CN114663589B - Three-dimensional modeling method, device and storage medium based on mobile luggage - Google Patents
Three-dimensional modeling method, device and storage medium based on mobile luggage Download PDFInfo
- Publication number
- CN114663589B CN114663589B CN202210289591.3A CN202210289591A CN114663589B CN 114663589 B CN114663589 B CN 114663589B CN 202210289591 A CN202210289591 A CN 202210289591A CN 114663589 B CN114663589 B CN 114663589B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- initial
- depth
- aggregated
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three-dimensional [3D] modelling for computer graphics
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30112—Baggage; Luggage; Suitcase
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30244—Camera pose
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the technical field of target detection and discloses a three-dimensional modeling method, equipment and a storage medium based on moving luggage, wherein the method comprises the steps of collecting a plurality of depth pictures in the moving process of the target luggage, and determining an initial depth picture and a depth picture to be aggregated from the initial depth picture to extract an initial point cloud and a point cloud to be aggregated; the method comprises the steps of determining an alignment coordinate system according to an initial point cloud, extracting an initial voxel set according to the initial point cloud, calculating horizontal displacement and normal vector of a target luggage corresponding to a depth picture to be aggregated, converting the point cloud to be aggregated into a conversion point cloud under the alignment coordinate system, extracting the voxel set to be aggregated according to the conversion point cloud, and constructing a three-dimensional grid model by utilizing the initial voxel set and each voxel set to be aggregated. The application utilizes the unidirectional motion characteristic of the luggage on the plane, applies the unidirectional motion characteristic as a constraint condition to pose calculation of the depth camera, reduces the error of the estimation of the relative pose of the depth camera and the moving object, and solves the problem of three-dimensional modeling of the moving luggage.
Description
Technical Field
The present application relates to the field of object detection technologies, and in particular, to a method, an apparatus, and a storage medium for three-dimensional modeling based on moving baggage.
Background
In the process of baggage check, the state of baggage is usually required to be tracked and detected, so that baggage with different hardness can be checked in real time to check whether the baggage is damaged, thereby ensuring the safe check of the baggage.
At present, a three-dimensional modeling technology is generally adopted to detect whether the luggage is damaged, and the real-time checking of the luggage is performed with three-dimensional modeling, so that the built three-dimensional model can be utilized to judge whether the luggage is damaged.
However, existing three-dimensional modeling generally requires that the baggage be stationary, that a depth image of the baggage be acquired by moving a depth camera, and that point cloud aggregation be achieved by computing the pose of the camera, thereby achieving three-dimensional modeling. In a baggage consignment scenario, conventional three-dimensional modeling has failed to meet the requirements for three-dimensional modeling of moving baggage.
Disclosure of Invention
The application mainly aims to provide a three-dimensional modeling method, equipment and storage medium based on moving baggage, which aim to realize rapid three-dimensional modeling of the moving baggage.
In a first aspect, the present application provides a three-dimensional modeling method based on moving baggage, comprising:
In the moving process of the target luggage, acquiring a plurality of depth pictures of the target luggage at a plurality of angles;
Determining the depth picture with the earliest acquisition time as an initial depth picture, and determining the depth picture with the acquisition time after the acquisition time of the initial depth picture as a depth picture to be aggregated;
Acquiring a point cloud corresponding to the target luggage from the initial depth picture as an initial point cloud, and acquiring the point cloud corresponding to the target luggage from the depth picture to be aggregated as a point cloud to be aggregated;
Determining a world coordinate system corresponding to the initial point cloud as an alignment coordinate system, and acquiring voxels of the initial point cloud as an initial voxel set;
calculating the horizontal displacement of the target luggage according to the depth picture to be aggregated and the initial depth picture, and calculating the normal vector of the plane of the target luggage according to the depth picture to be aggregated;
Converting the point cloud to be polymerized into a conversion point cloud corresponding to the alignment coordinate system by utilizing the horizontal displacement and the normal vector, and acquiring voxels of the conversion point cloud as a voxel set to be polymerized;
and constructing a three-dimensional grid model according to the initial voxel set and each voxel set to be aggregated, and carrying out mapping treatment on the three-dimensional grid model to obtain a target three-dimensional model corresponding to the target luggage.
In a second aspect, the present application also provides a terminal device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the mobile baggage based three-dimensional modeling method as described above.
In a third aspect, the present application also provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a three-dimensional modeling method based on moving baggage as described above.
The application provides a three-dimensional modeling method, equipment and a storage medium based on moving luggage, wherein in the application, a plurality of depth pictures with a plurality of angles are acquired in the moving process of target luggage, and in the process of carrying out aggregation processing on the depth pictures, the horizontal displacement and normal vector of the target luggage are calculated, so that the point cloud overlapping is realized by combining the horizontal displacement and the normal vector when the coordinate system is converted on the depth pictures, and a target three-dimensional model is constructed. According to the technical scheme provided by the application, the horizontal displacement and the normal vector of the target baggage among the depth pictures are combined, the horizontal displacement and the normal vector are used as constraint conditions to be applied to pose calculation of the depth camera, the error of relative pose estimation of the depth camera and the target object is reduced, and the accurate aggregation among a plurality of depth pictures is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are 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 a schematic flow chart of steps of a three-dimensional modeling method based on mobile baggage according to an embodiment of the present application;
FIG. 2 is a schematic view of an application scenario of a three-dimensional modeling method based on mobile baggage according to an embodiment of the present application;
fig. 3 is a schematic block diagram of a structure of a terminal device according to an embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations. In addition, although the division of the functional modules is performed in the apparatus schematic, in some cases, the division of the modules may be different from that in the apparatus schematic.
The embodiment of the application provides a three-dimensional modeling method, equipment and storage medium based on mobile baggage.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic step flow diagram of a three-dimensional modeling method based on moving baggage according to an embodiment of the present application.
