CN105807335B - Vehicle chassis inspection method and system - Google Patents

Abstract

Disclose a kind of vehicle chassis inspection method and system.The method comprising the steps of: obtaining the chassis image for being examined vehicle；The chassis image template with vehicle same model is obtained from database；The chassis image and chassis image template of examined vehicle are registrated；Poor is asked to the chassis image template after the chassis image and registration after registration, obtains variable domain of the chassis image of vehicle relative to chassis image template；The variable domain is presented.This method is detected the entrainment concealed automatically from the image of chassis, is had great practical value in field of safety check by image procossing and pattern-recognition means.

Description

Vehicle chassis inspection method and system

technical field

Embodiments of the present invention relate to vehicle chassis inspection, and in particular, relate to a method and system for automatically inspecting objects carried on a vehicle chassis using image processing and pattern recognition technologies in the field of safety inspection.

Background technique

Illegally concealing carried objects in the chassis of a car is one of the common means used by criminals to hide from the sky. The industry has paid considerable attention to this huge safety hazard, especially in airports, where there are already relevant standards or norms. At present, relevant detection methods include manual inspection, visible light image inspection of the chassis, etc. The shortcomings of the manual approach to visitation are obvious and cannot meet current needs. However, the cost of obtaining radiographic images is relatively high, and the chassis images are relatively messy, and it is also very difficult to detect entrained objects. Visible light inspection is usually carried out manually through the video image of the chassis obtained by the CCD device. In fact, this is still manually checked, which makes the checking efficiency low and the accuracy is not high.

Contents of the invention

Considering the above-mentioned problems in the prior art, a vehicle chassis inspection method and system are proposed, which can automatically detect entrained objects in chassis images.

In one aspect of the present invention, a vehicle chassis inspection method is proposed, comprising the steps of: obtaining a chassis image of the inspected vehicle; obtaining a chassis image template of the same model as the vehicle from a database; The image and the chassis image template are registered; the difference between the registered chassis image and the registered chassis image template is obtained to obtain the change area of the chassis image of the vehicle relative to the chassis image template; the change area is presented .

Preferably, the step of obtaining the chassis image template of the same vehicle model as the vehicle from the database includes: retrieving the chassis image template of the vehicle model from the database according to the unique identifier of the inspected vehicle.

Preferably, the step of obtaining the chassis image template of the same model as the vehicle from the database includes: obtaining a transmitted radiation image of the vehicle; extracting the internal structure information of the vehicle from the transmitted radiation image, and synthesizing the exterior of the vehicle Feature information, retrieve the chassis image template of the vehicle from the database.

Preferably, the step of registering the chassis image of the inspected vehicle and the chassis image template includes: performing rigid registration on the chassis image of the inspected vehicle and the chassis image template, so as to perform global Transformation alignment: perform elastic registration on the chassis image of the inspected vehicle and the chassis image template, so as to eliminate local deformation.

Preferably, the step of rigid registration includes: performing feature extraction on two images to obtain feature points; finding matching feature point pairs by performing similarity measurement; obtaining image space coordinate transformation parameters by matching feature point pairs; Perform image registration.

Preferably, the method further includes the step of: setting the values of pixels whose absolute values are smaller than a predetermined threshold in the variation region to zero.

Preferably, the method further includes the step of: performing binarization on the image, and performing connected region analysis; and setting the pixel value to zero in the region whose area is smaller or larger than a certain threshold value.

Preferably, the method further includes the step of: setting the pixel values in pairs of small regions greater than zero or less than zero to zero.

In another aspect of the present invention, a vehicle chassis inspection system is proposed, including: a sensing device that acquires a chassis image of the vehicle being inspected; a data processing unit that acquires a chassis image template of the same model as the vehicle from a database, Registering the chassis image of the inspected vehicle with the chassis image template, calculating the difference between the registered chassis image and the registered chassis image template, and obtaining the difference between the chassis image of the vehicle and the chassis image template A change area; a display device for presenting the change area.

Preferably, the vehicle chassis inspection system further includes: a radiation imaging system, which obtains a transmitted radiation image of the vehicle; wherein, the data processing unit extracts the internal structure information of the vehicle from the transmitted radiation image, and synthesizes the vehicle The external feature information of the vehicle model is retrieved from the database for the chassis image template.

The above scheme can automatically detect hidden entrained objects from the chassis image through image processing and pattern recognition means, and has great practical value in the field of security inspection.

Description of drawings

In order to better understand the present invention, the present invention will be described in detail according to the following drawings:

Fig. 1 shows a schematic diagram of a vehicle inspection system according to an embodiment of the present invention:

Fig. 2 shows a flowchart of a vehicle type identification method according to an embodiment of the present invention.

