time stamp.

For example, if the frequency of the millimeter wave radar is 20 hz and the frequency of the laser radar is 12 hz, the first time stamp and the second time stamp are shown in fig. 3, the first calculation time stamp of the time stamp t1 is a0, and the second calculation time stamp is a1.

Determining, based on the first calculated timestamp, the second calculated timestamp, and the second timestamp, that the second detection point cloud corresponding to the second timestamp has an associated first detection point cluster with an association relationship, may be specifically implemented as steps as shown in fig. 4:

In step 401, a third time stamp is obtained by determining that the laser radar marks a first time stamp and a second time stamp and then starting to mark the first time stamp at a first preset frequency at a first time interval, wherein the first time interval is obtained according to a second preset frequency;

For example, assuming that the frequency of the laser radar is 12hz and the frequency of the millimeter wave radar is 20 hz, the frequency of the third timestamp is 12hz, and since the frequency of the millimeter wave radar is 20 hz, the first time interval is 50 ms, which is the inverse of the frequency of the millimeter wave radar, and therefore the third timestamp is shown in fig. 5.

In step 402, for each third timestamp, determining a target second timestamp that is least in time sequence different from and preceding the third timestamp;

For example, continuing to take fig. 5 as an example, taking c0 as an example, the target second timestamp is b0.

In step 403, a first computation time stamp and a second computation time stamp corresponding to a target second time stamp are obtained;

Taking fig. 5 as an example, the first calculated timestamp corresponding to the target second timestamp b0 is a0, and the second calculated timestamp is a1.

In step 404, determining an associated first detection point cluster based on the first detection point cluster corresponding to the first calculated timestamp and the first detection point cluster corresponding to the second calculated timestamp;

in the embodiment of the application, the following two methods can be implemented specifically:

1) And performing linear interpolation processing on the first detection point cluster corresponding to the first calculation timestamp and the first detection point cluster corresponding to the second calculation timestamp to obtain an associated first detection point cluster.

For example, a first detection point cluster corresponding to a first calculation timestamp is an A point cluster, a first detection point cluster corresponding to a second calculation timestamp is a B point cluster, as shown in fig. 6, the A point cluster and the B point cluster are associated according to coordinates of points in the A point cluster and the B point cluster, namely, two points with closest coordinates are used as two associated points, for example, 1 is associated with a 1 'point, 2 is associated with a 2' point. And then carrying out linear interpolation on the associated points to obtain interpolation points, and obtaining an associated first detection point cluster based on the interpolation points.

2) And carrying out mean value processing on coordinates of a first detection point in the detection point cluster corresponding to the first calculation timestamp and the first detection point cluster corresponding to the second calculation timestamp to obtain an associated first detection point cluster.

For example, continuing to refer to fig. 6, the point cluster a and the point cluster B are first associated according to the coordinates of the points in the point cluster a and the point cluster B, that is, the two points with the closest coordinates are taken as the two associated points, for example, the point 1 is associated with the point 1', the point 2 is associated with the point 2. And then carrying out mean processing on the two points which are mutually related to obtain a related first detection point cluster.

In step 405, the associated first detection point cluster is taken as a first detection point cluster with an association relationship in time of a second detection point cloud corresponding to the target second timestamp.

2. Spatial synchronization

In order to facilitate calculation of subsequent steering angles, spatial synchronization processing is needed for the first detection point cluster and the second detection point cloud, and the method specifically comprises the steps of performing coordinate conversion on the first detection point based on rotation parameters and translation parameters, and performing coordinate conversion on the second detection point based on the rotation parameters and the translation parameters to obtain coordinates of the first detection point and coordinates of the second detection point after spatial synchronization, wherein the rotation parameters are used for enabling coordinate axes in a coordinate system corresponding to the first detection point and coordinate systems corresponding to the second detection point to rotate leftwards to coincide with coordinate axes of the spatial synchronization coordinate system, and the translation parameters are used for determining coordinate components of an origin of the spatial synchronization coordinate system in the coordinate system corresponding to the first detection point and the coordinate system corresponding to the second detection point. In the present application, the translation parameters and rotation parameters may be determined using the steps shown in fig. 7, wherein:

in step 701, measuring a target object by using a laser radar to obtain at least one measuring point of the target object and coordinates corresponding to the measuring point;

In step 702, measuring a target object by adopting a millimeter wave radar to obtain a first coordinate of the target object;

in step 703, rotation parameters and translation parameters are determined based on the mean of the coordinates and the first coordinates.