As shown in fig. 1, the three-dimensional modeling method based on moving baggage includes steps S10 to S16.
Step S10, acquiring a plurality of depth pictures of the target luggage at a plurality of angles in the moving process of the target luggage.
It is understood that the depth picture (DEPTH IMAGES) is a picture acquired by a depth camera, also referred to as a range image (RANGE IMAGES).
The application is applied to a three-dimensional modeling system of luggage, when target luggage is put on a conveyor belt, the conveyor belt drives the target luggage to move towards a preset direction, and a plurality of depth cameras arranged above the conveyor belt continuously collect a plurality of depth pictures of the target luggage at a plurality of angles in the moving process of the target luggage.
In some embodiments, the plurality of angles includes a first angle, a second angle, and a third angle;
the depth picture corresponding to the first angle at least comprises picture information of a first side surface and a second side surface of the target luggage;
The depth picture corresponding to the second angle includes at least picture information of a third side surface of the target baggage opposite to the first side surface and a fourth side surface opposite to the second side surface;
The depth picture corresponding to the third angle includes at least picture information of an upper surface of the target baggage, wherein the upper surface is connected to the first side, the second side, the third side, and the fourth side.
It will be appreciated that the first angle, the second angle and the third angle correspond to different image acquisition regions.
As shown in fig. 2, the three-dimensional modeling method based on moving baggage provided by the present application is applied to a baggage transportation system and is executed by a processor in a terminal device of the baggage transportation system.
Specifically, the baggage conveyor system includes a terminal device 20, a conveyor 21, and an image pickup device 22.
The conveyor includes a conveyor belt 210, a drive mechanism 211, a first rail 212, and a second rail 213. The first guardrail 212 and the second guardrail 213 are respectively installed on the driving mechanisms 211 at two sides of the conveyor belt 210.
The image capturing device 22 includes a first vertical bar 220, a second vertical bar 221, a cross bar 222, a first depth camera 223, a second depth camera 224, and a third depth camera 225. Wherein, the first vertical rod 220 is installed on the driving mechanism 211 near one side of the first guardrail 212, the second vertical rod 221 is installed on the driving mechanism 211 near one side of the second guardrail 213, the first end of the cross rod 222 is connected with one end of the first vertical rod 220 far away from the driving mechanism 211, and the second end of the cross rod 222 far away from the first end is connected with one end of the second vertical rod 221 far away from the driving mechanism 211.
The first depth camera 223 is mounted on a first cross bar side of the cross bar 222 near the first end, and an image capturing angle of the first depth camera 223 corresponds to the first angle 2230, for capturing a depth image of the initial conveying area of the conveyor belt 210.
The second depth camera 224 is mounted on a second cross bar side of the cross bar 222 near the second end and opposite to the first cross bar side, and an image capturing angle of the second depth camera 224 corresponds to a second angle 2240, for capturing a depth image of the last conveying area of the conveyor belt 210.
The third depth camera 225 is mounted on the middle position of the cross bar 222 near the side of the third cross bar of the conveyor belt 210, and the image capturing angle of the third depth camera 225 corresponds to the third angle 2250, for capturing a depth image of the middle conveying area of the conveyor belt 210.
The terminal device 20 is electrically connected to the first depth camera 223, the second depth camera 224, and the third depth camera 225, and is configured to receive and process depth pictures acquired by the first depth camera 223, the second depth camera 224, and the third depth camera 225.
Depth picture information including a first side 230 and a second side 231 of the target baggage 23 may be acquired by the first depth camera 223 when the target baggage 23 moves in the initial conveying region of the conveyor belt 210, depth picture information including a top region of the target baggage 23, that is, picture information of an upper surface 232 of the target baggage 23 may be acquired by the third depth camera 225 when the target baggage 23 moves in the middle conveying region of the conveyor belt 210, and depth picture information including a third side opposite to the first side 230 and a fourth side opposite to the second side 231 of the target baggage 23 may be acquired by the second depth camera when the target baggage 23 moves in the final conveying region of the conveyor belt 210.
In combination with capturing a plurality of depth pictures whose angles correspond to the first angle 2230, the second angle 2240, and the third angle 2250, picture information of the first side 230, the second side 231, the third side, the fourth side, and the upper surface 232 of the target baggage 23 may be obtained, thereby constructing a three-dimensional model of the target baggage 23.
Step S11, determining the depth picture with the earliest acquisition time as an initial depth picture, and determining the depth picture with the acquisition time after the acquisition time of the initial depth picture as a depth picture to be aggregated.
It will be appreciated that each of the plurality of depth pictures acquired for the corresponding target baggage 23 has its corresponding picture acquisition time. The depth picture with the earliest acquisition time is the initial depth picture, and other depth pictures except the initial depth picture, namely the depth pictures with the acquisition time after the acquisition time of the initial depth picture are all depth pictures to be aggregated.
In some embodiments, when the target baggage 23 is placed on the conveyor belt 210, the conveyor belt 210 drives the target baggage 23 to move from the initial conveying area to the final conveying area, the first depth image acquired by the target baggage 23 in the initial conveying area is the initial depth image, and the depth images acquired in the subsequent moving process are the depth images to be aggregated.
Step S12, acquiring a point cloud corresponding to the target luggage from the initial depth picture as an initial point cloud, and acquiring the point cloud corresponding to the target luggage from the depth picture to be aggregated as a point cloud to be aggregated.
It can be understood that, according to the attribute parameters of the depth camera for acquiring the initial depth image, the initial depth image may be converted into first integral point cloud data, where the first integral point cloud data includes not only the point cloud of the target baggage 23, but also the point cloud of the background portion other than the target baggage 23, and the point cloud corresponding to the target baggage 23 is segmented from the first integral point cloud data, so as to obtain the initial point cloud.
