WO2019024488A1

WO2019024488A1 - Vehicle damage assessment method, electronic device and computer readable storage medium

Info

Publication number: WO2019024488A1
Application number: PCT/CN2018/076523
Authority: WO
Inventors: 何刘兴
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2017-08-03
Filing date: 2018-02-12
Publication date: 2019-02-07
Also published as: CN107730485A; CN107730485B

Abstract

A vehicle damage assessment method, an electronic device and a computer readable storage medium, the vehicle damage assessment method comprising: acquiring a partial picture of a vehicle to be subject to damage assessment; searching for a corresponding vehicle body picture in a preset image database according to a model and a vehicle body position corresponding to the local picture, wherein the corresponding vehicle body picture is a corresponding picture of a complete vehicle body position; preprocessing the partial picture so that the preprocessed partial picture conforms to a preset image effect; comparing pixel values of all pixel points in the vehicle body picture and the partial picture to obtain a comparison result; and determining the damage degree of the vehicle to be subject to damage assessment on the basis of the comparison result. According to the technical solution, the difficulty of achieving automated vehicle damage assessment may be effectively lowered.

Description

Vehicle loss method, electronic device and computer readable storage medium

This application claims the priority of the Chinese patent application filed on August 3, 2017, the Chinese Patent Office, the application number is 201710655877.8, and the application name is "vehicle damage method, electronic device and computer readable storage medium", the entire contents of which are The citations are incorporated herein by reference.

Technical field

The present application relates to the field of electronic technologies, and in particular, to a method for determining a vehicle loss, an electronic device, and a computer readable storage medium.

Background technique

With the increase in car ownership, the density of vehicles on urban roads is increasing, and the resulting traffic accidents are also increasing. In the event of a traffic accident, in order to obtain auto insurance claims, the insurance company is required to make a damage to the vehicle.

Due to the large amount of manual damage and inefficiency, an automated vehicle loss reduction scheme has emerged, which is implemented as follows: Obtaining at least two angles of damaged images of the damaged location of the vehicle, based on pre-stored motor vehicles A table of the relationship between the damaged picture and the degree of damage at each position, and the acquired damaged picture is analyzed to determine the damage of the vehicle.

Although the above-mentioned vehicle loss-reduction scheme can improve the efficiency to a certain extent with respect to the manual damage-reducing scheme, the above-mentioned scheme needs to obtain the damaged pictures of various components of various vehicles in advance to generate the above relationship table, because the damaged picture of the vehicle The collection is difficult, so it is difficult to collect the pictures of all the parts of each model after the damage, and if some pictures of some models have been damaged, it will be difficult to locate the corresponding parts of the corresponding models. Damaged situation.

technical problem

The present application provides a method and device for locating a vehicle, and a computer readable storage medium, which are used to reduce the difficulty in realizing automatic damage of a vehicle.

Technical solution

The first aspect of the present application provides a method for determining a vehicle loss, which includes:

Obtain a partial photograph of the vehicle to be damaged;

According to the vehicle type and the vehicle body position corresponding to the partial photos, the corresponding body image is searched from the preset image database, wherein the corresponding body image is: a picture of the corresponding intact vehicle body position;

Pre-processing the partial photo above, so that the partial image obtained after the above pre-processing conforms to the preset image effect;

Comparing the obtained body image with the partial image to perform pixel comparison on the pixel values of the respective pixels, wherein the comparison result indicates that each pixel in the partial image is respectively related to the body image a pixel value difference size of the pixel, and a coverage area of the pixel value in which the absolute value of the pixel value difference is greater than a preset threshold, wherein the related pixel point refers to a pixel point in the partial image. Shooting points with the same pixel points;

Determining the degree of damage of the to-be-determined vehicle based on the comparison result, wherein the degree of damage is related to the difference in the pixel value and the coverage area.

A second aspect of the present application provides an electronic device, comprising: a memory, a processor, and computer readable instructions stored on the memory and operable on the processor, the processor implementing the computer readable instructions The following steps:

Obtain a partial photograph of the vehicle to be damaged;

Comparing the obtained body image with the partial image to perform pixel comparison on the pixel values of the respective pixels, wherein the comparison result indicates that each pixel in the partial image is respectively related to the body image a pixel value difference size of the pixel, and a coverage area of the pixel value in which the absolute value of the pixel value difference is greater than a preset threshold, wherein the related pixel point refers to a pixel point in the partial image. Shooting the same pixel points;

The degree of damage is determined based on the above comparison result, wherein the degree of damage is related to the difference in the pixel value described above and the coverage area.