It should be understood that, in the specific implementation, the execution sequence of the step 701 and the step 702 is not limited, and the step 701 may be executed first and then the step 702 may be executed, the step 702 may be executed first and then the step 701 may be executed, or the step 701 and the step 702 may be executed simultaneously.

For example, a small metal panel (target object) is selected to be placed right in front of the millimeter wave radar, and the millimeter wave radar far field measurement condition is met, at this time, the millimeter wave can accurately measure the position of the metal plate, the horizontal precision can reach 0.1 degree, the pitching precision can reach 0.2 degree, and meanwhile the laser radar can accurately measure the spatial position of the stationary metal plate. The laser radar azimuth measurement resolution is high, the metal plate can obtain a plurality of measurement points, and at the moment, the average value L of the coordinates of the points can be taken to determine translation parameters and rotation parameters together with the millimeter wave radar measurement Rm and the formula 1.

L r+t=rm, (formula 1)

Wherein L is the average value of laser radar measuring points, rm is the coordinate value of millimeter wave radar measuring points, R is a rotation parameter, and T is a translation parameter.

In summary, by moving the position of the metal plate, multiple sets of values of L and Rm can be obtained, and thus the rotation parameter and the translation parameter can be obtained.

3. Region expansion

In the present application, when performing area expansion on each first detection point in the first detection point cluster, the steps shown in fig. 8A may be implemented:

In step 801, determining a radial distance standard deviation, an azimuth angle standard deviation and a pitch angle standard deviation of the first detection point according to the signal-to-noise ratio of the first detection point;

step 802, determining a first difference between the radial distance of the first detection point and the radial distance standard deviation, and determining a first sum between the radial distance of the first detection point and the radial distance standard deviation;

In step 803, determining an expansion area of the radial distance according to the first difference value and the first sum value;

in step 804, determining a second difference between the azimuth of the first detection point and the azimuth standard deviation, and determining a second sum between the azimuth of the first detection point and the azimuth standard deviation;

In step 805, determining an extended area of azimuth from the second difference and the second sum;

step 806, determining a third difference between the pitch angle of the first detection point and the pitch angle standard deviation, and determining a third sum between the pitch angle of the first detection point and the pitch angle standard deviation;

In step 807, determining an expansion region of the pitch angle based on the third sum;

In step 808, an extended area of the first detection point is determined based on the extended area of the radial distance, the extended area of the azimuth angle, and the extended area of the pitch angle.

It should be appreciated that the order of the radial distance determination expansion area, azimuth angle determination expansion area, and pitch angle determination expansion area is not limited in the present application, and the skilled person may perform the setting of the execution order according to the need, and fig. 8A shows only one embodiment.

For example, the first measurement point A has coordinates of (r, a, e), where r represents the radial distance, a represents the azimuth angle, e represents the pitch angle, where the radial distance has an extension of (r- Δr, r+Δr), the azimuth angle has an extension of (a- Δa, a+Δa), the pitch angle has an extension of (e- Δe, e+Δe), where Δr is the standard deviation of r, Δa is the standard deviation of a, Δe is the standard deviation of e, where Δis the standard deviation of r, Δis the standard deviation of a, and Δis the standard deviation of e, and the extension of point A is shown in FIG. 8B.

In determining the standard deviation, a test may be performed using a radar target simulator. For example, when the standard deviation is measured, the target is set to be a fixed distance, then the reflected power of the target is adjusted, and when each adjustment is performed, multiple measurements are performed to calculate the standard deviation of the sample. When the azimuth standard deviation is calculated, the reflected power in different azimuth is set according to the antenna pattern, and then the azimuth sample standard deviation is calculated by measuring for a plurality of times during each adjustment.

In summary, the expansion area of the first detection point can be determined according to the expansion area of the radial distance, the expansion area of the azimuth angle and the expansion area of the pitch angle.

4. Association with

In the application, when the second detection points falling in the corresponding area of the first detection point are associated with the first detection point, if a plurality of second detection points fall in the expansion area of the first detection point, the second detection point with the maximum signal to noise ratio in the expansion area is determined, and the second detection point with the maximum signal to noise ratio is used as the second detection point associated with the first detection point.