Detailed ways

Specific embodiments of the present invention will be described in detail below, and it should be noted that the embodiments described here are only for illustration, not for limiting the present invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be apparent, however, to one of ordinary skill in the art that these specific details need not be employed to practice the present invention. In other instances, well-known structures, materials or methods have not been described in detail in order to avoid obscuring the present invention.

Throughout this specification, reference to "one embodiment," "an embodiment," "an example," or "example" means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in the present invention. In at least one embodiment. Thus, appearances of the phrases "in one embodiment," "in an embodiment," "an example," or "example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, particular features, structures or characteristics may be combined in any suitable combination and/or subcombination in one or more embodiments or examples. In addition, those of ordinary skill in the art should understand that the term "and/or" used herein includes any and all combinations of one or more of the associated listed items.

In the prior art, since the chassis image is inspected manually, the inspection efficiency is low and the accuracy is not high. To solve this problem, some embodiments of the present invention propose to use an automatic method for checking. For example, the chassis image of the inspected vehicle is obtained through a sensing device such as a CCD device, and then the chassis image template of the same model as the vehicle is obtained from the database. Furthermore, the chassis image of the inspected vehicle is registered with the chassis image template, and then the difference between the registered chassis image and the registered chassis image template is calculated to obtain the change of the chassis image of the vehicle relative to the chassis image template Area, the changing area is presented on the display, and the area where there may be entrainment is automatically indicated to the map judge. Through the above solution, the safety inspection of the chassis can be automatically performed, and the efficiency and accuracy of the inspection are improved.

Fig. 1 shows a schematic diagram of a vehicle inspection system according to an embodiment of the present invention. As shown in FIG. 1 , an inspection system according to an embodiment of the present invention involves automatic inspection of a vehicle chassis using visible light images.

The system shown in FIG. 1 includes a sensing device 110 , a radiation imaging system 150 , a storage device 120 , an image processing unit 140 and a display device 130 .

In some embodiments, the sensing device 110 includes one or more sensors, such as a CCD device, etc., used to obtain chassis information of the vehicle, and the like. In other embodiments, the sensing device may include a camera configured to capture a license plate image of the inspected vehicle; and a recognition unit configured to recognize the license plate number of the inspected vehicle from the license plate image. In other embodiments, the sensing device 110 includes a reader for reading the ID of the inspected vehicle from a radio frequency tag carried by the inspected vehicle.

The radiation imaging system 150 performs X-ray scanning on the inspected vehicle to obtain an X-ray image of the inspected vehicle. The storage device 120 stores the X-ray images and the vehicle model template database, including chassis image templates and transmission image templates.

The image processing unit 140 retrieves the model template corresponding to the vehicle from the model template database, and determines the variation area between the obtained chassis image and the chassis template image. The display device 130 presents the changing area to the user.

For example, when a small vehicle needs to be checked in, the sensing device 110 obtains a chassis image of the vehicle. The corresponding small vehicle can also be identified by the sensing device 110, and the software system and the unique identification ID of the small vehicle, such as a license plate number, are generated. The vehicle unique identification ID is the unique identification of the small vehicle clearance in the software system. The identification ID can be the data generated by the software system for the small vehicle, or can be identified by the license plate number of the vehicle. Currently, the software system is identified by the license plate number.

For example, the data processing unit 140 is responsible for searching the template library to obtain the chassis template image corresponding to the small vehicle to be checked. A region of change between the resulting chassis image and the chassis template image is determined. The display device 130 presents the changing area to the user.

The flow chart of the inspection method according to the embodiment of the present invention will be further described below with reference to FIG. 2 . Fig. 2 shows a flowchart of a vehicle chassis inspection method according to an embodiment of the present invention.

In step S21, a chassis image of the inspected vehicle is acquired. Preferably, the chassis image acquisition uses a linear CCD camera. There are many related products and patents at home and abroad, so I won’t repeat them here. This image is hereinafter referred to as the image to be detected.

Additionally, image acquisition may include image correction and denoising. Since the images obtained by the linear camera are related to the speed of the vehicle, it is necessary to correspond each column of images to the time stamp obtained by the real-time speed measuring device (such as radar) to obtain images of uniform resolution. Preferably, the physical size represented by each pixel in the image is set to be 5mm*5mm. Image denoising can be achieved through a variety of algorithms. Preferably, it is implemented using a bilateral filter.

In step S22, a chassis image template of the same model as the vehicle is obtained from the database. This image is hereinafter referred to as the template image. There are many ways to obtain the template, including but not limited to: 1) using the license plate information to obtain the template image from the current license plate image; 2) using the vehicle type recognition system to obtain the current vehicle chassis template image; 3) using manual methods , manually enter text, retrieve and select a template image. Preferably, a license plate recognition system is used, and the license plate is used as identification information to search the historical database for the latest image corresponding to the license plate under the same license plate as a template image.