Similarly, according to the attribute parameters of the depth camera for collecting the depth images to be aggregated, the depth images to be aggregated can be converted into second integral point cloud data, and point cloud data corresponding to the target baggage 23 is extracted from the second integral point cloud data, so as to obtain the point cloud to be aggregated.
In some embodiments, the acquiring the point cloud corresponding to the target baggage from the initial depth image as an initial point cloud includes:
determining a target horizontal region range and a target depth range according to the acquisition angle corresponding to the initial depth picture;
Acquiring a point cloud of the initial depth picture as a first point cloud;
extracting point clouds of which the projection areas are in the range of the target horizontal area from the first point cloud to obtain a second point cloud;
and extracting a point cloud with the depth value within the target depth range from the second point cloud to obtain an initial point cloud corresponding to the target luggage.
It will be appreciated that in the present application, the distance between the depth camera responsible for taking the depth picture and the conveyor belt 210 responsible for carrying and moving the target baggage 23 is fixed, and that the depth camera is fixedly mounted on the cross bar 222 above the conveyor belt 210, on the basis of which the image acquisition area range of the depth camera is also fixed.
In addition, the range of the image capturing area of the depth camera is also larger than that of the target baggage 23, and the depth image captured by the depth camera includes not only the image elements of the target baggage 23 but also the image elements such as the conveyor belt 210, the first barrier 212 and the second barrier 213 other than the target baggage 23. And, the distance between the target baggage 23 and the depth camera is necessarily closer than the distance between the conveyor belt 210 and the depth camera.
Therefore, the corresponding target horizontal area range and the target depth range may be preset according to the corresponding acquisition angle of the depth camera for acquiring the depth image, so as to extract, from the first point cloud, a point cloud having a projection area of the target baggage 23 within the target horizontal area range and a depth value within the target depth range, so as to obtain an initial point cloud of the target baggage 23, where the depth value corresponds to a z-axis coordinate value in three-dimensional coordinates of the point cloud.
In some embodiments, the acquiring the point cloud corresponding to the target baggage from the initial depth image as an initial point cloud includes:
Acquiring a comparison depth picture according to the acquisition angle corresponding to the initial depth picture, wherein the comparison depth picture is an empty depth picture of which the camera shooting angle corresponds to the acquisition angle and the picture element does not contain the target luggage;
Acquiring a point cloud of the initial depth picture as a first point cloud, and acquiring a point cloud of the comparison depth picture as a comparison point cloud;
and removing the point cloud matched with the comparison point cloud in the first point cloud to obtain an initial point cloud corresponding to the target luggage.
It will be appreciated that the depth camera is fixedly mounted in the air area above the conveyor belt 210, and that the depth camera from which the initial depth picture was taken may be determined from the corresponding acquisition angle of the initial depth picture. When there is no baggage on the conveyor belt 210, the conveyor belt 210 is in an empty state, and at this time, the depth image acquired by the depth camera without the picture element of the target baggage 23 is a comparison depth image. And the point cloud extracted from the comparison depth picture is the comparison point cloud.
And removing the point cloud which is the same as or similar to the three-dimensional coordinates and the color values of the specific point cloud in the first point cloud, and obtaining the initial point cloud corresponding to the target luggage 23 in the initial depth picture.
And S13, determining a world coordinate system corresponding to the initial point cloud as an alignment coordinate system, and acquiring voxels of the initial point cloud as an initial voxel set.
It can be understood that the world coordinate system corresponding to the initial point cloud is an alignment coordinate system, and after the alignment coordinate system is determined, other point clouds to be aggregated can be converted into the alignment coordinate system so as to aggregate with the initial point cloud, thereby constructing the three-dimensional grid model. At this time, the voxels extracted by using the initial point cloud are the initial voxel set.
And S14, calculating the horizontal displacement of the target luggage according to the depth picture to be aggregated and the initial depth picture, and calculating the normal vector of the plane of the target luggage according to the depth picture to be aggregated.
It will be appreciated that the initial depth image and the depth image to be aggregated are taken by the depth camera during the movement of the target baggage 23, i.e. the acquisition times of the initial depth image and the depth image to be aggregated are different, and the positions of the target baggage 23 in the initial depth image and the depth image to be aggregated are also different. From the initial depth picture and the position of the target baggage 23 in the depth picture to be aggregated, a horizontal displacement of the target baggage 23 from the position in the initial depth picture to the position in the depth picture to be aggregated may be calculated.
In addition, the plane on which the conveyor belt 210 responsible for carrying and moving the target baggage 23 is the plane on which the target baggage 23 is located, and the vector represented by a straight line perpendicular to the plane on which the conveyor belt 210 is located is the normal vector of the plane. In some embodiments, the normal vector may be obtained by applying RANSAC (random sample consensus) algorithm to the depth image to be aggregated, or may be obtained by applying least square method to the depth image to be aggregated, which is not limited herein.
In some implementations, the calculating the horizontal displacement of the target baggage from the depth picture to be aggregated and the initial depth picture includes:
acquiring the horizontal moving speed of the target luggage, and acquiring the acquisition time interval between the point cloud to be aggregated and the initial point cloud;
And obtaining the horizontal displacement of the target luggage according to the product of the horizontal movement speed and the acquisition time interval.
It will be appreciated that the target baggage 23 is placed on the conveyor belt 210, and the conveyor belt 210 drives the target baggage 23 to move at an average speed, so as to obtain a horizontal moving speed of the target baggage 23. On the basis, the acquisition time interval can be determined according to the acquisition time difference between the point cloud to be aggregated and the initial point cloud. And then the product of the horizontal movement speed and the acquisition time interval is calculated, so as to obtain the horizontal displacement of the target baggage 23.