For example, the extended area of the first detection point (4, 5, 10) is [ (4-0.2, 4+0.2), (5-0.3, 5+0.3), (10-0.1, 10+0.1) ], and the second detection point in the extended area is determined, if there are detection points A, B, C and D in the extended area, wherein the signal to noise ratio of the A point is 124, the signal to noise ratio of the B point is 106, the signal to noise ratio of the C point is 114, and the signal to noise ratio of the D point is 103, and the A point with the maximum signal to noise ratio is used as the second detection point related to the first detection point according to the signal to noise ratio of the detection points A, B, C and D.

5. Fusion of

In the present application, when information fusion is performed between a first detection point and a second detection point that are associated with each other, a step as shown in fig. 9 is performed for each of the second detection points, in which:

in step 901, taking the physical parameter information of the first detection point associated with the second detection point as the physical parameter information of the fusion detection point corresponding to the second detection point;

In step 902, the coordinates of the second detection point after spatial synchronization are used as the coordinates of the fusion detection point corresponding to the second detection point;

in step 903, the fusion detection point is formed based on the physical parameter information of the fusion detection point and the coordinates of the fusion detection point.

For example, the first detection point A and the second detection point B are associated detection points, the physical parameter information of the first detection point A is Doppler speed information, RCS, trace quality and a first timestamp, the signal to noise ratio is used as the physical parameter information of the fusion detection point C, and the coordinates of the second detection zone you B are used as the coordinates of the fusion detection zone you C.

6. Determining heading angle

In the application, because more than one moving vehicle appears in the target scene, before the initial course angle of the vehicle is determined based on the fusion detection point cloud, the fusion detection point cloud needs to be subjected to segmentation processing, and a pre-trained segmentation model is adopted for the time of the segmentation processing of the fusion detection point cloud. The segmentation model in the application can be a transducer model or a depth network model (Deep Neural Networks, DNN), and when the segmentation model is trained, a conventional network model training method can be adopted, for example, a point cloud containing a plurality of vehicles and a segmentation result of the point cloud are firstly obtained, the point cloud is used as an input of DNN, the segmentation result is used as an expected output to train the DD model, and parameters of the DNN model are adjusted according to a difference between the output result and the segmentation result until training converges. The application does not limit the method for training the network model, and the technician can set the training method according to the requirements.

In the present application, the determination of the heading angle of each vehicle based on the fusion detection point may be implemented as steps as shown in fig. 10, in which:

In step 1001, determining an initial heading angle of a vehicle based on a fusion detection point cloud;

In order to avoid the waste of calculation force caused by the fact that all fusion detection point clouds enter subsequent calculation, filtering the fusion detection point clouds before determining an initial course angle of a vehicle is needed, and removing the dead point clouds in the fusion detection point clouds, the method can be concretely implemented in the steps of determining the value of the absolute Doppler speed of each fusion detection point in the fusion detection point clouds to judge whether the fusion detection point clouds move or not, for example, if fusion detection points with the absolute Doppler value being different from zero exist, the fusion detection point clouds are considered to be moving, and if fusion detection points with the absolute Doppler value being different from zero do not exist in the fusion detection point clouds, the fusion detection point clouds are considered to be stationary point clouds, and the fusion detection point clouds are removed.

In addition to determining the motion state of the fusion detection point cloud according to the absolute Doppler value of the fusion detection point, whether the point cloud moves or not can be determined according to the position information of the fusion detection points in the front and rear two frames of fusion detection point clouds, specifically, the method can be implemented by determining the position information of each fusion detection point in the current frame of fusion detection point cloud and determining the position information of each fusion detection point in the previous frame of fusion detection point cloud, and if the fusion detection point with the position changed exists, the fusion detection point cloud can be considered to be moving.