A third aspect of the present application provides a computer readable storage medium storing computer readable instructions, when the computer readable instructions are executed by at least one processor, implementing the following steps: acquiring a part of a vehicle to be determined photo;

Beneficial effect

In the solution of the present application, by obtaining a partial photograph of the vehicle to be determined, according to the vehicle type and the vehicle body position corresponding to the partial photograph, the corresponding body image is searched from the preset image database, and then the found body image and the pre-processed image are obtained. The obtained partial picture performs pixel value comparison of each pixel point, and determines the degree of damage based on the comparison result. Since the solution of the present application is to pre-process and compare the pixel values of the pictures of the intact vehicle body position corresponding to the same vehicle model after pre-processing, it is only necessary to collect normal pictures of various vehicle body positions of various models. (that is, the picture of the car body position is good), there is no need to pre-collect the pictures of the various car body positions of various models, and it is less difficult to collect the normal pictures of the vehicle body positions than to collect the damaged pictures. Many, therefore, through the solution of the present application, on the one hand, automatic damage to the vehicle can be realized, and on the other hand, the difficulty in realizing the automatic damage of the vehicle can be effectively reduced.

DRAWINGS

1 is a schematic flow chart of an embodiment of a method for determining a vehicle loss according to the present application;

2 is a schematic flow chart of another embodiment of a method for determining a vehicle loss according to the present application;

3 is a schematic structural diagram of an embodiment of an electronic device provided by the present application;

4 is a block diagram of a computer readable instruction provided by the present application.

Embodiments of the invention

Embodiment 1

An embodiment of the present application describes a method for determining a vehicle loss. Referring to FIG. 1 , a method for determining a vehicle in an embodiment of the present application includes:

Step 101: Obtain a partial photo of the vehicle to be determined;

In the embodiment of the present application, a partial photograph of the vehicle to be determined may be understood as a photograph taken by the user for a certain vehicle body position of the vehicle to be determined.

In the embodiment of the present application, the user may be provided with a photo uploading interface. When the user needs to make a loss to the vehicle, the user may take a partial photo of the vehicle to be damaged (for example, a photo of the damaged vehicle body position), and then upload through the photo uploading interface. A partial photograph of the vehicle to be determined is taken to obtain the partial photograph in step 101. Alternatively, the user can also trigger the shooting control provided by the application (or webpage) in the corresponding application (or corresponding webpage) to take a partial photo of the vehicle to be determined, and trigger the “OK” button after the shooting is completed, ie A partial photograph of the photographed vehicle to be determined may be uploaded to obtain the partial photograph in step 101.

Optionally, in order to conveniently locate the vehicle type and the vehicle body position corresponding to the partial photos, a finder frame matching each vehicle body position of each vehicle type may be preset to determine the vehicle type and the vehicle body position corresponding to the corresponding partial photos by the user selected framing frame. . Specifically, when the vehicle type information of the vehicle to be determined is received, according to the vehicle type information, a preset finder frame matching the respective vehicle body positions of the corresponding vehicle type is displayed, so that the user selects the finder frame to perform the shooting of the corresponding vehicle body position. The following is a specific application scenario. In the embodiment of the present application, when the user triggers the vehicle loss process, the preset various models are displayed for the user to select. When the user selects a certain type of vehicle, the corresponding vehicle information will be After being uploaded, according to the vehicle type information, a preset finder frame matching the respective vehicle body positions of the corresponding vehicle type is displayed, so that the user selects the finder frame to take the corresponding vehicle body position, and when the user completes the shooting and determines the upload, the corresponding part The photo will be uploaded and step 101 will get the uploaded partial photo.

It should be noted that, when the user takes a partial photo of the vehicle to be damaged, the finder frame for providing the user with a specific vehicle body position is an alternative rather than a necessary solution. In other embodiments, the user can also shoot through the default finder frame. Partial photos of the vehicle are damaged and uploaded, which is not limited here.

Specifically, for a vehicle to be determined, a partial photo may be acquired, and two or more partial photos may be acquired. The number of the partial photos obtained is determined based on the number of user uploads, which is not limited herein.

Step 102: Search for a corresponding body image from a preset image database according to the vehicle type and the vehicle body position corresponding to the partial photo.

Wherein, the corresponding body picture is: a picture of the corresponding intact body position.

In the embodiment of the present application, a picture of each intact vehicle body position of each vehicle type is stored in the image database (that is, the vehicle body position in the picture is undamaged). In step 102, according to the vehicle type and the vehicle body position corresponding to the partial photos acquired in step 101, a picture of the corresponding intact vehicle body position of the corresponding vehicle model is searched from the preset image database.

In an application scenario, if the local photo obtained by the user selects the finder frame in the embodiment of the present application, the vehicle type and the vehicle body position corresponding to the partial photo may be directly determined according to the framing frame selected by the user.