And S15, converting the point cloud to be polymerized into a conversion point cloud corresponding to the alignment coordinate system by utilizing the horizontal displacement and the normal vector, and acquiring voxels of the conversion point cloud as a voxel set to be polymerized.
It will be appreciated that the point cloud to be aggregated needs to be converted into an aligned coordinate system before the point cloud to be aggregated is aggregated into the initial point cloud to construct the three-dimensional mesh model.
In the prior art, a target baggage 23 is usually stationary, and then a depth camera is rotated around the target baggage 23 to acquire depth images, and each depth image is converted into the same coordinate system by an ICP (ITERATIVE CLOSEST POINT ) algorithm to realize point cloud aggregation and construct a three-dimensional grid model.
In the present application, however, the target baggage 23 is placed on the conveyor belt 210, and the depth image is acquired during the process that the conveyor belt 210 drives the target baggage 23 to move, and the camera for acquiring the depth image is in a stationary state. That is, in each of the acquired depth pictures, the target baggage 23 is in a moving state, and in this case, there is a case where the calculation fails due to non-convergence in converting the coordinate system for a plurality of depth pictures using the conventional ICP algorithm. The method is characterized in that the surrounding environment of the moving object is changed, so that the shape of the point cloud between frames is inconsistent, and the calculated translation matrix and rotation matrix cannot overlap the point cloud no matter how calculated by the traditional ICP algorithm, which causes that a plurality of depth pictures cannot be aggregated, so that the construction of the three-dimensional network model fails.
In the application, the characteristic that the target luggage 23 moves on a plane is utilized, and the horizontal displacement and the normal vector are used as constraint conditions to realize the conversion of the point cloud to be polymerized into the conversion point cloud under the corresponding alignment coordinate system, and then the voxels are extracted from the conversion point cloud to obtain the voxel set to be polymerized.
By the technical scheme provided by the application, the linear motion of the target luggage 23 can be converted into the relative motion of the depth camera, the coordinate system of the target luggage 23 is kept unchanged, the subsequent three-dimensional grid model construction process is simplified, and the technical effect that the mobile luggage can be rapidly modeled in three dimensions by adopting a simple depth picture acquisition device is realized.
In some embodiments, the converting the point cloud to be aggregated into a converted point cloud corresponding to the aligned coordinate system using the horizontal displacement and the normal vector includes:
Determining the number of points in the initial point cloud as a first number, and determining the number of points in the point cloud to be aggregated as a second number;
screening a minimum value from the first number and the second number as a matching number, and selecting a first point set from the initial points Yun Zhongshai according to the matching number;
screening nearest neighbor points from the point cloud to be aggregated according to the first point set to obtain a second point set;
constructing a first matrix according to the horizontal displacement;
constructing a rotation matrix, and constructing a second matrix according to the rotation matrix and the first matrix;
performing matrix transformation on each point in the first point set according to the second matrix to obtain a third point set;
Calculating a translation matrix and the rotation matrix corresponding to the third point set and the second point set when the result value of a preset deviation function is minimum, wherein the preset deviation function is related to the second point set, the third point set, the normal vector, the translation matrix and the rotation matrix;
Performing rotation transformation on the second point set by using the rotation matrix to obtain a fourth point set, and performing translation transformation on the fourth point set by using the translation matrix to obtain a fifth point set;
performing rotation transformation on the point cloud to be aggregated by using the rotation matrix to obtain a first temporary point cloud, and performing translation transformation on the first temporary point cloud by using the translation matrix to obtain a second temporary point cloud;
and calculating the average distance between the fifth point set and the first point set, and determining the second temporary point cloud as a conversion point cloud when the average distance is smaller than a preset distance.
It can be understood that the initial point cloud and the point cloud to be aggregated are point clouds of the corresponding target baggage 23 extracted from the initial depth image and the depth image to be aggregated, respectively, the number of points in the initial point cloud is a first number, and the number of points in the point cloud to be aggregated is a second number. And when the first quantity is larger than or equal to the second quantity, determining the second quantity as the matching quantity.
The first point set is a set composed of points screened from the initial point cloud, and the number of the first point set points is the same as the matching number. After the first point set is determined, the nearest points of all points in the first point set can be obtained from the point cloud to be aggregated one by one, a second point set is obtained, and the number of the second point set points is the same as the matching number and corresponds to all points in the first point set one by one.
In this embodiment, assuming that the horizontal displacement is d, the first matrix constructed from the horizontal displacement is t prior＝[d,0,0]T.
Assuming that the constructed rotation matrix is R, a second matrix constructed according to the rotation matrix R and the first matrix is: Wherein R is a3×3 rotation matrix to be determined.
Let the first set of points be x= { xl, X2,..and xi }, and let the second set of points be p= { pl, P2,..and pi }.
Each point in the first set of points is matrix transformed according to the second matrix, resulting in a third set of points, y= { yl, Y2,..sub.yi }.
Assuming that the vector is N and the matching number is N P, the preset deviation function constructed by the application is as follows:
And after the result value of the preset deviation function is minimum, the rotation matrix R and the translation matrix t are used for carrying out rotation transformation and translation transformation on the second point set respectively to obtain a fifth point set, and the rotation matrix R and the translation matrix t are used for carrying out rotation transformation and translation transformation on the point cloud to be polymerized respectively to obtain a second temporary point cloud.
At this time, if the average distance between the fifth point set and the first point set is smaller than the preset distance, it is indicated that the second temporary point cloud obtained by the rotation matrix R and the translation matrix t is converted into the same alignment coordinate system as the initial point cloud, and at this time, it may be directly determined that the second temporary point cloud is the conversion point cloud.
In some embodiments, the method further comprises:
And when the average distance is greater than or equal to the preset distance, using the temporary point cloud as the point cloud to be polymerized, and re-executing the step of screening the nearest point from the point cloud to be polymerized according to the first point set.