When an initial course angle is determined for the screened fusion detection point clouds, shape estimation can be performed on each segmented fusion detection point cloud, for example, a plane with the same height is taken, then a method of searching rectangular boundary filtering (SEARCH RECTANGLE Board Filter, SRBF) is used, course angle azimuth values are between-180 degrees and 180 degrees, rough search can be firstly adopted, then fine search is adopted, the rough search angle interval is 2 degrees, the fine search is 0.2 degree, the rough search and the fine search are the same, and the rough search is described below by taking the rough search as an example:

As shown in FIG. 11, the azimuth value of the selected course angle is 0 degrees, the X axis is the direction pointed by the angle, the Y axis is the direction perpendicular to the X axis, the right rule is satisfied, then the fusion detection point cloud is projected under the coordinate, and the maximum values of the abscissa, the maximum value and the ordinate are calculated to be fit into a rectangle. For each fusion detection in the fusion detection point cloud, calculating the distance from the point to each boundary of the fitting rectangle, wherein the distance is a positive value. The smallest one of them is selected, and then the smallest distances of all points are accumulated, so that the accumulated smallest distance under the angle can be obtained.

For example, taking the point a in fig. 11 as an example, distances between four boundaries of the point a are l1, l2, l3 and l4, respectively, where l1 is the minimum distance, and then l1 is selected as the minimum distance of the point a.

And (3) performing the operation on all angles, then selecting the angle which can enable the minimum distance sum to be minimum, taking the angle as the initial course angle of the vehicle, and performing the fine search process as above, and avoiding redundant description.

In a specific implementation, the length or width of the rectangle may be smaller, so when the length or width of the rectangle is smaller than a certain threshold value, the rectangle can be considered to be an edge, and when the course angle is calculated, the course angle of the point cloud of the previous frame can be used as the course angle of the fusion detection point cloud of the current frame.

In step 1002, screening out a target fusion detection point according to the signal-to-noise ratio of each fusion detection point in the fusion detection point cloud;

In order to ensure the accuracy of the determined course angle, the method and the device select the target fusion detection points based on the signal to noise ratio, and can be concretely implemented by sequentially selecting four fusion detection points with the maximum signal to noise ratio as the target fusion detection points. A signal-to-noise ratio threshold value can also be set, and a fusion detection point with the signal-to-noise ratio larger than the threshold value is used as a fusion detection point. The application is not limited in this regard.

In step 1003, determining a wheel position difference of the vehicle based on the fusion detection point cloud and the fusion detection point cloud of the previous frame;

When the wheel position difference of the vehicle is determined, cluster analysis can be carried out on the fusion detection point cloud, the outline of the vehicle is obtained based on the fusion detection point cloud, the measured wheel position is obtained based on the outline of the vehicle, then the same processing is carried out on the previous frame of fusion detection point cloud, the wheel position of the previous frame of fusion detection point cloud is obtained, and further the wheel position difference of the vehicle can be obtained.

The wheel position in the fusion detection point cloud can be determined based on the DNN network model, and then the wheel position difference between the front moment and the rear moment can be obtained by combining the wheel position in the fusion detection point cloud of the previous frame. The position of the wheel may also be determined with reference to a common difference in position between the wheel and the vehicle body; the method for obtaining the wheel position difference is not limited, and all the methods for obtaining the wheel position difference are applicable to the method and can be selected by technicians according to requirements.

In the application, in order to further enable the determined course angle to be more accurate, the wheel position difference is the position difference of the driving wheels, namely, the wheel position difference is the wheel position difference of the rear wheels if the vehicle is a rear-drive vehicle, the wheel position difference is the wheel position difference of the front wheels if the vehicle is a front-drive vehicle, and the wheel position difference is the wheel position difference of four wheels if the vehicle is a four-drive vehicle.

In step 1004, the initial course angle, the target fusion detection point and the wheel position difference are input into a pre-trained motion model to obtain the course angle of the vehicle.

The following describes an example of inputting four target fusion detection points, namely, a wheel position difference of a rear wheel of a rear-drive vehicle:

The motion model may select a steering model (Constant Turn Rate and Velocity, CTRV), the filtering mode may select an Extended kalman filter (Extended KALMAN FILTER, EKF), the output of the motion model is V, yawrate, orientation, where V represents the body speed, yawrate represents the body yaw rate, orientation represents the heading angle of the vehicle, the input is Orientation Mea, VDoppler1, VDoppler2, VDoppler3, VDoppler, ΔΔ, ΔΔo, wherein orientation_ Mea is the initial heading angle, VDoppler1, VDoppler2, VDoppler, VDoppler4 is the Doppler information of the target fusion point, Δmesh, ΔΔ is the wheel position difference, and when the Extended kalman filter method is used to calculate, the measurement variance and the system variance are also needed. The measurement variance of the orientation_ Mea can be obtained by accumulating the intensity of the fusion detection points in the fusion detection point cloud and the sample variance when the shape of the fusion detection point cloud is estimated, and the system variance of VDoppler is determined according to the signal-to-noise ratio of the fusion detection points in the fusion detection point cloud. The system variance can be obtained by integrating the output result of the motion model at the previous moment with the deviation of the actual course angle of the vehicle and the deviation of the actual course angle of the vehicle, for example, the difference value of the deviation at the previous moment and the next moment can be calculated, and the system variance is determined based on the relation between the difference value and the threshold value.

For easy understanding, the following describes in detail the overall flow of a heading angle estimation method according to an embodiment of the present application, as shown in fig. 12, in which:

Step 1201, continuously detecting a target scene by adopting a millimeter wave radar to obtain a continuous multi-frame first detection point cluster, and continuously detecting the target scene by adopting a laser radar to obtain a continuous multi-frame second detection point cloud;

in step 1202, performing time synchronization processing and space synchronization processing on the first detection point cluster and the second detection point cloud to obtain the first detection point cluster and the second detection point cloud which have association relations in time and space;

In step 1203, performing area expansion on the coordinates of each first detection point in the first detection point cluster after the synchronization processing according to the standard deviation to obtain an expansion area of the first detection point, and determining a second detection point falling in the expansion area according to the coordinates of the second detection point;

In step 1204, associating the second detection point falling in the expansion area with the first detection point, and performing information fusion on the first detection point and the second detection point which are associated with each other to obtain a fusion detection point;

In step 1205, performing segmentation processing on a fusion detection point cloud formed by fusion detection points to obtain a fusion detection point cloud corresponding to each vehicle in a target scene;

In step 1206, determining an initial heading angle of the vehicle based on the fusion detection point cloud;

in step 1207, screening out a target fusion detection point according to the signal-to-noise ratio of each fusion detection point in the fusion detection point cloud;

In step 1208, determining a wheel position difference of the vehicle based on the fusion detection point cloud and the fusion detection point cloud of the previous frame;

In step 1209, the initial heading angle, the target fusion detection point and the wheel position difference are input into a pre-trained motion model to obtain the heading angle of the vehicle.

As shown in fig. 13, based on the same inventive concept, a heading angle determining apparatus 1300 is proposed, comprising:

the detection module 13001 is configured to continuously detect a target scene by using a millimeter wave radar to obtain a continuous multi-frame first detection point cluster, and continuously detect the target scene by using a laser radar to obtain a continuous multi-frame second detection point cloud, where the target scene includes at least one vehicle;

The synchronization module 13002 is configured to perform time synchronization processing and space synchronization processing on the first detection point cluster and the second detection point cloud to obtain a first detection point cluster and a second detection point cloud that have an association relationship in time and space;

The expansion module 13003 is configured to perform area expansion on coordinates of each first detection point in the first detection point cluster after the synchronization processing according to a standard deviation to obtain an expansion area of the first detection point, and determine a second detection point falling in the expansion area according to coordinates of a second detection point;

The fusion module 13004 is used for associating a second detection point falling in the expansion area with the first detection point and carrying out information fusion on the first detection point and the second detection point which are associated with each other to obtain a fusion detection point;

the course angle determining module 13005 is configured to segment a fusion detection point cloud formed by the fusion detection points to obtain a fusion detection point cloud corresponding to each vehicle in the target scene, and determine a course angle of each vehicle based on the fusion detection point cloud.

In some possible embodiments, the synchronization module 13002, when performing time synchronization processing on the first detection point cluster and the second detection point cloud, is configured to:

In some possible embodiments, the synchronization module 13002, when executing an associated first detection point cluster that determines that a second detection point cloud corresponding to the second timestamp has an association relationship based on the first calculated timestamp, the second calculated timestamp, and the second timestamp, is configured to:

In some possible embodiments, the synchronization module 13002, when executing the determination of the associated first detection point cluster based on the first detection point cluster corresponding to the first calculated timestamp and the first detection point cluster corresponding to the second calculated timestamp, is configured to:

In some possible embodiments, the synchronization module 13002, when performing spatial synchronization processing on the first detection point cluster and the second detection point cloud, is configured to:

The expansion module 13003, when performing area expansion on the coordinates of each first detection point in the first detection point cluster after the synchronization processing according to the standard deviation, is configured to:

In some possible embodiments, the fusion module 13004, when executing associating a second detection point falling in the corresponding region of the first detection point with the first detection point, is configured to:

In some possible embodiments, the first detection point cluster includes a plurality of first detection points, the second detection point cloud includes a plurality of second detection points, and the fusion module 13004 performs information fusion between the first detection points and the second detection points that are associated with each other to obtain a fusion detection point, including:

The following procedure is performed for each second detection point:

In some possible embodiments, the course angle determination module 13005, when executing the determination of the course angle of each vehicle based on the fusion detection point cloud, is configured to:

Performing, for each frame of fusion detection point cloud of each vehicle:

Having described the heading angle determination method and apparatus of an exemplary embodiment of the present application, next, an electronic device according to another exemplary embodiment of the present application is described.

Those skilled in the art will appreciate that the various aspects of the application may be implemented as a system, method, or program product. Accordingly, aspects of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects that may be referred to herein collectively as a "circuit," module "or" system.

In some possible embodiments, an electronic device according to the application may comprise at least one processor and at least one memory. Wherein the memory stores program code that, when executed by the processor, causes the processor to perform the steps in the heading angle determination method according to various exemplary embodiments of the application described above in this specification.

An electronic device 130 according to this embodiment of the present application is described below with reference to fig. 14. The electronic device 130 shown in fig. 14 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present application.

As shown in fig. 14, the electronic device 130 is embodied in the form of a general-purpose electronic device. The components of the electronic device 130 may include, but are not limited to, the at least one processor 131, the at least one memory 132, and a bus 133 connecting the various system components, including the memory 132 and the processor 131.

Bus 133 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, and a local bus using any of a variety of bus architectures.

Memory 132 may include readable media in the form of volatile memory such as Random Access Memory (RAM) 1321 and/or cache memory 1322, and may further include Read Only Memory (ROM) 1323.

Memory 132 may also include a program/utility 1325 having a set (at least one) of program modules 1324, such program modules 1324 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

The electronic device 130 may also communicate with one or more external devices 134 (e.g., keyboard, pointing device, etc.), one or more devices that enable a user to interact with the electronic device 130, and/or any device (e.g., router, modem, etc.) that enables the electronic device 130 to communicate with one or more other electronic devices. Such communication may occur through an input/output (I/O) interface 135. Also, electronic device 130 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 136. As shown, network adapter 136 communicates with other modules for electronic device 130 over bus 133. It should be appreciated that although not shown in FIG. 14, other hardware and/or software modules may be used in connection with electronic device 130, including, but not limited to, microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

In some possible embodiments, aspects of a heading angle determination method provided by the present application may also be implemented in the form of a program product comprising program code for causing a computer device to carry out the steps of a heading angle determination method according to various exemplary embodiments of the present application as described in the present specification, when the program product is run on the computer device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of a readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The program product for heading angle determination of embodiments of the present application may employ a portable compact disc read only memory (CD-ROM) and include program code and may be run on an electronic device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the consumer electronic device, partly on the consumer electronic device, as a stand-alone software package, partly on the consumer electronic device, partly on the remote electronic device, or entirely on the remote electronic device or server. In the case of remote electronic devices, the remote electronic device may be connected to the consumer electronic device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external electronic device (e.g., connected through the internet using an internet service provider).

It should be noted that although several units or sub-units of the apparatus are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. Indeed, the features and functions of two or more of the elements described above may be embodied in one element in accordance with embodiments of the present application. Conversely, the features and functions of one unit described above may be further divided into a plurality of units to be embodied.

Furthermore, although the operations of the methods of the present application are depicted in the drawings in a particular order, this is not required or suggested that these operations must be performed in this particular order or that all of the illustrated operations must be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims

1. A heading angle determination method, characterized in that the method comprises:

The method comprises the steps of carrying out area expansion on coordinates of each first detection point in a first detection point cluster after synchronous processing according to standard deviation to obtain an expansion area of the first detection point, and determining a second detection point falling in the expansion area according to coordinates of a second detection point, wherein the standard deviation is a standard deviation of physical parameters related to the first detection point;

The method comprises the steps of dividing fusion detection point clouds formed by the fusion detection points to obtain fusion detection point clouds corresponding to each vehicle in a target scene, determining an initial course angle of each vehicle based on the fusion detection point clouds, screening out target fusion detection points according to the signal to noise ratio of each fusion detection point in the fusion detection point clouds, determining the wheel position difference of each vehicle based on the fusion detection point clouds and the fusion detection point clouds of the previous frame, and inputting the initial course angle, the target fusion detection points and the wheel position difference into a pre-trained motion model to obtain the course angle of each vehicle.

2. The method of claim 1, wherein the time synchronizing the first cluster of detection points and the second cloud of detection points comprises:

Determining a first calculation time stamp and a second calculation time stamp corresponding to each second time stamp according to each second time stamp, wherein the first calculation time stamp is obtained by marking a first detection point cluster of each frame obtained by continuously detecting the target scene by the millimeter wave radar according to a first preset frequency, and the second time stamp is obtained by marking a second detection point cloud of each frame obtained by continuously detecting the target scene by the laser radar according to a second preset frequency;

3. The method of claim 2, wherein the determining, based on the first calculated timestamp, the second calculated timestamp, and the second timestamp, an associated first detection point cluster having an association with a second detection point cloud corresponding to the second timestamp, comprises:

Obtaining a third time stamp, wherein the third time stamp is obtained by determining that the laser radar marks a first time stamp and a second time stamp and then marks the first time stamp and the second time stamp at a second preset frequency at a first time interval;

4. The method of claim 3, wherein the determining an associated first cluster of detection points based on the first cluster of detection points corresponding to the first calculated timestamp and the first cluster of detection points corresponding to the second calculated timestamp comprises:

performing linear interpolation processing on the first detection point cluster corresponding to the first calculated timestamp and the first detection point cluster corresponding to the second calculated timestamp to obtain the associated first detection point cluster, or

5. The method of claim 1, wherein spatially synchronizing the first cluster of detection points and the second cloud of detection points comprises:

6. The method according to claim 5, characterized in that the rotation parameter and the translation parameter are obtained according to the following method:

7. The method of claim 1, wherein the step of determining the position of the substrate comprises,

The method for determining the expansion area of each first detection point in the synchronous processed first detection point cluster according to the standard deviation in the expansion areas of radial distance, azimuth angle and pitch angle comprises the following steps:

performing the following for each first detection point in the first detection point cluster:

8. The method of claim 1, wherein the associating the second detection point with the first detection point that falls within the extension area comprises:

9. The method of claim 1, wherein the first cluster of detection points comprises a plurality of first detection points, the second cloud of detection points comprises a plurality of second detection points, the fusing of information between the first and second detection points to obtain a fused detection point comprises:

The following procedure is performed for each second detection point:

10. A heading angle determining apparatus, characterized in that the apparatus comprises:

the system comprises an expansion module, a synchronization module, a detection module and a detection module, wherein the expansion module is used for carrying out area expansion on the coordinates of each first detection point in a first detection point cluster after the synchronization processing according to a standard deviation to obtain an expansion area of the first detection point, and determining a second detection point falling in the expansion area according to the coordinates of the second detection point;

The course angle determining module is used for carrying out segmentation processing on fusion detection point clouds formed by the fusion detection points to obtain fusion detection point clouds corresponding to each vehicle in the target scene, and executing the fusion detection point clouds for each frame of each vehicle, wherein the initial course angle of each vehicle is determined based on the fusion detection point clouds, the target fusion detection points are screened out according to the signal to noise ratio of each fusion detection point in the fusion detection point clouds, the wheel position difference of each vehicle is determined based on the fusion detection point clouds and the fusion detection point clouds of the previous frame, and the initial course angle, the target fusion detection points and the wheel position difference are input into a pre-trained motion model to obtain the course angle of each vehicle.

11. An electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to implement the method of any of claims 1-9.

12. A computer storage medium, characterized in that the computer storage medium stores a computer program for enabling a computer to perform the method according to any one of claims 1 to 9.