In another application scenario, if the local photo obtained by the default finder frame is used in the embodiment of the present application, the image and the vehicle body position corresponding to the partial photo may be determined by performing image recognition on the partial photo, or The user can manually input the vehicle model and the vehicle body position corresponding to the partial photograph, or can also provide the user with various vehicle models and various vehicle body positions, and the user selects the vehicle model and the vehicle body position corresponding to the partial photograph, which is not limited herein. .

Step 103: Perform pre-processing on the partial photo, so that the partial image obtained after the pre-processing is consistent with the preset image effect;

In the embodiment of the present application, in order to make the image effect of the partial photo (such as the image format and the light effect) consistent with the image effect of the image stored in the image database, the partial photo acquired in step 101 is preprocessed, so that the preprocessing is performed. The resulting partial image conforms to the preset image effect. Wherein, the foregoing preprocessing includes, but is not limited to, compression, cropping, and light shading.

Step 104: Compare the found body image with the partial image to perform pixel comparison on the pixel values of the respective pixels, and obtain a comparison result;

In the embodiment of the present application, the partial picture is a picture obtained by performing the preprocessing of step 103 on the partial photo acquired in step 101.

The comparison result indicates that the pixel values in the partial picture are different from the pixel values of the relevant pixel points in the body image, and the pixel values in which the absolute value of the pixel value difference is greater than a preset threshold are in the above part. The coverage area in the picture, wherein the relevant pixel point refers to the same pixel point as the pixel corresponding to the pixel point in the partial picture. That is, the above-mentioned comparison result can be used to obtain the picture obtained by the same shooting point in the above-mentioned vehicle body picture (ie, the body picture found in step 102) and the above partial picture (that is, the partial picture obtained in step 101 is preprocessed in step 103). The difference in the pixel value of the pixel corresponding to the two, and may determine the pixel whose absolute value of the pixel value difference is greater than the preset threshold based on the distribution of the pixel value whose absolute value of the pixel value difference is greater than the preset threshold The coverage area of the point. Specifically, the preset threshold may be set to zero.

In an application scenario, if the local photo obtained by the default finder frame is used in the embodiment, the step 104 may include: determining, according to the image matching algorithm, that the relevant pixel points of each pixel in the partial image are respectively a position in the body picture; comparing each pixel point in the partial picture with a pixel value in the body picture to determine the comparison result.

In another application scenario, if the embodiment of the present application is a partial photo obtained by the finder frame selected by the user, considering that there is a constraint of the finder frame, the partial image obtained by the pre-processing may be considered and found at this time. The body image is highly consistent, so the step 104 may include: sequentially, in order from the left to the right of the pixel position, from top to bottom, the pixel of each pixel position in the partial image and the same pixel in the body position. The pixel points of the point position are compared by pixel values to determine the above comparison result.

Step 105: Determine, according to the comparison result, the damage degree of the to-be-determined vehicle;

In the embodiment of the present application, the damage degree of the to-be-determined vehicle can be determined based on the comparison result obtained in step 104, wherein the damage degree is related to the difference in the pixel value and the coverage area. Specifically, the degree of damage may be positively correlated with the average value of the difference in pixel value and the above-mentioned coverage area, that is, if the average value of the difference in pixel value is larger, and the coverage area is larger, the degree of damage is greater.

Optionally, the damage degree of the vehicle to be determined is set to M major levels, and each of the large levels may be set with N small levels, wherein each large level corresponds to a coverage area interval, and each small level corresponds to a pixel value. The average interval of the difference size, the above M and N can be set according to actual needs. For example, it is assumed that the coverage area intervals are set as follows: (0, S1), (S1, S2), (S2, S3), and the average value interval of the following pixel value difference sizes is set in advance: (0, A1], (A1) , A2], (A2, A3), the damage degree of the vehicle to be determined can be set to three large levels, so that the first large level corresponds to (0, S1), the second largest level corresponds to (S1, S2), The three levels correspond to (S2, S3), and three small levels can be set in each large level, so that the first small level corresponds to (0, A1), the second small level corresponds to (A1, A2), and the third small level corresponds. (A2, A3) In addition, the level of damage of different levels can be defined as follows: 1.1 level <1.2 level <1.3 level <2.1 level <2.2 level <2.3 level <3.1 level <3.2 level <3.3 level. It is noted that the level 1.1 corresponds to the first small level of the first large level, the second small level of the first large level corresponding to the 1.2 level, and so on. The step 105 may be specifically: determining based on the comparison result. A level used to indicate the degree of damage of the vehicle to be determined.

Of course, in the embodiment of the present application, the damage degree of the to-be-determined vehicle may be determined by other methods. For example, a damage calculation function may be preset, and the damage calculation function takes the comparison result as an input parameter, and uses the output value as the output value. For the quantified value of the degree of damage, step 105 may be specifically performed to determine the degree of damage of the to-be-determined vehicle based on the comparison result and the preset damage calculation function.