In other embodiments, the radiation inspection system 150 obtains the transmitted radiation image of the vehicle, and then the data processing unit 140 extracts the internal structure information of the vehicle from the transmitted radiation image, synthesizes the external feature information of the vehicle, and retrieves the vehicle model from the database. Chassis image template.

Those skilled in the art can understand that the "template image" is at least but not limited to one image. For example, when using license plate information, multiple templates can be obtained, so that multiple results can be fused through 1) change detection for multiple templates; 2) multiple templates can realize probabilistic templates; 3) partial splicing of multiple templates Realize the optimal ideal template; 4) By some method, such as selecting the template with the lowest noise as the optimal template map, a better result can be obtained. For clarity, embodiments of the present invention focus on using change detection rather than template optimization strategies.

In step S23, registration is performed on the chassis image of the inspected vehicle and the chassis image template; registration is performed on the image to be tested and the template image. This patent uses two sub-steps, namely rigid registration and elastic registration to achieve optimized registration results. As a person skilled in the art, it is conceivable to use a variety of registration algorithms to optimize the registration results, such as using gradient maps, transform domain features, multi-scale and other methods to improve registration results. The two images after registration have the same size.

Rigid registration is to perform global transformation alignment on images, and the process is as follows: First, feature extraction is performed on two images to obtain feature points; matching feature point pairs are found by similarity measurement; and then the image space is obtained through matching feature point pairs Coordinate transformation parameters; finally image registration is performed by the coordinate transformation parameters. Feature extraction is the key to registration technology, and accurate feature extraction provides a guarantee for the successful feature matching. Finding a feature extraction method with good invariance and accuracy is crucial for matching accuracy. There are many methods of feature extraction. Preferably, this embodiment uses Speed Up Robust Features (SURF) to extract image feature points and descriptors at feature points. Afterwards, the image to be tested is subjected to transmission deformation on the template image. The deformation parameters are calculated using the Random Sample Consensus (RANSAC) algorithm.

The elastic registration of images is mainly for accurate registration of images to eliminate local deformation. Elastic registration methods are mainly divided into two categories: pixel-based methods and feature-based methods. After comparing the amount of calculation, effectiveness and other aspects, it is preferable to use the Demons elastic registration algorithm to complete this process. But those skilled in the art can use other methods to perform elastic registration.

In step S24, the difference between the registered chassis image and the registered chassis image template is calculated to obtain the variation area of the chassis image of the vehicle relative to the chassis image template. Preferably, the registered image to be tested is subtracted from the registered template image to obtain a difference map. In order to reduce the impact of the change of the collection environment, the difference map can be processed by using the median value method. This problem can be better overcome by calculating the overall or local median value of the difference map and subtracting the median value from the corresponding area.

In step S25, the variation area is presented. There are many ways to express the results, and the means can be but not limited to: 1) directly colorize the difference map; 2) binarize the difference map, and color the Unicom area; 3) binarize the difference map, and find the Unicom The edge of the region, coloring at the edge. The colorized difference map is fused with the image to be tested and output as the final result.

Preferably, the embodiments display results using a pseudo-color method. First calculate the absolute value of the difference map, and stretch the range of values to, for example, [100,255]. Then the image to be tested is converted into a black-and-white image with three channels of red, green, and blue, and then the difference image is assigned to the red channel to achieve a significant red display effect of the entrainment.

In other embodiments, the difference map may be processed before presenting the region of change. The goal of post-processing is to remove noise caused by stains, changes in vehicle position, and changes in the acquisition environment. The difference map is also an image, the size of which is the same as the registered image, and if its pixel is not zero, it means that the image at this pixel has changed. The post-processing method can be but not limited to: 1) Image denoising; 2) Threshold value processing, the value whose absolute value is less than a certain threshold is set to zero; 3) Binarize the image and analyze the connected area; the area is less than or greater than In the area of the value of a certain threshold, the pixel value is set to zero; 4) If the small areas greater than zero or less than zero appear in pairs, they are likely to be noise, and the pixel values in these areas are set to zero.

Although some embodiments of the present invention are realized through the above steps, the vehicle chassis can be inspected. However, those skilled in the art can easily understand that each step can be implemented using a variety of algorithms, and is not limited to the above-mentioned specific steps.

The foregoing detailed description has set forth numerous embodiments of the vehicle chassis inspection method and system by use of schematic diagrams, flowcharts, and/or examples. Where such schematic diagrams, flowcharts, and/or examples include one or more functions and/or operations, those skilled in the art will understand that each function and/or operation in such schematic diagrams, flowcharts, or examples may Individually and/or collectively implemented by various structures, hardware, software, firmware, or essentially any combination thereof. In one embodiment, several portions of the subject matter described herein may be implemented in Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), Digital Signal Processors (DSPs), or other integrated formats. However, those skilled in the art will recognize that some aspects of the embodiments disclosed herein may be equivalently implemented in whole or in part in an integrated circuit, implemented as one or more Computer programs (e.g., implemented as one or more programs running on one or more computer systems), implemented as one or more programs running on one or more processors (e.g., implemented as One or more programs running on multiple microprocessors), implemented as firmware, or substantially implemented as any combination of the above methods, and those skilled in the art will have the ability to design circuits and/or write software and and/or firmware code capabilities. Furthermore, those skilled in the art will recognize that the mechanisms of the presently disclosed subject matter can be distributed as a variety of forms of program products and that regardless of the particular type of signal-bearing media actually used to carry out the distribution, the subject matter of the presently disclosed Exemplary embodiments are applicable. Examples of signal bearing media include, but are not limited to: recordable-type media such as floppy disks, hard drives, compact discs (CDs), digital versatile discs (DVDs), digital tapes, computer memory, etc.; and transmission-type media such as digital and and/or simulated communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

While this invention has been described with reference to a few exemplary embodiments, it is to be understood that the terms which have been used are words of description and illustration, rather than of limitation. Since the present invention can be embodied in many forms without departing from the spirit or essence of the invention, it should be understood that the above-described embodiments are not limited to any of the foregoing details, but should be construed broadly within the spirit and scope of the appended claims. , all changes and modifications falling within the scope of the claims or their equivalents shall be covered by the appended claims.

Claims (8)

1. a kind of vehicle chassis inspection method, comprising steps of

Obtain the chassis image for being examined vehicle；

The chassis image template with the vehicle same model is obtained from database；

Chassis image and the chassis image template to the examined vehicle are registrated；

Poor is asked to the chassis image template after the chassis image and registration after registration, comprising: by the chassis image after the registration Chassis image template after subtracting the registration obtains poor figure, wherein the difference figure includes that the chassis image of the vehicle is opposite In the variable domain of chassis image template；

Variable domain is post-processed；And

Post-treated variable domain is presented；

It is wherein, described that carry out post-processing to variable domain include: to carry out binaryzation to the difference figure, and carry out connection region point Analysis, area are less than or greater than in the region of the value of certain thresholding, and pixel value is set to zero, are greater than zero or minus for what is occurred in pairs Pixel value in zonule is set to zero.

2. the method as described in claim 1, wherein obtaining the chassis image mould with the vehicle same model from database The step of plate includes:

The chassis image template of the vehicle is retrieved from database according to the unique identifier of examined vehicle.

3. the method as described in claim 1, wherein obtaining the chassis image mould with the vehicle same model from database The step of plate includes:

Obtain the transmission radiation image of the vehicle；

The internal structural information of the vehicle is extracted from the transmission radiation image, integrates the surface information of the vehicle, from The chassis image template of the vehicle is retrieved in database.

4. the method for claim 1, wherein the chassis image to the examined vehicle and the chassis image template The step of being registrated include:

Chassis image and the chassis image template to the examined vehicle carry out Rigid Registration, complete to carry out to image Office's transformation alignment；

Chassis image and the chassis image template to the examined vehicle carry out elastic registrating, to eliminate local change Shape.

5. method as claimed in claim 4, wherein the step of Rigid Registration includes:

Feature extraction is carried out to two images and obtains characteristic point；

Matched characteristic point pair is found by carrying out similarity measurement；

By matched characteristic point to obtaining image space coordinate conversion parameter；

Image registration is carried out by coordinate conversion parameter.

6. the method as described in claim 1 further comprises the steps of:

The pixel value for being less than predetermined threshold to absolute value in the variable domain is set as zero.

7. a kind of vehicle chassis inspection system, comprising:

Sensing equipment obtains the chassis image for being examined vehicle；

Data processing unit obtains the chassis image template with the vehicle same model from database, is examined to described The chassis image of vehicle and the chassis image template are registrated, to the chassis image after the chassis image and registration after registration Template asks poor, comprising: and the chassis image template after the chassis image after the registration to be subtracted to the registration obtains poor figure, In, the difference figure includes variable domain of the chassis image of the vehicle relative to chassis image template, and to variable domain It is post-processed；

It shows equipment, post-treated variable domain is presented,

Wherein, it includes: to carry out binaryzation to the difference figure, and carry out that the data processing unit, which carries out post-processing to variable domain, Connection regional analysis, area are less than or greater than in the region of the value of certain thresholding, and pixel value is set to zero, are greater than zero for what is occurred in pairs Or the pixel value in minus zonule is set to zero.

8. vehicle chassis inspection system as claimed in claim 7, further includes: radiation image-forming system obtains the saturating of the vehicle Penetrate radiation image；

Wherein, the data processing unit extracts the internal structural information of the vehicle from the transmission radiation image, comprehensive to be somebody's turn to do The surface information of vehicle retrieves the chassis image template of the vehicle from database.