Vehicle loss assessment analysis method, system and equipment based on remote image and medium

Abstract

The invention provides a vehicle loss assessment analysis method, system and device based on a remote image, and a medium, and the method comprises the steps: obtaining the remote image of a vehicle when the vehicle has an accident, and enabling the remote image to be an image collected at an accident site of the vehicle; after extracting a plurality of feature images from the remote image, determining a damaged area of the vehicle according to the plurality of feature images; and determining a damage parameter based on the damage area, and analyzing a damage assessment reference value of the vehicle by using the damage parameter. According to the method and the device, the loss assessment analysis can be quickly carried out according to the field remote image, the loss assessment standard can be unified, the assessment analysis deviation is reduced, the assessment precision is improved, the processing flow can be simplified, the assessment time consumption is shortened, and the assessment analysis efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of damage assessment of accident vehicles, and in particular to a vehicle damage assessment analysis method, system, equipment and medium based on remote imaging. Background Art

[0002] In the financial insurance field, when a claim report of an accident vehicle is received, the accident loss needs to be evaluated and a damage valuation can be obtained so that corresponding resource preparation and claims can be made based on the damage valuation. Therefore, accurate damage valuation is very important to insurance companies. If too much resources are prepared, the operating costs of the insurance company will increase; if insufficient resources are prepared, disputes and operational risks will arise.

[0003] Since there are different types of vehicle accidents, there may be damage to the vehicle, damage to the vehicle's contents, and casualties, so it is necessary to conduct damage assessment for each item of damage. Among them, the commonly used methods for damage assessment of vehicle damage include: after the accident, the vehicle is transported to a 4S store or repair shop, and the technicians conduct damage assessment based on the actual damage of the vehicle to obtain the vehicle's damage claim price.

[0004] However, the commonly used methods currently have the following technical problems: different assessors have different assessment standards and levels of experience, resulting in deviations in the final assessment results; and for severely damaged vehicles, assessors need to dismantle dozens or even hundreds of parts before conducting an assessment, which increases the time cycle of the entire disassembly and inspection assessment process and reduces processing efficiency. Summary of the invention

[0005] In view of the above problems, the present application is proposed to provide a vehicle damage assessment analysis method, system, device and medium based on remote imaging to overcome the above problems or at least partially solve the above problems, including:

[0006] A vehicle damage assessment and analysis method based on remote imaging, the method comprising:

[0007] When a vehicle has an accident, a remote image of the vehicle is acquired, wherein the remote image is an image collected at the accident scene of the vehicle;

[0008] After extracting a plurality of feature images from the remote image, determining the damaged area of ​​the vehicle according to the plurality of feature images;

[0009] Damage parameters are determined based on the damaged area, and damage assessment reference values ​​of the vehicle are analyzed using the damage parameters.

[0010] In a possible implementation, determining the damaged area of ​​the vehicle according to the plurality of feature images includes:

[0011] Extracting structural nodes of the vehicle outline from each of the feature images, and connecting multiple structural nodes of each of the feature images to construct a vehicle structural line drawing;

[0012] Calculating the similarity between each of the vehicle structure line drawings and a preset line drawing at a corresponding angle to obtain a plurality of line similarities;

[0013] If the similarity of each of the lines is greater than a preset similarity, it is determined that the vehicle is non-structurally damaged, and a preset image recognition model is called to recognize each of the feature images according to the chromaticity value to obtain a damaged area;

[0014] If at least one of the line similarities is less than a preset similarity, the vehicle is determined to be structurally damaged, and a preset structure recognition model is called to recognize each of the feature images according to the line similarity to obtain a damaged area.

[0015] In a possible implementation, the damage parameter includes: a device quantity value and a frame deformation ratio value;

[0016] The determining of damage parameters based on the damaged area comprises:

[0017] If it is determined that the vehicle is structurally damaged, the number of faulty devices in the damaged area is determined to obtain a device quantity value;

[0018] After counting the statistical quantity values ​​of the line similarities that are less than the preset similarity, searching for the statistical weight value according to the statistical quantity values;

[0019] After calculating the ratio of each line similarity to the preset similarity to obtain a similarity ratio, the product of the statistical weight value and the similarity ratio is calculated to obtain a frame deformation ratio value.

[0020] In a possible implementation, the damage parameters include: a damage area value and a vehicle paint unit value;

[0021] The determining of damage parameters based on the damaged area comprises:

[0022] If it is determined that the vehicle is non-structurally damaged, then the area and chromaticity value of the damaged area are determined respectively to obtain a damaged area value and a damaged chromaticity value;

[0023] According to the damaged chromaticity value, the price of the corresponding color is searched in a preset car paint list to obtain the car paint unit value.

[0024] In a possible implementation, analyzing a damage assessment reference value of a vehicle by using the damage parameter includes:

[0025] Determining driving parameters of the vehicle, wherein the driving parameters include mileage and age of the vehicle;

[0026] The driving parameters and the damage parameters are used to calculate a damage reference value for the vehicle.

[0027] In a possible implementation, acquiring a remote image of the vehicle includes:

[0028] After establishing communication with the smart terminal of the user of the accident vehicle, shooting prompt information is sent to the smart terminal, so that the user can refer to the prompt information to shoot and upload the image of the accident vehicle to obtain a remote image.