It can be appreciated that if the average distance between the fifth point set and the first point set is greater than or equal to the preset distance, it is indicated that the second temporary point cloud has not been converted into the alignment coordinate system, at this time, the temporary point cloud may be used as the point cloud to be aggregated, and the step of screening the nearest neighbor points from the point cloud to be aggregated according to the first point set may be re-performed until a suitable rotation matrix and translation matrix t are matched, so that the average distance between the fifth point set and the first point set is smaller than the preset distance.
And S16, constructing a three-dimensional grid model according to the initial voxel set and each voxel set to be aggregated, and carrying out mapping treatment on the three-dimensional grid model to obtain a target three-dimensional model corresponding to the target luggage.
It can be understood that after the voxel set to be aggregated of each point cloud to be aggregated under the aligned coordinate system is obtained, the initial voxel set and each voxel set to be aggregated can be aggregated to construct a three-dimensional grid model, and the three-dimensional grid model is mapped to obtain the target three-dimensional model.
In some embodiments, the mapping process of the three-dimensional grid model may be implemented using an MVS (Multi-View step) algorithm, or may be implemented by other methods according to needs, which is not limited herein.
In some embodiments, the constructing a three-dimensional grid model according to the initial voxel set and each voxel set to be aggregated includes:
calculating TSDF values and weight values of the initial voxel set and each voxel in each voxel set to be aggregated;
aggregating each voxel set to be aggregated into the initial voxel set according to the TSDF value and the weight value to obtain an aggregate result voxel set;
And identifying the isosurface of the aggregation result voxel set, and constructing a three-dimensional grid model according to the isosurface.
In some embodiments, TSDF (truncated SIGNED DISTANCE function based signed distance function) algorithms may be used to calculate TSDF values and weight values for each voxel in the initial set of voxels and each set of voxels to be aggregated. And aggregating each voxel set to be aggregated into an initial voxel set according to the TSDF value and the weight value corresponding to each voxel to obtain an aggregate result voxel set.
After the aggregate result voxel set is obtained, the equivalent surface of the voxel set can be identified according to MC (Marching Cube) algorithm to construct a three-dimensional grid model.
In the application, a plurality of depth pictures with a plurality of angles are acquired in the process of moving the target luggage 23, and the horizontal displacement and the normal vector of the target luggage 23 are calculated in the process of carrying out aggregation treatment on the depth pictures, so that the point cloud overlapping is realized by combining the horizontal displacement and the normal vector when the coordinate system is converted on the depth pictures, thereby constructing the target three-dimensional model. By the technical scheme provided by the application, the horizontal displacement and the normal vector of the target baggage 23 between the depth pictures are combined, so that the accurate aggregation among a plurality of depth pictures is realized, and the rapid three-dimensional modeling of the moving baggage is realized.
As shown in fig. 3, the terminal device 301 includes a processor 3011, a memory, and a network interface connected via a system bus, where the memory may include a storage medium 3012 and an internal memory 3015, and the storage medium 3012 may be non-volatile or volatile.
The storage medium 3012 may store an operating system and computer programs. The computer programs include program instructions that, when executed, cause the processor 3011 to perform any of the three-dimensional modeling methods based on moving baggage.
The processor 3011 is used to provide computing and control capabilities to support the operation of the overall terminal device.
The internal memory 3015 provides an environment for the execution of a computer program in the storage medium 3012 that, when executed by the processor 3011, causes the processor 3011 to perform any of a variety of three-dimensional modeling methods based on moving baggage.
The network interface is used for network communication such as transmitting assigned tasks and the like. It will be appreciated by those skilled in the art that the structure shown in fig. 3 is merely a block diagram of a portion of the structure associated with the present inventive arrangements and is not limiting of the terminal device to which the present inventive arrangements are applied, and that a particular terminal device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
It is to be appreciated that the Processor 3011 can be a central processing unit (Central Processing Unit, CPU), and the Processor 3011 can also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein in some embodiments the processor 3011 is configured to run a computer program stored in a memory to implement the steps of:
In the moving process of the target luggage, acquiring a plurality of depth pictures of the target luggage at a plurality of angles;
Determining the depth picture with the earliest acquisition time as an initial depth picture, and determining the depth picture with the acquisition time after the acquisition time of the initial depth picture as a depth picture to be aggregated;
Acquiring a point cloud corresponding to the target luggage from the initial depth picture as an initial point cloud, and acquiring the point cloud corresponding to the target luggage from the depth picture to be aggregated as a point cloud to be aggregated;
Determining a world coordinate system corresponding to the initial point cloud as an alignment coordinate system, and acquiring voxels of the initial point cloud as an initial voxel set;
calculating the horizontal displacement of the target luggage according to the depth picture to be aggregated and the initial depth picture, and calculating the normal vector of the plane of the target luggage according to the depth picture to be aggregated;
Converting the point cloud to be polymerized into a conversion point cloud corresponding to the alignment coordinate system by utilizing the horizontal displacement and the normal vector, and acquiring voxels of the conversion point cloud as a voxel set to be polymerized;
and constructing a three-dimensional grid model according to the initial voxel set and each voxel set to be aggregated, and carrying out mapping treatment on the three-dimensional grid model to obtain a target three-dimensional model corresponding to the target luggage.
In some embodiments, the processor 3011 is configured to, when acquiring a point cloud corresponding to the target baggage from the initial depth picture as an initial point cloud, implement:
determining a target horizontal region range and a target depth range according to the acquisition angle corresponding to the initial depth picture;
Acquiring a point cloud of the initial depth picture as a first point cloud;
extracting point clouds of which the projection areas are in the range of the target horizontal area from the first point cloud to obtain a second point cloud;
and extracting a point cloud with the depth value within the target depth range from the second point cloud to obtain an initial point cloud corresponding to the target luggage.