Optionally, after step 105, the estimated compensation amount of the to-be-determined vehicle may be calculated based on the vehicle type, the vehicle body position, and the damage degree determined in step 104, and then the estimated compensation amount of the to-be-determined vehicle is outputted for the user. And/or claims related staff can be informed of the estimated amount of compensation.

Optionally, if the partial photo of the to-be-determined vehicle acquired in step 101 is two or more, the position and the vehicle body position corresponding to the partial photo may be performed on each partial photo obtained in the embodiment of the present application. The step of searching for the corresponding body image from the preset image database and the subsequent steps (that is, performing the above steps 102 to 105 for each partial photo obtained). Further, after step 105, the estimated compensation amount of the vehicle to be determined may be calculated based on the vehicle body position and the damage degree corresponding to the vehicle type and the two or more partial photos, and then the estimated compensation amount of the vehicle to be determined is outputted. So that the user and / or claims related staff can be informed of the estimated amount of compensation.

It should be noted that the vehicle damage method in the embodiment of the present application may be implemented by a vehicle loss device, which may be integrated into an electronic device such as a mobile phone, a server, a personal computer, or the like, which is not limited herein.

It can be seen from the above that in the embodiment of the present application, by obtaining a partial photo of the vehicle to be determined, according to the vehicle type and the vehicle body position corresponding to the partial photo, the corresponding body image is searched from the preset image database, and then the found body image is found. The pixel values of the respective pixels are compared with the partial images obtained by the pre-processing, and the degree of damage is determined based on the comparison result. Since the solution of the present application is to pre-process and compare the pixel values of the pictures of the intact vehicle body position corresponding to the same vehicle model after pre-processing, it is only necessary to collect normal pictures of various vehicle body positions of various models. (that is, the picture of the car body position is good), there is no need to pre-collect the pictures of the various car body positions of various models, and it is less difficult to collect the normal pictures of the vehicle body positions than to collect the damaged pictures. Many, therefore, through the solution of the present application, on the one hand, automatic damage to the vehicle can be realized, and on the other hand, the difficulty in realizing the automatic damage of the vehicle can be effectively reduced.

Embodiment 2

The difference between the embodiment of the present application and the first embodiment is that the preset frame corresponding to the vehicle body position is provided for the user to take a photo to improve the accuracy of the vehicle body position recognition, thereby further improving the accuracy of the vehicle damage. Sex. Specifically, referring to FIG. 2, the method for determining a vehicle in the embodiment of the present application includes:

Step 201: Receive vehicle type information of a vehicle to be determined;

In the embodiment of the present application, when the user needs to perform fixed loss on the vehicle, the vehicle type information of the vehicle to be determined may be input in a preset fixed loss interface and the preset startup control is triggered to upload the vehicle type information to trigger the vehicle damage process. Or, in the case that the model information is already bound, the preset startup control is directly triggered to upload the pre-bound vehicle information to trigger the vehicle damage process. Alternatively, when the user triggers the vehicle damage process, the preset various models are displayed for the user to select. When the user selects a certain type of vehicle, the corresponding vehicle type information is uploaded, and step 201 receives the uploaded vehicle type information.

Step 202: Display, according to the received vehicle type information, a preset finder frame that matches each vehicle body position of the corresponding vehicle type, so that the user selects the finder frame to perform shooting of the corresponding vehicle body position;

Step 203: Obtain a partial photo of the to-be-determined vehicle.

In the embodiment of the present application, when the user completes the shooting based on the preset finder frame and determines the upload, the corresponding partial photo is uploaded, and step 203 acquires the uploaded partial photo.

Step 204: Search for a corresponding body image from a preset image database according to the vehicle type and the vehicle body position corresponding to the partial photo.

Step 205: Perform pre-processing on the partial photo, so that the partial image obtained after the pre-processing is consistent with the preset image effect;

In the embodiment of the present application, in order to make the image effect (for example, the image format and the light effect) of the partial photo consistent with the image effect of the image stored in the image database, the partial photo acquired in step 203 is preprocessed, so that the preprocessing is performed. The resulting partial image conforms to the preset image effect. Wherein, the foregoing preprocessing includes, but is not limited to, compression, cropping, and light shading.

Step 206: Compare the found body image with the partial image to perform pixel comparison on each pixel point, and obtain a comparison result;

In the embodiment of the present application, the partial picture is a picture obtained by performing the pre-processing of step 205 on the partial photo acquired in step 203.