[0029] In a possible implementation, after the step of analyzing the damage assessment reference value of the vehicle using the damage parameter, the method further includes:

[0030] The total annual amount of the accident vehicle is calculated using the damage assessment reference value;

[0031] If the total annual limit value is greater than the rated value of the accident vehicle, a recommended car insurance is generated and pushed to the user's smart terminal for the user's reference.

[0032] A vehicle damage assessment and analysis system based on remote imaging, the system comprising:

[0033] An acquisition module, used for acquiring a remote image of the vehicle when an accident occurs to the vehicle, wherein the remote image is an image collected at the accident scene of the vehicle;

[0034] A determination module, configured to extract a plurality of feature images from the remote image and determine the damaged area of ​​the vehicle according to the plurality of feature images;

[0035] The analysis module is used to determine damage parameters based on the damaged area and use the damage parameters to analyze the damage assessment reference value of the vehicle.

[0036] In a possible implementation, determining the damaged area of ​​the vehicle according to the plurality of feature images includes:

[0037] Extracting structural nodes of the vehicle outline from each of the feature images, and connecting multiple structural nodes of each of the feature images to construct a vehicle structural line drawing;

[0038] Calculating the similarity between each of the vehicle structure line drawings and a preset line drawing at a corresponding angle to obtain a plurality of line similarities;

[0039] If the similarity of each of the lines is greater than a preset similarity, it is determined that the vehicle is non-structurally damaged, and a preset image recognition model is called to recognize each of the feature images according to the chromaticity value to obtain a damaged area;

[0040] If at least one of the line similarities is less than a preset similarity, the vehicle is determined to be structurally damaged, and a preset structure recognition model is called to recognize each of the feature images according to the line similarity to obtain a damaged area.

[0041] In a possible implementation, the damage parameter includes: a device quantity value and a frame deformation ratio value;

[0042] The determining of damage parameters based on the damaged area comprises:

[0043] If it is determined that the vehicle is structurally damaged, the number of faulty devices in the damaged area is determined to obtain a device quantity value;

[0044] After counting the statistical quantity values ​​of the line similarities that are less than the preset similarity, searching for the statistical weight value according to the statistical quantity values;

[0045] After calculating the ratio of each line similarity to the preset similarity to obtain a similarity ratio, the product of the statistical weight value and the similarity ratio is calculated to obtain a frame deformation ratio value.

[0046] In a possible implementation, the damage parameters include: a damage area value and a vehicle paint unit value;

[0047] The determining of damage parameters based on the damaged area comprises:

[0048] If it is determined that the vehicle is non-structurally damaged, then the area and chromaticity value of the damaged area are determined respectively to obtain a damaged area value and a damaged chromaticity value;

[0049] According to the damaged chromaticity value, the price of the corresponding color is searched in a preset car paint list to obtain the car paint unit value.

[0050] In a possible implementation, analyzing a damage assessment reference value of a vehicle by using the damage parameter includes:

[0051] Determining driving parameters of the vehicle, wherein the driving parameters include mileage and age of the vehicle;

[0052] The driving parameters and the damage parameters are used to calculate a damage reference value for the vehicle.

[0053] In a possible implementation, acquiring a remote image of the vehicle includes:

[0054] After establishing communication with the smart terminal of the user of the accident vehicle, shooting prompt information is sent to the smart terminal, so that the user can refer to the prompt information to shoot and upload the image of the accident vehicle to obtain a remote image.

[0055] In a possible implementation, the system further includes:

[0056] A calculation module, for calculating the total annual amount of the accident vehicle using the damage assessment reference value after the step of analyzing the damage assessment reference value of the vehicle using the damage parameter;

[0057] The recommendation module is used to generate a recommended car insurance and push it to the user's smart terminal for reference if the annual total amount value is greater than the rated value of the accident vehicle.

[0058] A device includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the steps of vehicle damage assessment analysis based on remote imaging as described above are implemented.

[0059] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of vehicle damage assessment analysis based on remote imaging as described above are implemented.

[0060] This application has the following advantages:

[0061] In the embodiments of the present application, the present invention can obtain a remote image of the vehicle when an accident occurs; determine the damaged area of ​​the vehicle based on a number of characteristic images in the remote image; determine damage parameters based on the damaged area, and use the damage parameters to analyze the damage assessment reference value of the vehicle. By performing the above operations through the business processing system, damage assessment analysis can be quickly performed based on the remote images of the scene, which can not only unify the standards for damage assessment, reduce the deviation of assessment analysis, and improve the accuracy of assessment, but also simplify the processing process, shorten the time consumption of assessment, and improve the efficiency of assessment analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0063] Figure 1 It is a flowchart of a vehicle damage assessment and analysis method based on remote imaging provided by an embodiment of the present application;

[0064] Figure 2 is a schematic diagram of the structure of the OpenPose network provided in an embodiment of the present application;

[0065] Figure 3 It is a structural block diagram of a vehicle damage assessment and analysis system based on remote imaging provided in one embodiment of the present application;

[0066] Figure 4 It is a structural diagram of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0067] In order to make the objects, features and advantages of the present application more obvious and understandable, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0068] In the financial insurance field, when a claim report of an accident vehicle is received, the accident loss needs to be evaluated and a damage valuation can be obtained so that corresponding resource preparation and claims can be made based on the damage valuation. Therefore, accurate damage valuation is very important to insurance companies. If too much resources are prepared, the operating costs of the insurance company will increase; if insufficient resources are prepared, disputes and operational risks will arise.