In some embodiments, the processor 3011 is configured to, when acquiring a point cloud corresponding to the target baggage from the initial depth picture as an initial point cloud, implement:
Acquiring a comparison depth picture according to the acquisition angle corresponding to the initial depth picture, wherein the comparison depth picture is an empty depth picture of which the camera shooting angle corresponds to the acquisition angle and the picture element does not contain the target luggage;
Acquiring a point cloud of the initial depth picture as a first point cloud, and acquiring a point cloud of the comparison depth picture as a comparison point cloud;
and removing the point cloud matched with the comparison point cloud in the first point cloud to obtain an initial point cloud corresponding to the target luggage.
In some implementations, the processor 3011, when calculating a horizontal displacement of the target baggage from the depth pictures to be aggregated and the initial depth pictures, is to implement:
acquiring the horizontal moving speed of the target luggage, and acquiring the acquisition time interval between the point cloud to be aggregated and the initial point cloud;
And obtaining the horizontal displacement of the target luggage according to the product of the horizontal movement speed and the acquisition time interval.
In some embodiments, the processor 3011 is configured to, when converting the point cloud to be aggregated into a converted point cloud corresponding to the aligned coordinate system using the horizontal displacement and the normal vector:
Determining the number of points in the initial point cloud as a first number, and determining the number of points in the point cloud to be aggregated as a second number;
screening a minimum value from the first number and the second number as a matching number, and selecting a first point set from the initial points Yun Zhongshai according to the matching number;
screening nearest neighbor points from the point cloud to be aggregated according to the first point set to obtain a second point set;
constructing a first matrix according to the horizontal displacement;
constructing a rotation matrix, and constructing a second matrix according to the rotation matrix and the first matrix;
performing matrix transformation on each point in the first point set according to the second matrix to obtain a third point set;
Calculating a translation matrix and the rotation matrix corresponding to the third point set and the second point set when the result value of a preset deviation function is minimum, wherein the preset deviation function is related to the second point set, the third point set, the normal vector, the translation matrix and the rotation matrix;
Performing rotation transformation on the second point set by using the rotation matrix to obtain a fourth point set, and performing translation transformation on the fourth point set by using the translation matrix to obtain a fifth point set;
performing rotation transformation on the point cloud to be aggregated by using the rotation matrix to obtain a first temporary point cloud, and performing translation transformation on the first temporary point cloud by using the translation matrix to obtain a second temporary point cloud;
and calculating the average distance between the fifth point set and the first point set, and determining the second temporary point cloud as a conversion point cloud when the average distance is smaller than a preset distance.
In some embodiments, the processor 3011 is further to implement:
And when the average distance is greater than or equal to the preset distance, using the temporary point cloud as the point cloud to be polymerized, and re-executing the step of screening the nearest point from the point cloud to be polymerized according to the first point set.
In some embodiments, the processor 3011 is configured to implement, when constructing a three-dimensional mesh model from the initial set of voxels and each of the sets of voxels to be aggregated:
calculating TSDF values and weight values of the initial voxel set and each voxel in each voxel set to be aggregated;
aggregating each voxel set to be aggregated into the initial voxel set according to the TSDF value and the weight value to obtain an aggregate result voxel set;
And identifying the isosurface of the aggregation result voxel set, and constructing a three-dimensional grid model according to the isosurface.
In some embodiments, the processor 3011, when acquiring a plurality of depth pictures of the target baggage at a plurality of angles, the plurality of angles including a first angle, a second angle, and a third angle;
the depth picture corresponding to the first angle at least comprises picture information of a first side surface and a second side surface of the target luggage;
The depth picture corresponding to the second angle includes at least picture information of a third side surface of the target baggage opposite to the first side surface and a fourth side surface opposite to the second side surface;
The depth picture corresponding to the third angle includes at least picture information of an upper surface of the target baggage, wherein the upper surface is connected to the first side, the second side, the third side, and the fourth side.
It should be noted that, for convenience and brevity of description, the specific working process of the terminal device described above may refer to the corresponding process in the foregoing embodiment of the three-dimensional modeling method based on mobile baggage, and will not be described in detail herein.
Embodiments of the present application also provide a storage medium, which is a computer readable storage medium, where a computer program is stored, where the computer program includes program instructions, where a method implemented when the program instructions are executed may refer to embodiments of the three-dimensional modeling method based on mobile baggage according to the present application.
The computer readable storage medium may be an internal storage unit of the terminal device according to the foregoing embodiment, for example, a hard disk or a memory of the terminal device. The computer-readable storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk provided on the terminal device, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like.
It is to be understood that the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. A method of three-dimensional modeling based on moving baggage, the method comprising:
In the moving process of the target luggage, acquiring a plurality of depth pictures of the target luggage at a plurality of angles;
Determining the depth picture with the earliest acquisition time as an initial depth picture, and determining the depth picture with the acquisition time after the acquisition time of the initial depth picture as a depth picture to be aggregated;
Acquiring a point cloud corresponding to the target luggage from the initial depth picture as an initial point cloud, and acquiring the point cloud corresponding to the target luggage from the depth picture to be aggregated as a point cloud to be aggregated;
Determining a world coordinate system corresponding to the initial point cloud as an alignment coordinate system, and acquiring voxels of the initial point cloud as an initial voxel set;
calculating the horizontal displacement of the target luggage according to the depth picture to be aggregated and the initial depth picture, and calculating the normal vector of the plane of the target luggage according to the depth picture to be aggregated;
Converting the point cloud to be polymerized into a conversion point cloud corresponding to the alignment coordinate system by utilizing the horizontal displacement and the normal vector, and acquiring voxels of the conversion point cloud as a voxel set to be polymerized;
and constructing a three-dimensional grid model according to the initial voxel set and each voxel set to be aggregated, and carrying out mapping treatment on the three-dimensional grid model to obtain a target three-dimensional model corresponding to the target luggage.