The comparison result indicates that the pixel values in the partial picture are different from the pixel values of the relevant pixel points in the body image, and the pixel values in which the absolute value of the pixel value difference is greater than a preset threshold are in the above part. The coverage area in the picture, wherein the relevant pixel point refers to the same pixel point as the pixel corresponding to the pixel point in the partial picture. That is, the above-mentioned comparison result can be used to obtain the picture obtained by the same shooting point in the above-mentioned vehicle body picture (ie, the body picture found in step 204) and the above partial picture (that is, the partial picture obtained in step 203 is preprocessed by step 205). The difference in the pixel value of the pixel corresponding to the two, and may determine the pixel whose absolute value of the pixel value difference is greater than the preset threshold based on the distribution of the pixel value whose absolute value of the pixel value difference is greater than the preset threshold The coverage area of the point. Specifically, the preset threshold may be set to zero.

Since the embodiment of the present application is a partial photo obtained by the finder frame selected by the user, considering that there is a constraint of the finder frame, the partial image obtained after the pre-processing is considered to be highly consistent with the found body image. Therefore, the step 206 may include: sequentially, in order from left to right and from top to bottom of the pixel position, pixel points of each pixel position in the partial image and pixel points of the same pixel position in the vehicle body position to perform pixel values. Compare to determine the above comparison results.

Step 207: Determine, according to the comparison result, the damage degree of the to-be-determined vehicle;

In the embodiment of the present application, the damage degree of the to-be-determined vehicle can be determined based on the comparison result obtained in step 206, wherein the damage degree is related to the difference in the pixel value and the coverage area. Specifically, the degree of damage may be positively correlated with the average value of the difference in pixel value and the above-mentioned coverage area, that is, if the average value of the difference in pixel value is larger, and the coverage area is larger, the degree of damage is greater.

Specifically, the description of step 105 in the embodiment shown in FIG. 1 may be referred to in step 207, and details are not described herein again.

Optionally, after step 207, the estimated compensation amount of the to-be-determined vehicle may be calculated based on the vehicle type, the vehicle body position, and the damage degree determined in step 207, and then the estimated compensation amount of the to-be-determined vehicle is outputted for the user. And/or claims related staff can be informed of the estimated amount of compensation.

Optionally, if the partial photo of the to-be-determined vehicle acquired in step 203 is two or more, the position and the vehicle body position corresponding to the partial photo may be performed for each partial photo obtained in the embodiment of the present application. The step of searching for the corresponding body image from the preset image database and the subsequent steps (the above steps 204 to 207 may be performed for each partial photo obtained. Further, after step 207, based on the above model, the above two After calculating the estimated compensation amount of the vehicle to be determined, the above-mentioned partial photos respectively correspond to the position of the vehicle body and the degree of damage, and then output the estimated compensation amount of the vehicle to be determined, so that the user and/or the claim-related staff can know the above estimate. compensation amount.

It can be seen from the above that in the embodiment of the present application, by obtaining a partial photo of the vehicle to be determined, according to the vehicle type and the vehicle body position corresponding to the partial photo, the corresponding body image is searched from the preset image database, and then the found body image is found. The pixel values of the respective pixels are compared with the partial images obtained by the pre-processing, and the degree of damage is determined based on the comparison result. Since the solution of the present application is to pre-process and compare the pixel values of the pictures of the intact vehicle body position corresponding to the same vehicle model after pre-processing, it is only necessary to collect normal pictures of various vehicle body positions of various models. (that is, the picture of the car body position is good), there is no need to pre-collect the pictures of the various car body positions of various models, and it is less difficult to collect the normal pictures of the vehicle body positions than to collect the damaged pictures. Many, therefore, through the solution of the present application, on one hand, automatic damage to the vehicle can be realized, on the other hand, the difficulty in realizing the automatic damage of the vehicle can be effectively reduced, and on the other hand, by providing a preset matching with the position of the vehicle body. The framing frame allows the user to take photos, which can improve the accuracy of the vehicle body position recognition, and further improve the accuracy of the vehicle's damage.

Embodiment 3

Corresponding to the vehicle loss determination method described above in the first embodiment or the second embodiment, FIG. 3 is a schematic diagram showing the operating environment of the computer readable instructions (for example, computer readable instructions) related to the vehicle loss determination method provided by the embodiment of the present application. For the convenience of description, only parts related to the embodiments of the present application are shown.

In the embodiment of the present application, the computer readable instructions are installed and run in an electronic device. The electronic device may include, but is not limited to, one or more memories 31 (only one is shown), one or more processors 32 (only one is shown), and the above-described memory 31 and processor 32 are connected by a bus 33. . Figure 3 shows only the electronic device with components 31-33, but it should be understood that not all illustrated components may be implemented, and more components (e.g., displays, etc.) or fewer components may be implemented instead.

Memory 31 may be an internal storage unit of an electronic device, such as a hard disk or memory of the electronic device, in some embodiments. The memory 31 may also be an external storage device of the electronic device in other embodiments, such as a plug-in hard disk equipped on the electronic device, and a smart memory card (Smart Media) Card, SMC), Secure Digital (SD) card, Flash Card, etc. Further, the memory 31 may also include both an internal storage unit of the electronic device and an external storage device. The memory 31 is used to store application software installed on an electronic device and various types of data, such as the above-described computer readable instructions and the like. The memory 31 can also be used to temporarily store data that has been output or is about to be output.

Processor 32 may be a central processor (Central) in some embodiments A processing unit (CPU), a microprocessor or other data processing chip for running program code or processing data stored in the memory 31, such as executing the computer readable instructions described above.

Further, based on FIG. 3, please refer to FIG. 4. FIG. 4 is a functional block diagram of computer readable instructions corresponding to the above-described vehicle loss-reduction method according to Embodiment 1 or Embodiment 2 according to an embodiment of the present application. In the embodiment of the present application, the computer readable instructions may be divided into one or more modules, and the one or more modules are stored in a computer readable storage medium, such as the memory 31, and are processed by one or more processors. (This embodiment is executed by the processor 32) to complete the application. For example, in FIG. 4, the computer readable instructions described above may be partitioned into an acquisition module 41, a lookup module 42, a preprocessing module 43, a pixel value comparison module 44, and a determination module 45. The following description will specifically describe the functions of the acquisition module 41, the lookup module 42, the pre-processing module 43, the pixel value comparison module 44, and the determination module 45.

An obtaining module 41, configured to acquire a partial photo of the vehicle to be determined;

The searching module 42 is configured to search for a corresponding body image from a preset image database according to the vehicle type and the vehicle body position corresponding to the partial photos acquired by the obtaining module 41, wherein the corresponding body image is: the corresponding intact vehicle body position image;

The pre-processing module 43 is configured to pre-process the partial photo acquired by the obtaining module 41, so that the partial image obtained after the pre-processing is consistent with the preset image effect;

The pixel value comparison module 44 is configured to compare the vehicle body image found by the search module 42 with the partial image of the pixel value of each pixel to obtain a comparison result, wherein the comparison result indicates: in the partial image a pixel value difference between each pixel point and an associated pixel point in the body image, and a coverage value of a pixel value in which the absolute value of the pixel value difference is greater than a preset threshold value, wherein the relevant pixel point is Refers to the same pixel point as the pixel corresponding to the pixel in the above partial picture.

The determining module 45 is configured to determine the damage degree of the to-be-determined vehicle based on the comparison result of the pixel value comparison module 44, wherein the damage degree is related to the difference in the pixel value and the coverage area.

Optionally, the computer readable instructions described above may be segmented into the following modules:

a receiving module, configured to receive vehicle type information of the vehicle to be determined;

The display module is configured to display, according to the vehicle type information, a preset finder frame that matches each vehicle body position of the corresponding vehicle type, so that the user selects the finder frame to perform the shooting of the corresponding vehicle body position.

a vehicle type determining module, configured to determine a vehicle type corresponding to the partial photo according to the vehicle type information of the to-be-determined vehicle received by the receiving module;

The vehicle body position determining module is configured to determine a vehicle body position corresponding to the partial photo based on the framing frame selected by the user.

a valuation module, configured to calculate an estimated compensation amount of the to-be-determined vehicle based on the vehicle type, the vehicle body position, and the damage degree;

The output module is configured to output an estimated compensation amount of the to-be-determined vehicle calculated by the above-mentioned valuation unit.

Optionally, if the partial photo of the to-be-determined vehicle acquired by the obtaining module 41 is two or more, the searching module 42 is triggered for each partial photo; the estimating module is specifically configured to: based on the above-mentioned model, the two or more partial photos Calculate the estimated compensation amount of the above-mentioned vehicle to be determined, corresponding to the position of the vehicle body and the degree of damage.

It should be understood that the electronic device in the embodiment of the present application may be used to implement all the technical solutions in the foregoing method embodiments, and the parts that are not detailed and mentioned in the embodiments of the present application may be referred to the description of the foregoing method embodiments. I won't go into details here.

Claims

A method for determining a vehicle loss, comprising:

Obtain a partial photograph of the vehicle to be damaged;

Searching, according to the vehicle type and the vehicle body position corresponding to the partial photograph, a corresponding body image from a preset image database, wherein the corresponding body image is: a picture of the corresponding intact vehicle body position;

Pre-processing the partial photo such that the partial image obtained after the pre-processing conforms to a preset image effect;

Comparing the searched body image with the partial image for pixel values of respective pixels to obtain a comparison result, wherein the comparison result indicates that each pixel point in the partial image is respectively related to the a pixel value difference size of a relevant pixel in the body image, and an absolute value of the pixel value difference magnitude is greater than a preset threshold value of a pixel area in the partial image, wherein the related pixel point refers to the a pixel point corresponding to a pixel corresponding to a pixel in a partial picture;

Determining the degree of damage of the to-be-determined vehicle based on the comparison result, wherein the degree of damage is related to the difference in the pixel value and the coverage area.
The vehicle damage method according to claim 1, wherein the obtaining a partial photograph of the vehicle to be determined comprises:

Receiving vehicle type information of the vehicle to be determined;

According to the vehicle type information, a preset finder frame matching the respective vehicle body positions of the corresponding vehicle type is displayed, so that the user selects the finder frame to perform the shooting of the corresponding vehicle body position.
The vehicle damage method according to claim 2, wherein the obtaining a partial photograph of the vehicle to be determined comprises:

Determining, according to the received vehicle type information of the to-be-determined vehicle, a vehicle model corresponding to the partial photograph;

The position of the vehicle body corresponding to the partial photo is determined based on the framing frame selected by the user.
The vehicle damage method according to claim 1, wherein the obtaining a partial photograph of the vehicle to be determined comprises:

Image recognition is performed on the partial photograph, and the vehicle type and the vehicle body position corresponding to the partial photograph are determined.
The vehicle damage method according to any one of claims 1 to 4, wherein the determining the degree of damage based on the comparison result further comprises:

Calculating an estimated compensation amount of the to-be-determined vehicle based on the vehicle type, the vehicle body position, and the damage degree;

The estimated compensation amount of the vehicle to be determined is output.
The method of claim 5, wherein if the acquired partial photos of the to-be-determined vehicle are two or more, performing: according to the partial photo, for each partial photo The vehicle model and the vehicle body position, the steps of finding the corresponding body image from the preset image database and the subsequent steps;

Calculating the estimated compensation amount of the to-be-determined vehicle based on the vehicle type, the vehicle body position, and the damage degree, including:

Calculating the estimated compensation amount of the to-be-determined vehicle based on the vehicle body position and the damage degree corresponding to the vehicle type and the two or more partial photos.
An electronic device, comprising: a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, the processor executing the computer readable instructions as follows step:

Obtain a partial photograph of the vehicle to be damaged;

Searching, according to the vehicle type and the vehicle body position corresponding to the partial photograph, a corresponding body image from a preset image database, wherein the corresponding body image is: a picture of the corresponding intact vehicle body position;

Pre-processing the partial photo such that the partial image obtained after the pre-processing conforms to a preset image effect;

Comparing the searched body image with the partial image for pixel values of respective pixels to obtain a comparison result, wherein the comparison result indicates that each pixel point in the partial image is respectively related to the a pixel value difference size of a relevant pixel in the body image, and an absolute value of the pixel value difference magnitude is greater than a preset threshold value of a pixel area in the partial image, wherein the related pixel point refers to the a pixel point corresponding to a pixel corresponding to a pixel in a partial picture;

Determining the degree of damage of the to-be-determined vehicle based on the comparison result, wherein the degree of damage is related to the difference in the pixel value and the coverage area.
The electronic device according to claim 7, wherein the processor further implements the following steps when the computer readable instructions are executed:

Receiving vehicle type information of the vehicle to be determined before acquiring the partial photograph of the vehicle to be determined;

According to the vehicle type information, a preset finder frame matching the respective vehicle body positions of the corresponding vehicle type is displayed, so that the user selects the finder frame to perform the shooting of the corresponding vehicle body position.
The electronic device according to claim 8, wherein the processor further implements the following steps when the computer readable instructions are executed:

After obtaining the partial photograph of the vehicle to be determined, determining the vehicle type corresponding to the partial photograph according to the received vehicle type information of the to-be-determined vehicle;

The position of the vehicle body corresponding to the partial photo is determined based on the framing frame selected by the user.
The electronic device according to claim 7, wherein the processor further implements the following steps when the computer readable instructions are executed:

After the partial photograph of the vehicle to be determined is acquired, image recognition is performed on the partial photograph, and the vehicle type and the vehicle body position corresponding to the partial photograph are determined.
The electronic device according to any one of claims 7 to 10, wherein the processor further implements the following steps when the computer readable instructions are executed:

After determining the degree of damage based on the comparison result, calculating an estimated compensation amount of the to-be-determined vehicle based on the vehicle type, the vehicle body position, and the damage degree;

The estimated compensation amount of the vehicle to be determined is output.
The electronic device according to any one of the preceding claims, wherein when the processor executes the computer readable instructions, the method further comprises the step of: when the obtained partial photos of the to-be-determined vehicle are two or more And performing, according to each partial photo, the step of searching for a corresponding body image from the preset image database according to the vehicle type and the vehicle body position corresponding to the partial photo, and subsequent steps

Calculating the estimated compensation amount of the to-be-determined vehicle based on the vehicle type, the vehicle body position, and the damage degree, including:

Calculating the estimated compensation amount of the to-be-determined vehicle based on the vehicle body position and the damage degree corresponding to the vehicle type and the two or more partial photos.
An electronic device, comprising:

Obtaining a module for obtaining a partial photo of the vehicle to be determined;

a search module, configured to search for a corresponding body image from a preset image database according to the vehicle type and the vehicle body position corresponding to the partial photos acquired by the acquiring module, wherein the corresponding body image is: a corresponding intact vehicle body position picture of;

a pre-processing module, configured to pre-process a partial photo obtained by the acquiring module, so that the partial image obtained after the pre-processing conforms to a preset image effect;

a pixel value comparison module, configured to compare a body image of the search module and the partial image with a pixel value of each pixel to obtain a comparison result, wherein the comparison result indicates: the local part a pixel value difference between the pixel points in the picture and the relevant pixel point in the body image, and a coverage value of the pixel value in which the absolute value of the pixel value difference is greater than a preset threshold value, wherein The relevant pixel point refers to the same pixel point as the shooting point corresponding to the pixel point in the partial picture.

And a determining module, configured to determine, according to the comparison result of the pixel value comparison module, a damage degree of the to-be-determined vehicle, wherein the damage degree is related to the pixel value difference size and the coverage area.
The electronic device according to claim 13, wherein the electronic device further comprises:

a receiving module, configured to receive vehicle type information of the vehicle to be determined;

The display module is configured to display, according to the vehicle type information, a preset finder frame that matches each vehicle body position of the corresponding vehicle type, so that the user selects the finder frame to perform shooting of the corresponding vehicle body position.
The electronic device according to claim 14, wherein the electronic device further comprises:

a vehicle type determining module, configured to determine a vehicle type corresponding to the partial photo according to the vehicle type information of the to-be-determined vehicle received by the receiving module;

The vehicle body position determining module is configured to determine a vehicle body position corresponding to the partial photo based on a framing frame selected by the user.
The electronic device according to any one of claims 13 to 15, wherein the electronic device further comprises:

a valuation module, configured to calculate an estimated compensation amount of the to-be-determined vehicle based on the vehicle type, the vehicle body position, and the damage degree;

And an output module, configured to output an estimated compensation amount of the to-be-determined vehicle calculated by the valuation unit.
The electronic device according to claim 16, wherein if the partial photo of the to-be-determined vehicle acquired by the acquiring module is two or more, the searching module is triggered for each partial photo;

The evaluation module is specifically configured to: calculate an estimated compensation amount of the to-be-determined vehicle based on the vehicle body, the vehicle body position corresponding to the two or more partial photos, and the damage degree.
A computer readable storage medium having stored thereon computer readable instructions, wherein the computer readable instructions, when executed by a processor, implement the following steps:

Obtain a partial photograph of the vehicle to be damaged;

Searching, according to the vehicle type and the vehicle body position corresponding to the partial photograph, a corresponding body image from a preset image database, wherein the corresponding body image is: a picture of the corresponding intact vehicle body position;

Pre-processing the partial photo such that the partial image obtained after the pre-processing conforms to a preset image effect;

Comparing the searched body image with the partial image for pixel values of respective pixels to obtain a comparison result, wherein the comparison result indicates that each pixel point in the partial image is respectively related to the a pixel value difference size of a relevant pixel in the body image, and an absolute value of the pixel value difference magnitude is greater than a preset threshold value of a pixel area in the partial image, wherein the related pixel point refers to the a pixel point corresponding to a pixel corresponding to a pixel in a partial picture;

Determining the degree of damage of the to-be-determined vehicle based on the comparison result, wherein the degree of damage is related to the difference in the pixel value and the coverage area.
The computer readable storage medium of claim 18, wherein the computer readable instructions are executed by a processor to implement the following steps:

Receiving vehicle type information of the vehicle to be determined before acquiring the partial photograph of the vehicle to be determined;

According to the vehicle type information, a preset finder frame matching the respective vehicle body positions of the corresponding vehicle type is displayed, so that the user selects the finder frame to perform the shooting of the corresponding vehicle body position.
The computer readable storage medium of claim 19, wherein the computer readable instructions are executed by a processor to implement the following steps:

After obtaining the partial photograph of the vehicle to be determined, determining the vehicle type corresponding to the partial photograph according to the received vehicle type information of the to-be-determined vehicle;

The position of the vehicle body corresponding to the partial photo is determined based on the framing frame selected by the user.