[0069] Since there are different types of vehicle accidents, there may be damage to the vehicle, damage to the vehicle's contents, and casualties, so it is necessary to conduct damage assessment for each item of damage. Among them, the commonly used methods for damage assessment of vehicle damage include: after the accident, the vehicle is transported to a 4S store or repair shop, and the technicians conduct damage assessment based on the actual damage of the vehicle to obtain the vehicle's damage claim price.

[0070] However, the commonly used methods currently have the following technical problems: different assessors have different assessment standards and experience levels, resulting in deviations in the final assessment results; and for severely damaged vehicles, the vehicle may suffer secondary damage during transportation or driving. The assessors at the subsequent 4S shop or repair shop need to dismantle dozens or even hundreds of parts for evaluation, which increases the time cycle of the entire disassembly and inspection assessment process and reduces processing efficiency.

[0071] Reference Figure 1 , showing a flowchart of a vehicle damage assessment and analysis method based on remote imaging provided by an embodiment of the present application;

[0072] In one embodiment, the vehicle damage assessment and analysis method based on remote imaging is applicable to a business processing system of an insurance company. The business processing system can communicate with the smart terminal of a user who has purchased auto insurance, and can also communicate with the vehicle terminal of the user's vehicle.

[0073] By communicating with smart terminals, various auto insurance information and auto insurance processing procedures can be pushed to users; by communicating with the on-board terminal, the vehicle data can be obtained in real time and the vehicle status can be detected when an accident occurs, so as to assist technicians in conducting damage assessment based on the detected data, so as to improve the accuracy of the assessment, reduce the workload of the assessment and simplify the assessment process, thereby improving the efficiency of the damage assessment.

[0074] Wherein, as an example, the vehicle damage assessment analysis method based on remote imaging may include:

[0075] S11. When a vehicle accident occurs, a remote image of the vehicle is acquired, wherein the remote image is an image collected at the accident scene of the vehicle.

[0076] In one embodiment, when a vehicle has an accident, the business processing system may obtain a remote image of the vehicle, wherein the remote image is an image captured at the accident scene of the accident vehicle.

[0077] By acquiring images of accident vehicles at remote locations, it is possible to determine the damage to the vehicle in the accident, such as whether there is breakage, dents, friction, etc. Subsequently, an accurate damage assessment can be conducted on the damage to the vehicle based on the images at the scene. The entire process is executed by the business processing system, which can unify the assessment standards for damage assessment and reduce the deviation of damage assessment; at the same time, based on the assessment and analysis of images collected in real time and on site, the assessment accuracy can be further improved to assist technicians in conducting damage assessment.

[0078] Optionally, if further processing or evaluation is required later, the user of the accident vehicle can be prompted to transport the vehicle to a 4S store or repair shop, and the technicians can refer to the subsequent evaluation and analysis results, which can simplify the technicians' operating procedures.

[0079] In one embodiment, in order to improve the accuracy of subsequent evaluation and analysis, images of the accident vehicle at different angles can be acquired, so that the damage to the vehicle surface and interior can be determined based on the images at different angles, and then evaluation and analysis can be performed based on the identified damage to the vehicle surface and interior.

[0080] Wherein, as an example, the acquisition of the remote image of the vehicle may include the following sub-steps:

[0081] S111. After establishing communication with the smart terminal of the user of the accident vehicle, a shooting prompt message is sent to the smart terminal, so that the user can shoot and upload an image of the accident vehicle with reference to the prompt message to obtain a remote image.

[0082] In one implementation, if the user of the accident vehicle can ensure his personal safety after the accident, the user will generally notify the insurance company after the accident. For example, the user may call the insurance personnel to report the accident to facilitate subsequent claims; or report the accident on the platform of the business processing system.

[0083] After receiving the user's report information, communication can be established with the user's smart terminal. At this time, shooting prompt information can be sent to the user. The text of the shooting prompt information contains the operation prompt content of shooting the image of the accident vehicle. For example, the user can be prompted to shoot around the accident vehicle from left to right to obtain a remote image; or the user can be prompted to shoot the accident vehicle from different angles to obtain a remote image.

[0084] After an accident, if the user of the accident vehicle fails to take images while ensuring personal safety, in order to obtain remote images, the user can communicate with the vehicle's on-board terminal and take real-time images of the vehicle through the on-board terminal controller camera to obtain remote images. Alternatively, the user can obtain images taken by the vehicle's driving camera to obtain remote images.

[0085] In another optional embodiment, the various camera devices of the accident vehicle are damaged or fail to shoot images in the accident. Optionally, after the user reports the accident, the user's location can be obtained, and then the user communicates with the surrounding surveillance cameras according to the location to call the images recorded by the surrounding surveillance cameras. For example, if an accident occurs at the xx intersection, the image of the surveillance camera at the xx intersection can be obtained to obtain a remote image.

[0086] The captured images can be used to determine the actual state of the accident vehicle after the accident, and then an accurate assessment can be made based on its actual condition.

[0087] S12: After extracting a plurality of feature images from the remote image, determine the damaged area of ​​the vehicle according to the plurality of feature images.

[0088] In one embodiment, if the entire remote image is recognized and processed, it takes a long time and consumes a large amount of computing resources of the business processing system. In order to reduce the amount of data to be processed, a number of feature images can be extracted from the remote image, and then the damaged area of ​​the vehicle can be determined based on the several feature images. The damaged area is the area of ​​the vehicle that is damaged after the vehicle accident.

[0089] In one operation mode, if the remote image is a continuously shot image, for example, an image shot by a user of an accident vehicle around the vehicle, images can be extracted from the remote image according to the shooting angle to obtain several feature images. One image is extracted from the left view angle, one image is extracted from the right view angle, one image is extracted from the main view angle, and one image is extracted from the rear view angle, thereby obtaining several feature images.

[0090] If the remote image is taken from different angles, for example, the user of the accident vehicle takes a segment of image from the left perspective, a segment of image from the right perspective, a segment of image from a wide angle, etc., images can be extracted from each segment of image at a preset time interval to obtain several feature images.

[0091] It should be noted that the specific extraction method can be adjusted according to actual needs.

[0092] In different accidents, the damage to the vehicle varies. If the accident is serious, the damage to the vehicle is large and may even need to be scrapped. In order to accurately determine the structure of the accident vehicle and determine the area of ​​the accident based on its structure, as an example, determining the damaged area of ​​the vehicle based on the plurality of feature images may include the following sub-steps:

[0093] S121, extracting structural nodes of a vehicle outline from each of the feature images, and connecting multiple structural nodes of each of the feature images to construct a vehicle structural line drawing.

[0094] S122, calculating the similarity between each of the vehicle structure line drawings and a preset line drawing at a corresponding angle to obtain a plurality of line similarities.

[0095] S123. If the similarity of each of the lines is greater than a preset similarity, it is determined that the vehicle is non-structurally damaged, and a preset image recognition model is called to recognize each of the feature images according to the chromaticity value to obtain a damaged area.

[0096] S124. If at least one of the line similarities is less than a preset similarity, it is determined that the vehicle is structurally damaged, and a preset structure recognition model is called to recognize each of the feature images according to the line similarity to obtain a damaged area.

[0097] In one operation mode, the structural nodes of the vehicle contour can be extracted from each feature image, and multiple structural nodes of each feature image can be connected to construct a vehicle structural line map, which is an image of the vehicle contour lines at an angle corresponding to the feature image.

[0098] Specifically, each feature image can be processed based on the vehicle contour recognition algorithm to obtain the structural node corresponding to each feature image. Optionally, the vehicle contour recognition algorithm can be an OpenPose algorithm, referring to Figure 2 , shows a schematic diagram of the structure of the OpenPose network provided by an embodiment of the present application. The specific processing flow of the OpenPose algorithm is as follows:

[0099] In the first step, we collect multiple images of the vehicle’s appearance from different angles and train them through the VGG-19 neural network to obtain the external features of the vehicle’s appearance images.

[0100] The second step is to enter the prediction stage. Each prediction stage is divided into two branches for iterative training. Branch 1_1 predicts the position of the structural nodes of each key structure of the vehicle through multiple convolutional layers;

[0101] In the third step, branch 1_2 predicts the connection information between the structural nodes of each key structure through multiple convolutional layers;

[0102] In the fourth step, the loss function is calculated once in each prediction stage, and then the image features extracted by VGG-19, the location information of the structural nodes, and the connection information between the structural nodes are integrated and sent to the next stage for further training;

[0103] In the fifth step, the process is repeated, and finally after t (t≥2) stages, the structural nodes of the key structures of the vehicle in the image are obtained.

[0104] In order to accurately extract the structural nodes of the vehicle contour, each feature image can be preprocessed first. Specifically, the image can be denoised to eliminate the influence of irrelevant information in the image on subsequent results. At the same time, the image brightness can be adjusted to improve the accuracy of structural node recognition.

[0105] First, the external features of the training set data are extracted through the first 19 layers of the visual geometry group neural network (VGG-19). Then, based on this, the structure nodes extracted from each feature image are converted into a format and clustered, that is, the structure nodes of each feature image are connected together to form a vehicle structure line map for each feature image.

[0106] Optionally, a vehicle structure detector may be provided, and the coordinates of the structure nodes after affine transformation may be input into the vehicle structure detector to obtain the coordinates of the structure nodes of different vehicle structures, and the coordinates may be connected together to obtain a vehicle structure line drawing for each feature image.

[0107] Next, the similarity between each vehicle structure line drawing and the preset line drawing of the corresponding angle may be calculated to obtain a plurality of line similarities.

[0108] The vehicle structure line drawing is a contour line drawing of the appearance of the accident vehicle taken from a certain angle. For example, the first vehicle structure line drawing is a contour line drawing of the appearance of the accident vehicle taken from a left perspective, and then the similarity between the vehicle structure line drawing from the left perspective and the preset line drawing from the left perspective is calculated to obtain the line similarity of the left perspective.

[0109] In one embodiment, the preset line graph may be a line graph obtained by extracting structural nodes from an appearance image of the vehicle taken before the accident and connecting and constructing the same. In order to reduce the deviation, in actual operation, after purchasing the auto insurance, the user may upload the appearance images of the vehicle at different angles to the business processing system. The appearance images uploaded by the user are processed according to the steps of constructing the structural line graph to obtain the preset line graph.

[0110] Optionally, when a user has an accident or changes the appearance of the vehicle and uploads a new image, the new image can be used as the appearance image for the next line similarity calculation. For example, after the accident, each feature image can be stored and used for the next calculation. Optionally, the image can be cleaned up once a year to prompt the user to re-upload.

[0111] After calculating the line similarity, it can be determined whether each line similarity is greater than a preset similarity. If each line similarity is greater than the preset similarity, it means that the vehicle structure has little or no change, and the vehicle frame has no structural damage, and it can be determined that the damage to the vehicle in this accident is non-structural damage.