2. The method according to claim 1, wherein the obtaining, from the initial depth picture, a point cloud corresponding to the target baggage as an initial point cloud includes:
determining a target horizontal region range and a target depth range according to the acquisition angle corresponding to the initial depth picture;
Acquiring a point cloud of the initial depth picture as a first point cloud;
extracting point clouds of which the projection areas are in the range of the target horizontal area from the first point cloud to obtain a second point cloud;
and extracting a point cloud with the depth value within the target depth range from the second point cloud to obtain an initial point cloud corresponding to the target luggage.
3. The method according to claim 1, wherein the obtaining, from the initial depth picture, a point cloud corresponding to the target baggage as an initial point cloud includes:
Acquiring a comparison depth picture according to the acquisition angle corresponding to the initial depth picture, wherein the comparison depth picture is an empty depth picture of which the camera shooting angle corresponds to the acquisition angle and the picture element does not contain the target luggage;
Acquiring a point cloud of the initial depth picture as a first point cloud, and acquiring a point cloud of the comparison depth picture as a comparison point cloud;
and removing the point cloud matched with the comparison point cloud in the first point cloud to obtain an initial point cloud corresponding to the target luggage.
4. A method according to any of claims 1-3, wherein said calculating a horizontal displacement of the target baggage from the depth pictures to be aggregated and the initial depth pictures comprises:
acquiring the horizontal moving speed of the target luggage, and acquiring the acquisition time interval between the point cloud to be aggregated and the initial point cloud;
And obtaining the horizontal displacement of the target luggage according to the product of the horizontal movement speed and the acquisition time interval.
5. The method of claim 4, wherein said converting said point cloud to be aggregated into a converted point cloud corresponding to said aligned coordinate system using said horizontal displacement and said normal vector comprises:
Determining the number of points in the initial point cloud as a first number, and determining the number of points in the point cloud to be aggregated as a second number;
screening a minimum value from the first number and the second number as a matching number, and selecting a first point set from the initial points Yun Zhongshai according to the matching number;
screening nearest neighbor points from the point cloud to be aggregated according to the first point set to obtain a second point set;
constructing a first matrix according to the horizontal displacement;
constructing a rotation matrix, and constructing a second matrix according to the rotation matrix and the first matrix;
performing matrix transformation on each point in the first point set according to the second matrix to obtain a third point set;
Calculating a translation matrix and the rotation matrix corresponding to the third point set and the second point set when the result value of a preset deviation function is minimum, wherein the preset deviation function is related to the second point set, the third point set, the normal vector, the translation matrix and the rotation matrix;
Performing rotation transformation on the second point set by using the rotation matrix to obtain a fourth point set, and performing translation transformation on the fourth point set by using the translation matrix to obtain a fifth point set;
performing rotation transformation on the point cloud to be aggregated by using the rotation matrix to obtain a first temporary point cloud, and performing translation transformation on the first temporary point cloud by using the translation matrix to obtain a second temporary point cloud;
and calculating the average distance between the fifth point set and the first point set, and determining the second temporary point cloud as a conversion point cloud when the average distance is smaller than a preset distance.
6. The method of claim 5, wherein the method further comprises:
And when the average distance is greater than or equal to the preset distance, using the temporary point cloud as the point cloud to be polymerized, and re-executing the step of screening the nearest point from the point cloud to be polymerized according to the first point set.
7. The method of claim 6, wherein constructing a three-dimensional mesh model from the initial set of voxels and each of the sets of voxels to be aggregated comprises:
calculating TSDF values and weight values of the initial voxel set and each voxel in each voxel set to be aggregated;
aggregating each voxel set to be aggregated into the initial voxel set according to the TSDF value and the weight value to obtain an aggregate result voxel set;
And identifying the isosurface of the aggregation result voxel set, and constructing a three-dimensional grid model according to the isosurface.
8. The method of claim 7, wherein the plurality of angles comprises a first angle, a second angle, and a third angle;
the depth picture corresponding to the first angle at least comprises picture information of a first side surface and a second side surface of the target luggage;
The depth picture corresponding to the second angle includes at least picture information of a third side surface of the target baggage opposite to the first side surface and a fourth side surface opposite to the second side surface;
The depth picture corresponding to the third angle includes at least picture information of an upper surface of the target baggage, wherein the upper surface is connected to the first side, the second side, the third side, and the fourth side.
9. A terminal device, characterized in that it comprises a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for enabling a connection communication between the processor and the memory, wherein the computer program, when being executed by the processor, implements the steps of the three-dimensional modeling method based on mobile baggage according to any one of claims 1 to 8.