[0112] If the vehicle has no structural damage in this accident, the accident may be caused by friction. After friction, the paint on the surface of the vehicle will be removed, causing the color of the vehicle's appearance to change. In order to identify the color of the appearance, the preset image recognition model can be called to identify each feature image according to the chromaticity value to obtain the damaged area.

[0113] In order to improve the recognition accuracy, the image contrast of the feature image can be enhanced first, and then a preset image recognition model is called to recognize the adjusted feature image to obtain the damaged area.

[0114] Specifically, the preset image recognition model may be a CMYK (Cyan Magenta Yellow Key) color model, an HSB model or an RGB model.

[0115] In an actual operation mode, a plurality of vehicle appearance images may be used in advance for model training, and the user may mark the colors corresponding to the vehicle appearance and the colors corresponding to the non-vehicle appearance in a plurality of preset neural networks in advance.

[0116] During recognition, if the vehicle's appearance is defective or damaged, its color will deviate from the color corresponding to the actual appearance. The model can identify the area of ​​the image corresponding to the color of the vehicle's appearance and the area of ​​the image corresponding to the color of the non-vehicle appearance based on the chromaticity value, and then determine the damaged area of ​​the image.

[0117] Similarly, if at least one of the line similarities is less than the preset similarity, it means that at a certain angle, the vehicle structure appearance changes greatly, and the vehicle frame may change significantly, then the vehicle is determined to be structurally damaged, and the vehicle may have structural damage in the accident. For example, if a vehicle is involved in a rear-end collision, its front end is dented, and the line similarity corresponding to the feature image in the left or right perspective will be less than the preset similarity.

[0118] Next, the preset structure recognition model can be called to identify each feature image according to the line similarity to obtain the damaged area.

[0119] Specifically, a vehicle structure line diagram with line similarity less than a preset similarity and a preset line diagram at a corresponding angle are input into a preset structure recognition model. The preset structure recognition model can identify the difference lines between the two line diagrams and determine the position coordinates of the lines on the vehicle, and then perform image capture according to the feature image at the corresponding angle according to the position coordinates to obtain the damaged area.

[0120] S13. Determine damage parameters based on the damaged area, and use the damage parameters to analyze damage assessment reference values ​​for the vehicle.

[0121] After the damaged area is determined, the damage parameters can be determined based on the characteristic parameters of the damaged area, and then damage assessment can be performed based on the damage parameters to obtain a damage assessment reference value. Subsequent damage assessment personnel or technical personnel can make an assessment based on the damage assessment reference value.

[0122] Among them, the damage parameters may include the size of the damaged area, the proportion of the damaged area to the entire vehicle, the vehicle parts and equipment involved in the damaged area, etc.

[0123] In one embodiment, if it is determined that the vehicle has structural damage, the main damage to the vehicle is the frame and various parts and equipment inside the vehicle. If the frame is severely deformed or the parts inside the vehicle (engine or gearbox or battery of new energy vehicles) are severely damaged, subsequent claims for scrapping are required. In order to determine the degree of frame deformation of the vehicle and the number of faulty devices, in one embodiment, the damage parameters include: the number of devices and the frame deformation ratio.

[0124] The device quantity value may be the number of devices that have failed in the damaged area of ​​the vehicle. The frame deformation ratio value is the ratio of the frame structure line of the vehicle after the accident to the frame structure line of the vehicle before the accident.

[0125] Wherein, as an example, the determining of the damage parameter based on the damaged area may include the following sub-steps:

[0126] S21. If it is determined that the vehicle is structurally damaged, the number of faulty devices in the damaged area is determined to obtain a device quantity value.

[0127] S22, after counting the statistical quantity values ​​of the line similarities that are less than a preset similarity, searching for a statistical weight value according to the statistical quantity values.

[0128] S23, after calculating the ratio of each line similarity to a preset similarity to obtain a similarity ratio, calculate the product of the statistical weight value and the similarity ratio to obtain a frame deformation ratio value.

[0129] In one embodiment, if it is determined that the vehicle has structural damage, the regional coordinates of the damaged area can be obtained, and then a communication connection with the vehicle's on-board terminal can be established according to the regional coordinates. The on-board terminal can communicate with the vehicle equipment corresponding to the regional coordinates to obtain its real-time parameters. If the real-time parameters of the vehicle equipment are not within the normal parameter range, the vehicle equipment is determined to be a faulty equipment. Then, the number of faulty equipment can be counted to obtain the equipment quantity value.

[0130] In actual operation, after an accident occurs, the equipment around the damaged area may also be affected, causing the equipment around the damaged area to also fail. Optionally, after determining the area coordinates, the area coordinates are widened to form a search range, and then the real-time parameters of the vehicle equipment in the search area are collected, and whether the vehicle equipment is a faulty device is determined based on the real-time parameters.

[0131] After counting the number of equipment values, the number of line similarities less than the preset similarity can be counted, and the statistical weight value can be searched according to the statistical number values. If the number of line similarities less than the preset similarity is larger, it means that more locations of the vehicle structure are deformed and the deformation ratio is larger.

[0132] Specifically, the user can pre-set the relationship between the statistical quantity value and the statistical weight value, for example, Y=AX+B, where Y is the statistical weight value, X is the statistical quantity value, A is a constant greater than 1, and B is a calculation parameter, and A and B can be adjusted according to actual needs.

[0133] Next, the ratio of each line similarity to the preset similarity can be calculated to obtain a similarity ratio, and finally the product of the statistical weight value and the similarity ratio is calculated to obtain a frame deformation ratio value.

[0134] The deformation ratio of the frame can be used to determine the deformation ratio of the frame, and then the damage can be assessed based on the deformation size of the frame structure and the amount of damaged equipment, which can improve the accuracy of the damage assessment.

[0135] In another embodiment, in one of the embodiments, if it is determined that the vehicle has no structural damage, the accident may be caused by surface friction, and the main damage to the vehicle is damage to the vehicle surface and appearance, such as friction of the door. In order to determine the friction of the vehicle appearance, in one embodiment, the damage parameters include: damage area value and vehicle paint unit value.

[0136] The damaged area value may be the area of ​​the vehicle surface where friction occurs, and the paint unit value may be the unit price of the paint applied to the vehicle.

[0137] Wherein, as an example, the determining of the damage parameter based on the damaged area may include the following sub-steps:

[0138] S31. If it is determined that the vehicle is non-structurally damaged, the area and chromaticity value of the damaged region are determined respectively to obtain a damaged area value and a damaged chromaticity value.

[0139] S32, searching for the price of the corresponding color in a preset car paint list according to the damaged chromaticity value, to obtain a car paint unit price.

[0140] In one operation mode, if the vehicle is determined to be non-structurally damaged, the characteristic image can be identified, and the area and chromaticity value corresponding to the damaged area can be obtained, and the damaged area value and damaged chromaticity value can be obtained. Then, the price of the corresponding color can be searched in the preset car paint list according to the damaged chromaticity value to obtain the car paint unit value.

[0141] Specifically, a preset car paint list can be obtained from technicians at a 4S store or repair shop. The preset car paint list can include unit prices of car paints of different colors. The price of the corresponding color can be searched in the preset car paint list according to the damaged chromaticity value, thereby obtaining the car paint unit value.

[0142] After the damage parameters are determined, in order to perform damage assessment for different damage parameters, for example, analyzing the damage assessment reference value of the vehicle using the damage parameters may include the following sub-steps:

[0143] S131. Determine driving parameters of the vehicle, wherein the driving parameters include the mileage and service life of the vehicle.

[0144] S132. Calculate a damage assessment reference value of the vehicle using the driving parameters and the damage parameters.

[0145] In one operation mode, the driving parameters of the vehicle may be determined, wherein the driving parameters may include the mileage and age of the vehicle. If the mileage is greater, the vehicle's value retention rate is higher, and the amount that can be claimed is less; if the mileage is less, the vehicle's value retention rate is lower, and the amount that can be claimed is more. Similarly, if the age of the vehicle is greater, the probability of vehicle failure is higher, and the amount that can be claimed is less; if the age of the vehicle is less, the probability of vehicle failure is lower, and the amount that can be claimed is higher.

[0146] In one operation mode, in order to quantify the mileage and service life, after obtaining the mileage (the unit can be ten thousand miles), the reciprocal of the mileage can be calculated to obtain the quantified mileage. Similarly, after obtaining the service life (the unit can be years), the reciprocal of the service life can be calculated to obtain the quantified service life.

[0147] In one operating mode, the driving parameters may be used together with the parameters to calculate a damage reference value for the vehicle.

[0148] In specific operations, if it is determined that the vehicle has structural damage, the calculation of the damage reference value can be shown as follows:

[0149] P = [N*(equipment unit price) + S*(vehicle unit price)]*L*Y;

[0150] Among them, P is the reference value for damage assessment; N is the number of equipment; S is the frame deformation ratio; L is the quantified mileage; and Y is the quantified service life.

[0151] In specific operations, if it is determined that the vehicle has no structural damage, the calculation of the damage reference value can be shown as follows:

[0152] P = [A*C]*[L+Y];

[0153] Among them, P is the reference value for damage assessment; A is the damaged area value; C is the single value of the paint; L is the quantified mileage; and Y is the quantified service life.

[0154] In addition, after calculating the damage reference value, subsequent claims processing is required. When the user's claim amount for the year is high, it is necessary to adjust the scrapping of the car insurance to protect the interests of the enterprise. As an example, the method may also include the following steps:

[0155] S14. Calculate the total annual amount of the accident vehicle using the damage assessment reference value.

[0156] S15. If the total annual limit value is greater than the rated value of the accident vehicle, a recommended car insurance is generated and pushed to the user's smart terminal for the user's reference.

[0157] Specifically, after calculating the damage assessment reference value, the amount of the user's claim within this year can be obtained, and then the sum of the damage assessment reference value and the amount of the claim within this year is calculated to obtain the annual total amount of the accident vehicle.

[0158] Determine whether the annual total amount is greater than the rated value of the accident vehicle. If the annual total amount is greater than the rated value of the accident vehicle, it means that the total amount of the user's vehicle this year is large. In order to adjust the user's auto insurance premium next year, you can search for the corresponding auto insurance according to the annual total amount. Specifically, you can search for auto insurance that meets the annual total amount, and then push the searched auto insurance to the user's smart terminal for the user's reference.

[0159] In this embodiment, the embodiment of the present invention provides a vehicle damage assessment analysis method based on remote imaging, and its beneficial effects are: the present invention can obtain remote imaging of the vehicle when an accident occurs; determine the damaged area of ​​the vehicle based on several characteristic images in the remote imaging; determine damage parameters based on the damaged area, and use the damage parameters to analyze the damage assessment reference value of the vehicle. By performing the above operations through the business processing system, damage assessment analysis can be quickly performed based on the remote imaging of the scene, which can not only unify the standards for damage assessment assessment, reduce the deviation of assessment analysis, and improve the accuracy of assessment, but also simplify the processing process, shorten the time consumption of assessment, and improve the efficiency of assessment analysis.

[0160] The embodiment of the present invention also provides a vehicle damage assessment analysis system based on remote imaging, referring to Figure 3 , showing a schematic structural diagram of a vehicle damage assessment and analysis system based on remote imaging provided by an embodiment of the present invention.

[0161] Wherein, as an example, the vehicle damage assessment analysis system based on remote imaging may include:

[0162] The acquisition module 301 is used to acquire a remote image of the vehicle when an accident occurs to the vehicle, wherein the remote image is an image collected at the accident scene of the vehicle;

[0163] A determination module 302 is used to extract a plurality of feature images from the remote image and determine the damaged area of ​​the vehicle according to the plurality of feature images;

[0164] The analysis module 303 is used to determine damage parameters based on the damaged area and use the damage parameters to analyze the damage assessment reference value of the vehicle.

[0165] Optionally, determining the damaged area of ​​the vehicle according to the plurality of feature images includes:

[0166] Extracting structural nodes of the vehicle outline from each of the feature images, and connecting multiple structural nodes of each of the feature images to construct a vehicle structural line drawing;

[0167] Calculating the similarity between each of the vehicle structure line drawings and a preset line drawing at a corresponding angle to obtain a plurality of line similarities;

[0168] If the similarity of each of the lines is greater than a preset similarity, it is determined that the vehicle is non-structurally damaged, and a preset image recognition model is called to recognize each of the feature images according to the chromaticity value to obtain a damaged area;

[0169] If at least one of the line similarities is less than a preset similarity, the vehicle is determined to be structurally damaged, and a preset structure recognition model is called to recognize each of the feature images according to the line similarity to obtain a damaged area.

[0170] Optionally, the damage parameters include: a device quantity value and a frame deformation ratio value;

[0171] The determining of damage parameters based on the damaged area comprises:

[0172] If it is determined that the vehicle is structurally damaged, the number of faulty devices in the damaged area is determined to obtain a device quantity value;

[0173] After counting the statistical quantity values ​​of the line similarities that are less than the preset similarity, searching for the statistical weight value according to the statistical quantity values;

[0174] After calculating the ratio of each line similarity to the preset similarity to obtain a similarity ratio, the product of the statistical weight value and the similarity ratio is calculated to obtain a frame deformation ratio value.

[0175] Optionally, the damage parameters include: a damage area value and a paint unit value;

[0176] The determining of damage parameters based on the damaged area comprises:

[0177] If it is determined that the vehicle is non-structurally damaged, then the area and chromaticity value of the damaged area are determined respectively to obtain a damaged area value and a damaged chromaticity value;

[0178] According to the damaged chromaticity value, the price of the corresponding color is searched in a preset car paint list to obtain the car paint unit value.

[0179] Optionally, analyzing a damage assessment reference value of a vehicle by using the damage parameter includes:

[0180] Determining driving parameters of the vehicle, wherein the driving parameters include mileage and age of the vehicle;

[0181] The driving parameters and the damage parameters are used to calculate a damage reference value for the vehicle.

[0182] Optionally, acquiring a remote image of the vehicle includes:

[0183] After establishing communication with the smart terminal of the user of the accident vehicle, shooting prompt information is sent to the smart terminal, so that the user can refer to the prompt information to shoot and upload the image of the accident vehicle to obtain a remote image.

[0184] Optionally, the system further comprises:

[0185] A calculation module, for calculating the total annual amount of the accident vehicle using the damage assessment reference value after the step of analyzing the damage assessment reference value of the vehicle using the damage parameter;

[0186] The recommendation module is used to generate a recommended car insurance and push it to the user's smart terminal for reference if the annual total amount value is greater than the rated value of the accident vehicle.

[0187] Reference Figure 4 , shows a computer device of a vehicle damage assessment analysis method based on remote imaging of the present application, which may specifically include the following:

[0188] The computer device 12 is in the form of a general-purpose computing device, and the components of the computer device 12 may include but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0189] The bus 18 represents one or more of several types of bus 18 structures, including a memory bus 18 or memory controller, a peripheral bus 18, an accelerated graphics port, a processor or a local bus 18 using any of a variety of bus 18 architectures. These architectures include, by way of example, but are not limited to, an Industry Standard Architecture (ISA) bus 18, a Micro Channel Architecture (MAC) bus 18, an Enhanced ISA bus 18, an Audio Video Electronics Standards Association (VESA) local bus 18, and a Peripheral Component Interconnect (PCI) bus 18.

[0190] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0191] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). Although Figure 3Not shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, which are configured to perform the functions of the various embodiments of the present application.

[0192] A program / utility 40 having a set (at least one) of program modules 42 may be stored in, for example, a memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0193] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, cameras, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs)), wide area networks (WANs), and / or public networks (e.g., the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34, etc.

[0194] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, such as implementing the vehicle damage assessment analysis method based on remote imaging provided in the embodiment of the present application.

[0195] That is, when the processing unit 16 executes the above program, the following is achieved:

[0196] When a vehicle has an accident, a remote image of the vehicle is acquired, wherein the remote image is an image collected at the accident scene of the vehicle;

[0197] After extracting a plurality of feature images from the remote image, determining the damaged area of ​​the vehicle according to the plurality of feature images;

[0198] Damage parameters are determined based on the damaged area, and damage assessment reference values ​​of the vehicle are analyzed using the damage parameters.

[0199] In an embodiment of the present application, the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the vehicle damage assessment analysis method based on remote imaging as provided in all embodiments of the present application is implemented.

[0200] That is, when the program is executed by the processor:

[0201] When a vehicle has an accident, a remote image of the vehicle is acquired, wherein the remote image is an image collected at the accident scene of the vehicle;

[0202] After extracting a plurality of feature images from the remote image, determining the damaged area of ​​the vehicle according to the plurality of feature images;

[0203] Damage parameters are determined based on the damaged area, and damage assessment reference values ​​of the vehicle are analyzed using the damage parameters.

[0204] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device.

[0205] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0206] The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on the remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.

[0207] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0208] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0209] The above is a detailed introduction to the vehicle damage assessment and analysis method, system, device and medium based on remote imaging provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle damage assessment and analysis method based on remote imaging, characterized in that: The method comprises: When a vehicle has an accident, a remote image of the vehicle is acquired, wherein the remote image is an image collected at the accident scene of the vehicle; After extracting a plurality of feature images from the remote image, determining the damaged area of ​​the vehicle according to the plurality of feature images; Damage parameters are determined based on the damaged area, and damage assessment reference values ​​of the vehicle are analyzed using the damage parameters.

2. The vehicle damage assessment and analysis method based on remote imaging according to claim 1 is characterized in that: The determining the damaged area of ​​the vehicle according to the plurality of feature images comprises: Extracting structural nodes of the vehicle outline from each of the feature images, and connecting multiple structural nodes of each of the feature images to construct a vehicle structural line drawing; Calculating the similarity between each of the vehicle structure line drawings and a preset line drawing at a corresponding angle to obtain a plurality of line similarities; If the similarity of each of the lines is greater than a preset similarity, it is determined that the vehicle is non-structurally damaged, and a preset image recognition model is called to recognize each of the feature images according to the chromaticity value to obtain a damaged area; If at least one of the line similarities is less than a preset similarity, the vehicle is determined to be structurally damaged, and a preset structure recognition model is called to recognize each of the feature images according to the line similarity to obtain a damaged area.

3. The vehicle damage assessment and analysis method based on remote imaging according to claim 2 is characterized in that: The damage parameters include: equipment quantity value and frame deformation ratio value; The determining of damage parameters based on the damaged area comprises: If it is determined that the vehicle is structurally damaged, the number of faulty devices in the damaged area is determined to obtain a device quantity value; After counting the statistical quantity values ​​of the line similarities that are less than the preset similarity, searching for the statistical weight value according to the statistical quantity values; After calculating the ratio of each line similarity to the preset similarity to obtain a similarity ratio, the product of the statistical weight value and the similarity ratio is calculated to obtain a frame deformation ratio value.

4. The vehicle damage assessment and analysis method based on remote imaging according to claim 2 is characterized in that: The damage parameters include: damage area value and vehicle paint unit value; The determining of damage parameters based on the damaged area comprises: If it is determined that the vehicle is non-structurally damaged, then the area and chromaticity value of the damaged area are determined respectively to obtain a damaged area value and a damaged chromaticity value; According to the damaged chromaticity value, the price of the corresponding color is searched in a preset car paint list to obtain the car paint unit value.

5. The vehicle damage assessment and analysis method based on remote imaging according to claim 2 is characterized in that: The method of analyzing the damage reference value of the vehicle by using the damage parameter includes: Determining driving parameters of the vehicle, wherein the driving parameters include mileage and age of the vehicle; The driving parameters and the damage parameters are used to calculate a damage reference value for the vehicle.

6. The vehicle damage assessment and analysis method based on remote imaging according to any one of claims 1 to 5, characterized in that: The step of acquiring a remote image of the vehicle includes: After establishing communication with the smart terminal of the user of the accident vehicle, shooting prompt information is sent to the smart terminal, so that the user can refer to the prompt information to shoot and upload the image of the accident vehicle to obtain a remote image.

7. The vehicle damage assessment and analysis method based on remote imaging according to any one of claims 1 to 5, characterized in that: After the step of analyzing the damage assessment reference value of the vehicle using the damage parameter, the method further includes: The total annual amount of the accident vehicle is calculated using the damage assessment reference value; If the total annual limit value is greater than the rated value of the accident vehicle, a recommended car insurance is generated and pushed to the user's smart terminal for the user's reference.

8. A vehicle damage assessment and analysis system based on remote imaging, characterized in that: The system comprises: An acquisition module, used for acquiring a remote image of the vehicle when an accident occurs to the vehicle, wherein the remote image is an image collected at the accident scene of the vehicle; A determination module, configured to extract a plurality of feature images from the remote image and determine the damaged area of ​​the vehicle according to the plurality of feature images; The analysis module is used to determine damage parameters based on the damaged area and use the damage parameters to analyze the damage assessment reference value of the vehicle.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the vehicle damage assessment and analysis method based on remote imaging as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer-executable program, and the computer-executable program is used to enable a computer to execute the vehicle damage assessment analysis method based on remote imaging as described in any one of claims 1-7.

Images