10. A storage medium for computer readable storage, characterized in that the storage medium stores one or more programs executable by one or more processors to implement the steps of the mobile baggage based three-dimensional modeling method of any of claims 1 to 8.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411780448.XA CN119762670A (en) | 2022-03-23 | 2022-03-23 | Point cloud conversion method, device and storage medium based on mobile luggage |
| CN202411769025.8A CN119762669A (en) | 2022-03-23 | 2022-03-23 | Baggage conveyor system |
| CN202411765750.8A CN119762668A (en) | 2022-03-23 | 2022-03-23 | Point cloud conversion method, device and storage medium based on mobile luggage |
| CN202210289591.3A CN114663589B (en) | 2022-03-23 | 2022-03-23 | Three-dimensional modeling method, device and storage medium based on mobile luggage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210289591.3A CN114663589B (en) | 2022-03-23 | 2022-03-23 | Three-dimensional modeling method, device and storage medium based on mobile luggage |
Related Child Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411765750.8A Division CN119762668A (en) | 2022-03-23 | 2022-03-23 | Point cloud conversion method, device and storage medium based on mobile luggage |
| CN202411769025.8A Division CN119762669A (en) | 2022-03-23 | 2022-03-23 | Baggage conveyor system |
| CN202411780448.XA Division CN119762670A (en) | 2022-03-23 | 2022-03-23 | Point cloud conversion method, device and storage medium based on mobile luggage |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114663589A CN114663589A (en) | 2022-06-24 |
| CN114663589B true CN114663589B (en) | 2025-01-07 |
Family
ID=82030832
Family Applications (4)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210289591.3A Active CN114663589B (en) | 2022-03-23 | 2022-03-23 | Three-dimensional modeling method, device and storage medium based on mobile luggage |
| CN202411780448.XA Pending CN119762670A (en) | 2022-03-23 | 2022-03-23 | Point cloud conversion method, device and storage medium based on mobile luggage |
| CN202411769025.8A Pending CN119762669A (en) | 2022-03-23 | 2022-03-23 | Baggage conveyor system |
| CN202411765750.8A Pending CN119762668A (en) | 2022-03-23 | 2022-03-23 | Point cloud conversion method, device and storage medium based on mobile luggage |
Family Applications After (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411780448.XA Pending CN119762670A (en) | 2022-03-23 | 2022-03-23 | Point cloud conversion method, device and storage medium based on mobile luggage |
| CN202411769025.8A Pending CN119762669A (en) | 2022-03-23 | 2022-03-23 | Baggage conveyor system |
| CN202411765750.8A Pending CN119762668A (en) | 2022-03-23 | 2022-03-23 | Point cloud conversion method, device and storage medium based on mobile luggage |
Country Status (1)
| Country | Link |
|---|---|
| CN (4) | CN114663589B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120580210A (en) * | 2025-05-28 | 2025-09-02 | 四川蓉电科技发展有限公司 | Airport luggage damage detection and recording equipment based on machine vision recognition |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201701383D0 (en) * | 2017-01-27 | 2017-03-15 | Ucl Business Plc | Apparatus, method and system for alignment of 3D datasets |
| CN113506373A (en) * | 2021-06-29 | 2021-10-15 | 超节点创新科技(深圳)有限公司 | Real-time luggage three-dimensional modeling method, electronic device and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3073043B1 (en) * | 2017-10-27 | 2019-11-15 | Tiama | METHOD AND INSTALLATION FOR ONLINE DIMENSIONAL CONTROL OF MANUFACTURED OBJECTS |
| WO2021134296A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳元戎启行科技有限公司 | Obstacle detection method and apparatus, and computer device and storage medium |
-
2022
- 2022-03-23 CN CN202210289591.3A patent/CN114663589B/en active Active
- 2022-03-23 CN CN202411780448.XA patent/CN119762670A/en active Pending
- 2022-03-23 CN CN202411769025.8A patent/CN119762669A/en active Pending
- 2022-03-23 CN CN202411765750.8A patent/CN119762668A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201701383D0 (en) * | 2017-01-27 | 2017-03-15 | Ucl Business Plc | Apparatus, method and system for alignment of 3D datasets |
| CN113506373A (en) * | 2021-06-29 | 2021-10-15 | 超节点创新科技(深圳)有限公司 | Real-time luggage three-dimensional modeling method, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119762669A (en) | 2025-04-04 |
| CN114663589A (en) | 2022-06-24 |
| CN119762670A (en) | 2025-04-04 |
| CN119762668A (en) | 2025-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fathi et al. | Automated sparse 3D point cloud generation of infrastructure using its distinctive visual features | |
| US9483703B2 (en) | Online coupled camera pose estimation and dense reconstruction from video | |
| US9715761B2 (en) | Real-time 3D computer vision processing engine for object recognition, reconstruction, and analysis | |
| CN110111388B (en) | Three-dimensional object pose parameter estimation method and visual equipment | |
| KR102608956B1 (en) | A method for rectifying a sequence of stereo images and a system thereof | |
| CN111598946A (en) | Object pose measuring method and device and storage medium | |
| Chen et al. | Robust affine-invariant line matching for high resolution remote sensing images | |
| JP6172432B2 (en) | Subject identification device, subject identification method, and subject identification program | |
| US10460472B2 (en) | System and method for model adaptation | |
| CN111429344B (en) | Laser SLAM closed-loop detection method and system based on perceptual hashing | |
| CN111724446A (en) | A zoom camera extrinsic parameter calibration method for 3D reconstruction of buildings | |
| CN114663626B (en) | Baggage fast modeling method, device and storage medium based on single frame sampling | |
| Kallwies et al. | Triple-SGM: stereo processing using semi-global matching with cost fusion | |
| CN114663589B (en) | Three-dimensional modeling method, device and storage medium based on mobile luggage | |
| Ladikos et al. | A real-time tracking system combining template-based and feature-based approaches. | |
| CN118864469B (en) | Adaptive image acquisition method, medium and device | |
| Paudel et al. | 2D–3D synchronous/asynchronous camera fusion for visual odometry | |
| Arevalo et al. | Improving piecewise linear registration of high-resolution satellite images through mesh optimization | |
| CN121486699B (en) | Video stitching method, device and medium of array camera | |
| CN118314162B (en) | Dynamic visual SLAM method and device for time sequence sparse reconstruction | |
| Dai et al. | Line segment grouping and linking: a key step toward automated photogrammetry for non-contact site surveying | |
| Ranade et al. | Mapping of sparse 3d data using alternating projection | |
| Ma et al. | Research on Positioning and dimension measurement of truck compartment based on Semantic segmentation in automatic loading system | |
| Han et al. | Curvature Scale Space Corner Detection Based Registration Algorithm for Infrared and Visible Light Images of Power Equipment | |
| Abbas et al. | Robust feature matching in terrestrial image sequences |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |