Vehicle loss assessment list determination method, system and device and storage medium

Abstract

The invention discloses a vehicle loss assessment list determination method, system and device and a storage medium. The method comprises the following steps: acquiring a license plate picture, a frame picture and a first picture with a virtual damage area of a user, and generating guidance information for guiding the user to place a second picture in a damage detection frame; the second picture comprises one or more vehicle damages; when it is detected that the vehicle damage of the second picture is located in a preset area of a damage detection frame and the center of the vehicle damage coincides with the center of the damage detection frame, determining vehicle parts corresponding to all the vehicle damage from the damage detection frame; according to all the vehicle parts and the first picture, second guiding information used for guiding shooting of the contour picture of the vehicle parts is generated; and determining a vehicle loss assessment list according to the license plate picture, the frame picture, the second picture and the contour picture. The method can be widely applied to the technical field of image processing.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, system, device and storage medium for determining a vehicle damage assessment list. Background Art

[0002] In the relevant technologies, the core business of traditional auto insurance can be roughly divided into four categories: insurance, investigation, claims, repair or maintenance. Among them, in the investigation stage, the surveyor needs to go to the scene to collect evidence after receiving the assigned task, give a damage estimate after careful evaluation, and finally submit a damage report. When an accident occurs, if the user wants to initiate the claims process, he needs to report the case first and wait for the surveyor to collect evidence on site. After that, he needs to track the repair process of the accident vehicle. During the repair, the damage assessor often needs to go to the repair shop to develop a detailed repair plan. After the insurance company has reviewed the invoice and other materials, it will make insurance claims. Waiting for vehicle inspection takes a long time, which can easily lead to a poor insurance experience for users. At the same time, the vehicle inspection and review has invested a lot of manpower costs, and the review results also rely on the subjective judgment of the vehicle inspector. There is a lack of unified standards, which leads to a decrease in the accuracy of vehicle damage assessment. Therefore, the problems existing in the relevant technologies need to be solved urgently. Summary of the invention

[0003] The purpose of this application is to solve one of the technical problems existing in the related art to at least a certain extent.

[0004] To this end, an object of an embodiment of the present application is to provide a method, system, device and storage medium for determining a vehicle damage assessment list. This method can reduce the participation of human resources in the vehicle damage assessment list. This method can improve the accuracy of vehicle damage assessment and save human resource costs.

[0005] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present application include:

[0006] On the one hand, an embodiment of the present application provides a method for determining a vehicle damage assessment list, comprising:

[0007] Acquire a license plate image, a frame image, and a first image of a virtual damage area of ​​a vehicle taken by a user, and generate first guidance information for guiding the user to place a second image in a damage detection frame according to the first guidance information; the second image includes one or more vehicle damages;

[0008] When it is detected that the vehicle damage is located within a first preset area of ​​the damage detection frame, and the center of the vehicle damage coincides with the center of the damage detection frame, determining a vehicle component corresponding to the vehicle damage from the damage detection frame;

[0009] generating second guidance information according to the vehicle component and the first picture, so that the user takes a contour picture of the vehicle component according to the second guidance information;

[0010] A vehicle damage assessment list is determined based on the license plate image, the frame image, the second image, and the outline image.

[0011] The present application obtains a license plate image, a frame image and a first image with a virtual vehicle damage area selected by the user, and generates first guidance information for guiding the user's operation, so that the user places the second image in a damage detection frame according to the first guidance information; the second image includes one or more vehicle damages; when it is detected that the vehicle damage is located in a first preset area of ​​the damage detection frame, and the center of the vehicle damage coincides with the center of the damage detection frame, the vehicle component corresponding to the vehicle damage is determined from the damage detection frame; according to the vehicle component and the first image, second guidance information is generated, so that the user takes a contour image of the vehicle component according to the second guidance information; according to the license plate image, the frame image, the second image and the contour image, a vehicle damage assessment list is determined; the present application can determine the vehicle damage assessment list through the license plate image, the frame image and the second image determined according to the first image with a virtual vehicle damage area selected by the user. Compared with the traditional solution, the present application can reduce the participation of human resources in the vehicle damage assessment list, improve the accuracy of vehicle damage assessment and save human resource costs.

[0012] In addition, the vehicle damage assessment list determination method according to the above embodiment of the present application may also have the following additional technical features:

[0013] Furthermore, in one embodiment of the present application, generating the second guidance information based on the vehicle component and the first picture includes: determining the actual area corresponding to the vehicle damage in the vehicle component; and when the vehicle virtual damage area is the same as the actual area, generating the second guidance information corresponding to the vehicle component.

[0014] Further, in one embodiment of the present application, determining the vehicle component corresponding to the vehicle damage from the damage detection frame includes:

[0015] Determine n first edge coordinates of the vehicle damage in the damage detection frame and a set of second coordinates of all the vehicle components in the damage detection frame, where n is a positive integer;

[0016] The vehicle component corresponding to the vehicle damage is determined according to the first edge coordinates and all sets of the second coordinates.

[0017] Further, in one embodiment of the present application, determining the vehicle component corresponding to the vehicle damage according to the first edge coordinate and all sets of the second coordinates includes:

[0018] When the n first edge coordinates are the same as the corresponding second coordinates in the second coordinate set, determining the vehicle component corresponding to the second coordinate set as the vehicle component corresponding to the vehicle damage;

[0019] When ni first edge coordinates are the same as the corresponding second coordinates in one second coordinate set, and i first edge coordinates are the same as the corresponding second coordinates in another second coordinate set, the second coordinate set whose corresponding second coordinates are the same as ni first edge coordinates is determined as one of the vehicle components corresponding to the vehicle damage, and another second coordinate set whose corresponding second coordinates are the same as i first edge coordinates is determined as another of the vehicle components corresponding to the vehicle damage; wherein i is a positive integer, and n is greater than i.

[0020] Furthermore, in one embodiment of the present application, the method further includes: when damage to any of the vehicles in the second image is not detected, generating third guidance information so that the user can reposition the second image according to the third guidance information.

[0021] Furthermore, in one embodiment of the present application, the method also includes: when it is detected that the vehicle damage is not located within the first preset area of ​​the damage detection frame, generating fourth guidance information so that the user can coincide the center of the vehicle damage with the center of the damage detection frame according to the fourth guidance information.

[0022] Furthermore, in one embodiment of the present application, determining the vehicle damage assessment list based on the license plate picture, the frame picture, the second picture and the contour picture includes: determining vehicle model features based on the license plate picture and the frame picture; inputting the vehicle model features, the second picture and the contour picture into a trained vehicle damage assessment model to determine the vehicle damage assessment list.

[0023] On the other hand, an embodiment of the present application provides a vehicle damage assessment list determination system, comprising:

[0024] an acquisition module, used to acquire a license plate image, a frame image, and a first image with a virtual vehicle damage area selected by a user, and generate first guidance information for guiding the user to place a second image in a damage detection frame according to the first guidance information; the second image includes one or more vehicle damages;

[0025] A first processing module, configured to determine a vehicle component corresponding to the vehicle damage from the damage detection frame when it is detected that the vehicle damage is located within a first preset area of ​​the damage detection frame and the center of the vehicle damage coincides with the center of the damage detection frame;

[0026] A second processing module, configured to generate second guidance information according to the vehicle component and the first picture, so that the user can take a contour picture of the vehicle component according to the second guidance information;

[0027] The third processing module is used to determine the vehicle damage assessment list based on the license plate image, the frame image, the second image and the outline image.

[0028] On the other hand, an embodiment of the present application provides a vehicle damage assessment list determination device, comprising:

[0029] at least one processor;

[0030] at least one memory for storing at least one program;

[0031] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned vehicle damage assessment list determination method.

[0032] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned method for determining the vehicle damage assessment list.

[0033] The advantages and benefits of the present application will be partially given in the following description, and partially become apparent from the following description, or be understood through the practice of the present application:

[0034] The embodiment of the present application discloses a method, system, device and storage medium for determining a vehicle damage list, which obtains a license plate picture, a frame picture and a first picture with a virtual vehicle damage area selected by the user, and generates a first guidance information for guiding the user operation, so that the user places the second picture in a damage detection frame according to the first guidance information; the second picture includes one or more vehicle damages; when the vehicle damage is detected to be located in a first preset area of ​​the damage detection frame, and the center of the vehicle damage coincides with the center of the damage detection frame, the vehicle parts corresponding to the vehicle damage are determined from the damage detection frame; according to the vehicle parts and the first picture, second guidance information is generated, so that the user takes a contour picture of the vehicle parts according to the second guidance information; according to the license plate picture, the frame picture, the second picture and the contour picture, the vehicle damage list is determined; the present application can determine the vehicle damage list through the license plate picture, the frame picture and the second picture determined according to the first picture with a virtual vehicle damage area selected by the user. Compared with the traditional solution, the present application can reduce the participation of human resources in the vehicle damage list, improve the accuracy of vehicle damage assessment and save human resource costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present application or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 A schematic diagram of the steps of a method for determining a vehicle damage assessment list provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of the steps of generating second guidance information according to vehicle parts and a first picture in a method for determining a vehicle damage assessment list provided in an embodiment of the present application;

[0038] Figure 3 A schematic diagram of the steps of determining vehicle parts corresponding to vehicle damage from a damage detection frame in a method for determining a vehicle damage assessment list provided in an embodiment of the present application;

[0039] Figure 4 A schematic diagram of the steps of determining a vehicle damage assessment list according to a license plate image, a frame image, a second image, and a contour image in a method for determining a vehicle damage assessment list provided in an embodiment of the present application;

[0040] Figure 5A schematic diagram of a system interface for photographing a license plate and a frame number through icon guidance in a method for determining a vehicle damage assessment list provided in an embodiment of the present application;

[0041] Figure 6 A schematic diagram of a system interface in which a user can select a damaged area of ​​a vehicle in a method for determining a vehicle damage assessment list provided in an embodiment of the present application;

[0042] Figure 7 A schematic diagram of an interface with a damage detection box and a star mark in a method for determining a vehicle damage assessment list provided in an embodiment of the present application;

[0043] Figure 8 A schematic diagram of an interface for guiding contour photography in a method for determining a vehicle damage assessment list provided in an embodiment of the present application;

[0044] Fig. 9 A schematic diagram of a flow chart of another method for determining a vehicle damage assessment list provided in an embodiment of the present application;

[0045] Fig.10 A schematic diagram of the structure of a vehicle damage assessment list determination system provided in an embodiment of the present application;

[0046] Fig.11 A schematic diagram of the structure of a vehicle damage assessment list determination device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0048] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0050] First, let’s explain the artificial intelligence model that appears in this application:

[0051] YOLO model: YOLO's model structure is based on a deep convolutional neural network (CNN), usually using Darknet as the backbone network. Darknet is a custom convolutional neural network structure with a deep layer and a large receptive field, which can effectively capture the feature information in the image. YOLOv1 is the first version of the YOLO algorithm, which uses a 24-layer Darknet network structure and achieves good performance on the PASCAL VOC dataset. Subsequently, improved versions such as YOLOv2 and YOLOv3 were launched one after another. They have optimized the model structure, loss function, training strategy, etc., further improving the detection accuracy and speed. Due to the real-time and high accuracy characteristics of YOLO, it is widely used in various target detection tasks, such as autonomous driving, video surveillance, face recognition, etc. In the field of autonomous driving, YOLO can detect obstacles such as vehicles and pedestrians on the road in real time, providing important perception information for autonomous driving systems. In the field of video surveillance, YOLO can be used to detect abnormal behaviors, intruders and other targets, and improve the intelligence level of the monitoring system. In addition, YOLO can also be used in image retrieval, augmented reality and other fields.

[0052] U-Net model: The U-Net model is named for its unique U-shaped network structure, which combines the symmetrical design of the encoder and decoder to achieve efficient image segmentation. Specifically, the network structure of U-Net can be divided into the following parts: Encoder (contraction path): The encoder part consists of multiple convolutional layers and pooling layers, which are used to gradually compress the spatial dimensions of the input image to extract high-level features of the image. Each convolutional layer is usually followed by an activation function (such as ReLU) to increase the nonlinear ability of the network. Decoder (expansion path): The decoder part consists of multiple upsampling layers and convolutional layers, which are used to gradually restore the spatial dimensions of the image and use the feature information in the encoder for detail recovery. The upsampling layer is usually implemented using methods such as transposed convolution or bilinear interpolation. Skip connection: Skip connection is one of the key components in the U-Net model. It directly passes the feature map in the encoder to the layer of the corresponding scale in the decoder, which helps to preserve the detail information of the image and accelerate the convergence process. This splicing operation enables U-Net to capture the contextual information of the image while retaining the detail information of the image, thereby improving the accuracy of segmentation.

[0053] The working principle of U-Net is mainly based on its unique network structure and effective feature extraction and fusion mechanism. In the encoder part, the network gradually extracts high-level features of the image through convolutional layers and pooling layers, and reduces the spatial dimension. In the decoder part, the network gradually restores the spatial dimension of the image through upsampling layers and convolutional layers, and uses the feature information in the jump connection to restore details. This structure enables U-Net to achieve satisfactory segmentation results with fewer training samples.

[0054] In the relevant technologies, the core business of traditional auto insurance can be roughly divided into four categories: insurance, investigation, claims, repair or maintenance. Among them, in the investigation stage, the surveyor needs to go to the scene to collect evidence after receiving the assigned task, give a damage estimate after careful evaluation, and finally submit a damage report. When a vehicle accident occurs, if the user wants to initiate the claims process, he needs to report the case first and wait for the surveyor to collect evidence on site. After that, he needs to track the repair process of the accident vehicle. When the vehicle is repaired, the damage assessor often needs to go to the repair shop to develop a detailed repair plan. After the insurance company has reviewed the invoice and other materials, it will make insurance compensation to the corresponding owner of the vehicle. The process of waiting for vehicle inspection takes a long time, which can easily cause the user's insurance experience to be poor. At the same time, the vehicle inspection and review in this process has invested a lot of manpower costs, and the review results also rely on the subjective judgment of the vehicle inspector, and lack of unified standards. Therefore, there are still technical problems that need to be solved in the relevant technologies.

[0055] Therefore, refer to Figure 1 , Figure 1 This is a schematic diagram of the steps of the method for determining the vehicle damage list of this application. Figure 1 The vehicle damage assessment list determination method of the present application may include steps S101 to S104.

[0056] S101, obtaining a license plate image, a frame image, and a first image of a virtual damage area of ​​a vehicle selected by a user, and generating first guidance information for guiding the user's operation, so that the user places a second image in a damage detection frame according to the first guidance information; the second image includes one or more vehicle damages.

[0057] It is understandable that the license plate image can be an image with a corresponding license plate of the vehicle that can be recognized by the recognition device. The license plate image can be an image taken by a user through a shooting device that establishes a wired or wireless connection with the processor. The shooting device in this embodiment can be a mobile phone, a tablet computer, a camera or other shooting devices. The frame image can be an image with a corresponding vehicle model that can be recognized, such as an image with a vehicle vin code or an image of the entire car frame. When the frame image is an image of the entire car frame, the frame image can include a front photo, a rear photo, a left photo and a rear photo of the frame. The first image is a two-dimensional or three-dimensional image of the whole vehicle after the user circles the virtual damage area of ​​the vehicle. The first image can include multiple user-circled vehicle virtual damage areas, each user-circled vehicle virtual damage area can correspond to a vehicle component or more than two user-circled vehicle virtual damage areas can correspond to a vehicle component. The first guidance information can be information for guiding user operations, which can be displayed on a display to remind the user. Vehicle damage can be damage on the actual vehicle body. The second image can be a picture taken by the user with one or more vehicle damages. Each damage can correspond to one or more vehicle components, and a vehicle component can also correspond to one or more damages.

[0058] In some feasible embodiments of the present application, the processor can establish a wired or wireless connection with the shooting device. After the connection is established, the processor can obtain the license plate image taken by the user and the frame images in the four directions of front, back, left and right from the shooting device. At the same time, the processor can establish a wired or wireless connection with the display system. After the connection is established, the processor obtains a first image of the virtual damage area of ​​the vehicle selected by the user from the display system. After obtaining the first image, the processor can generate a first guidance information for guiding the user's operation and display it on the screen of the display system. The user can place a second image including a vehicle damage in the damage detection frame of the detection device connected to the processor according to the first guidance information on the screen.

[0059] In other feasible embodiments of the present application, the processor can establish a wired or wireless connection with the shooting device. After the connection is established, the processor can obtain the license plate image and the frame image with the VIN code taken by the user from the shooting device, and the processor can establish a wired or wireless connection with the display system. After the connection is established, the processor obtains a first image of the virtual damage area of ​​the vehicle selected by the user from the display system. After obtaining the first image, the processor can generate a first guidance information for guiding the user's operation and display it on the screen of the display system. The user can place a second image including two or more vehicle damages in the damage detection frame of the detection device connected to the processor according to the first guidance information on the screen.

[0060] It should be noted that the wired connection method of the above-mentioned embodiment may include a connection between a mobile device and a processing module, and may also include a connection between a processing module and a hardware device, as well as a wired connection between other devices currently known or to be developed in the future and the processing module; and the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (Ultra Wide Band) connection, and other wireless connection methods currently known or to be developed in the future.

[0061] S102: When it is detected that the vehicle damage is located within a first preset area of ​​the damage detection frame, and the center of the vehicle damage coincides with the center of the damage detection frame, determining a vehicle component corresponding to the vehicle damage from the damage detection frame.

[0062] It is understandable that the first preset area can be an area defined by the relevant personnel themselves. The first preset area can be an area that coincides with the center of the damage detection frame, and the length of the area can be the same as the length of the damage detection frame, or it can be 1 / 2 of the length of the damage detection frame, or it can be 1 / 4 of the length of the damage detection frame. Similarly, the width of the area can be the same as the width of the damage detection frame, or it can be 1 / 2 of the width of the damage detection frame, or it can be 1 / 4 of the width of the damage detection frame. The damage detection frame may include one or more vehicle parts, or one or more damages. Each vehicle part may include one or more damages. The center of the damage detection frame may include a star mark, and the center of the star mark coincides with the center of the damage detection frame.

[0063] In some feasible embodiments of the present application, after the user places the second image including one or more vehicle damages in a damage detection frame of a detection device connected to the processor according to the first guidance information on the screen, the processor can detect the vehicle damage. When it is detected that any actual vehicle damage in the vehicle image including one or more vehicle damages is within a rectangular area that coincides with the center of the damage detection frame and whose length and width are only half of the length and width of the damage detection frame, and the center of any vehicle damage coincides with the center of the damage detection frame and the center of the star mark of the damage detection frame, the processor can determine the vehicle parts corresponding to all vehicle damages from the damage detection frame according to the algorithm.

[0064] In some other feasible embodiments of the present application, in some feasible embodiments of the present application, after the user places the second image including one or more vehicle damages in a damage detection frame of a detection device connected to the processor according to the first guidance information on the screen, the processor can detect the vehicle damage. When it is detected that any actual vehicle damage in the vehicle image including one or more vehicle damages is within a rectangular area that coincides with the center of the damage detection frame and whose length and width are only 1 / 4 of the length and width of the damage detection frame, and the center of any vehicle damage coincides with the center of the damage detection frame and the center of the star mark of the damage detection frame, the processor can determine the vehicle parts corresponding to all vehicle damages from the damage detection frame according to the algorithm.

[0065] S103: Generate second guidance information according to the vehicle component and the first picture, so that the user can take a contour picture of the vehicle component according to the second guidance information.

[0066] It is understandable that the second guidance information can be used to guide the user to take a picture of the outline of the vehicle component. The first guidance information can be "please take a picture of the outline of the vehicle component".

[0067] In some feasible embodiments of the present application, the processor may compare all vehicle components in the damage detection frame with the vehicle virtual damage area in the first image. According to the comparison result, the processor may generate second guidance information. The second guidance information may guide the user to take a contour image of the vehicle component.

[0068] S104, determining a vehicle damage assessment list based on the license plate image, the frame image, the second image and the outline image.

[0069] It is understandable that the license plate image and the frame image can determine the identity of the vehicle and the owner corresponding to the vehicle.

[0070] In some feasible embodiments of the present application, the processor can determine the identity of the vehicle and the corresponding owner of the vehicle based on the license plate image and the frame image, and after obtaining the identity of the owner and the vehicle, the owner identity information, the vehicle identity information, the second image including one or more vehicle damages, and the contour image of the damaged component can be input into the trained artificial intelligence model to obtain the corresponding vehicle damage assessment list.

[0071] In summary, a method for determining a vehicle damage list in this embodiment obtains a license plate image, a frame image, and a first image with a vehicle virtual damage area selected by the user, and generates a first guidance information for guiding the user's operation, so that the user places the second image in the damage detection frame according to the first guidance information; the second image includes one or more vehicle damages; when it is detected that the vehicle damage is located in the first preset area of ​​the damage detection frame, and the center of the vehicle damage coincides with the center of the damage detection frame, the vehicle parts corresponding to the vehicle damage are determined from the damage detection frame; according to the vehicle parts and the first image, second guidance information is generated, so that the user takes a contour image of the vehicle parts according to the second guidance information; according to the license plate image, the frame image, the second image, and the contour image, the vehicle damage list is determined; the present application can determine the vehicle damage list through the license plate image, the frame image, and the second image determined according to the first image with a vehicle virtual damage area selected by the user. Compared with the traditional solution, the present application can reduce the participation of human resources in the vehicle damage list, improve the accuracy of vehicle damage assessment, and save human resource costs.

[0072] Further, refer to Figure 2 , Figure 2 FIG. 1 is a schematic diagram of the steps of generating the second guidance information according to the vehicle components and the first picture in this embodiment. Figure 2 This step may include step S201 to step S202.

[0073] S201. Determine the actual area corresponding to the vehicle damage in the vehicle components.

[0074] S202: When the virtual damage area of ​​the vehicle is the same as the actual area, generate second guidance information corresponding to the vehicle component.

[0075] It is understandable that, for any vehicle component, the virtual damage area of ​​the vehicle circled by the user may be one, and correspondingly, the actual area corresponding to the vehicle damage photographed may also be one or more. The virtual damage area of ​​the vehicle circled by the user may be multiple, and correspondingly, the actual area corresponding to the vehicle damage photographed may also be one or more.

[0076] In some feasible embodiments of the present application, the processor may compare one or more actual areas on a damaged vehicle component with a user-selected vehicle virtual damage area. If all of the vehicle virtual damage areas are the same as all of the actual areas, the processor may generate second guidance information corresponding to the vehicle component. It should be noted that when the comparison areas are the same, they can be determined by the preset feature coordinates corresponding to each area. If the preset feature coordinates of the vehicle virtual damage area are the same as the feature coordinates of the actual area, it can be considered that the vehicle virtual damage area is the same as the actual area.

[0077] Exemplarily, there are four actual areas with vehicle damage on the vehicle, namely A, B, C and D. Area A and area B are located on the f component, while area C and area D are located on the g component, and the virtual vehicle damage areas selected by the user are areas A, B, C and E on the vehicle. Area A and area B are located on the f component actually photographed, and area C and area E are located on the g component. At this time, for the f component, because area A and area B of the virtual damage area of ​​the vehicle are the same as area A and area B of the actual area, the processor can generate the second guidance information corresponding to the f component, so that the user can take the outline picture of the f component according to the guidance information. For the g component, because area C and area E of the virtual damage area of ​​the vehicle are different from area C and area D of the actual area, the processor will not generate the second guidance information corresponding to the g component, so that the user can take the outline picture of the g component according to the guidance information, but will prompt the user to retake the pictures of area C and area D.

[0078] Further, refer to Figure 3 , Figure 3 Schematic diagram of the steps of determining the vehicle parts corresponding to the vehicle damage from the damage detection frame in this embodiment. Figure 3 In the step, the step may include step S301 to step S302.

[0079] S301, determining n first edge coordinates of vehicle damage in a damage detection frame and a second coordinate set of all vehicle components in the damage detection frame, where n is a positive integer.

[0080] S302: Determine the vehicle component corresponding to the vehicle damage according to the first edge coordinates and all second coordinate sets.

[0081] It is understandable that there may be many vehicle damages in the damage detection frame. Each vehicle damage may include n first edge coordinates. The second coordinate set may include a set of all coordinates of the vehicle component in the damage detection frame. The first edge coordinates and all coordinates of the vehicle component in the damage detection frame may be coordinates in the same coordinate system.

[0082] In some feasible embodiments of the present application, the processor may first determine n first edge coordinates of the vehicle damage in the damage detection frame and a second coordinate set of all vehicle components in the damage detection frame, where n is a positive integer. The processor may then determine the vehicle component corresponding to the vehicle damage based on the first edge coordinates and all second coordinate sets.

[0083] Furthermore, the step of determining a vehicle component corresponding to any vehicle damage according to the first edge coordinates and the second coordinate set may include step S401 or step S402.

[0084] S401. When the n first edge coordinates are the same as the corresponding second coordinates in the second coordinate set, determine the vehicle component corresponding to the second coordinate set as the vehicle component corresponding to the vehicle damage.

[0085] S402. When ni first edge coordinates are the same as the corresponding second coordinates in a second coordinate set, and i first edge coordinates are the same as the corresponding second coordinates in another second coordinate set, the second coordinate set in which the corresponding second coordinates are the same as the ni first edge coordinates is determined as a vehicle component corresponding to vehicle damage, and another second coordinate set in which the corresponding second coordinates are the same as the i first edge coordinates is determined as another vehicle component corresponding to vehicle damage; wherein i is a positive integer, and n is greater than i.

[0086] In some feasible embodiments of the present application, when n first edge coordinates are the same as a number of second coordinates corresponding to one of the vehicle components in the second coordinate set, the vehicle component corresponding to the second coordinate set is determined as the vehicle component corresponding to the vehicle damage. When ni first edge coordinates are the same as a number of second coordinates corresponding to one of the second coordinate sets, and i first edge coordinates are the same as a number of second coordinates corresponding to another second coordinate set, the vehicle component corresponding to one of the second coordinate sets is determined as a vehicle component corresponding to the vehicle damage; the vehicle component corresponding to another second coordinate set is determined as another vehicle component corresponding to the vehicle damage; wherein n and i are both integers, and n is greater than i.

[0087] Similarly, when nik first edge coordinates are the same as a number of second coordinates corresponding to one of the second coordinate sets, and i first edge coordinates are the same as a number of second coordinates corresponding to the second second coordinate set, and k first edge coordinates are the same as a number of second coordinates corresponding to the third second coordinate set, the vehicle component corresponding to one of the second coordinate sets is determined as a vehicle component corresponding to vehicle damage. The vehicle component corresponding to the second second coordinate set is determined as another vehicle component corresponding to vehicle damage, and the vehicle component corresponding to the third second coordinate set is determined as another vehicle component corresponding to vehicle damage.

[0088] Similarly, when nikj first edge coordinates are the same as a number of second coordinates corresponding to one of the second coordinate sets, and i first edge coordinates are the same as a number of second coordinates corresponding to the second second coordinate set, and k first edge coordinates are the same as a number of second coordinates corresponding to the third second coordinate set, and j first edge coordinates are the same as a number of second coordinates corresponding to the fourth second coordinate set, the vehicle component corresponding to one of the second coordinate sets is determined to be a vehicle component corresponding to vehicle damage. The vehicle component corresponding to the second second coordinate set is determined to be a second vehicle component corresponding to vehicle damage, the vehicle component corresponding to the third second coordinate set is determined to be another third vehicle component corresponding to vehicle damage, and the vehicle component corresponding to the fourth second coordinate set is determined to be a third vehicle component corresponding to vehicle damage.

[0089] For example, if a vehicle damage has 4 edge coordinates in the damage detection frame, and they are the same as the 4 coordinates in the coordinate set corresponding to part A, then the vehicle damage is located in part A. If a vehicle damage has 4 edge coordinates in the damage detection frame, and 3 of the 4 edge coordinates are the same as the 3 coordinates in the coordinate set corresponding to part A, and one coordinate is the same as one coordinate corresponding to part B, then the vehicle damage is located in part A and part B.

[0090] Furthermore, in one embodiment of the present application, the vehicle damage assessment list determination method may also include step S105.

[0091] S105. When damage to any vehicle in the second image is not detected, generate third guidance information so that the user can reposition the second image according to the third guidance information.

[0092] In some feasible embodiments of the present application, the processor can obtain the license plate picture, the frame picture and the first picture of the virtual damage area of ​​the vehicle selected by the user, and generate the first guidance information for guiding the user operation, so that the user places the second picture in the damage detection frame according to the first guidance information; the second picture includes one or more vehicle damages. When any vehicle damage of the second picture is not detected, the processor can generate the third guidance information, so that the user can re-place the second picture according to the third guidance information, and place the second picture in the damage detection frame according to the first guidance information for guiding the user operation. When it is detected that any vehicle damage of the second picture is located in the first preset area of ​​the damage detection frame, and the center of any vehicle damage coincides with the center of the damage detection frame, the vehicle parts corresponding to all vehicle damages are determined from the damage detection frame; according to the vehicle parts and the first picture, the second guidance information is generated, so that the user can take the outline picture of the vehicle parts according to the second guidance information; according to the license plate picture, the frame picture, the second picture and the outline picture, the processor can determine the vehicle damage assessment list.

[0093] Furthermore, the method for determining a vehicle damage assessment list may also include step S106.

[0094] S106. When it is detected that the vehicle damage is not located within the first preset area of ​​the damage detection frame, fourth guidance information is generated to enable the user to align the center of the vehicle damage with the center of the damage detection frame according to the fourth guidance information.

[0095] In some feasible embodiments of the present application, the processor can obtain a license plate image, a frame image, and a first image of a virtual damage area of ​​the vehicle selected by the user, and generate a first guidance information for guiding the user's operation, so that the user places the second image in the damage detection frame according to the first guidance information; the second image includes one or more vehicle damages. When it is detected that the vehicle damage is not located in the first preset area of ​​the damage detection frame, a fourth guidance information is generated, so that the user overlaps the center of the vehicle damage with the center of the damage detection frame according to the fourth guidance information. After the user overlaps the center of any vehicle damage with the center of the damage detection frame according to the fourth guidance information, the processor can determine the vehicle parts corresponding to all vehicle damages from the damage detection frame. According to the vehicle parts and the first image, the second guidance information is generated, so that the user takes a contour image of the vehicle parts according to the second guidance information. Then, the processor can determine the vehicle damage assessment list according to the license plate image, the frame image, the second image, and the contour image.

[0096] Further, refer to Figure 4 , Figure 4 This is a schematic diagram of the steps for determining a vehicle damage list based on the license plate image, frame image, second image, and outline image. Figure 7This step may include step S501-step S502.

[0097] S501: Determine vehicle model characteristics based on the license plate image and the frame image.

[0098] S502: Input the vehicle model features, the second image, and the outline image into the trained vehicle damage assessment model to determine the vehicle damage assessment list.

[0099] In some feasible embodiments of the present application, the vehicle model features are used to characterize the identity information of the vehicle and the identity information of the owner. The vehicle damage assessment model can be an existing artificial intelligence multimodal model or an artificial intelligence image recognition model. The vehicle damage assessment model can adopt image recognition models such as YOLO or U-Net. During training, license plate images, frame images, second images, and contour images can be extracted from historical data to train the model, and finally a trained vehicle damage assessment model is obtained. After obtaining the trained vehicle damage assessment model, the vehicle model features, the second image, and the contour image are input into the corresponding vehicle damage assessment model to obtain the final vehicle damage assessment list. The final vehicle damage assessment list can also be saved for the next vehicle damage assessment model.

[0100] The implementation principle of the present application scheme is explained below with reference to the accompanying drawings.

[0101] In some embodiments, reference Figure 5-Figure 9 . First, the user clicks "Start Shooting", and the vehicle damage assessment list determination system can enter the damage assessment photo shooting stage.

[0102] When taking damage assessment photos, the system can first generate icon instructions to guide users to take photos of the license plate and frame number, obtain image information of the license plate and frame number, and thus reduce the situation where some users cannot find the frame number.

[0103] After obtaining the license plate and frame number information, the system will start to take pictures of the damaged car and replace the parts. In this process, the system can pop up a virtual 3D car to let the user select the damaged area of ​​the vehicle.

[0104] After the user has selected the damaged area of ​​the vehicle, the corresponding guidance information is generated to guide the user to aim the camera's star at the center of the damage, and detect whether the user has completely placed the damage in the damage detection box. At the same time, the built-in damage detection model is called to detect vehicle damage.

[0105] If the system detects damage, and if the damage is located in the middle area, which is a rectangle that is one-fourth the length and width of the screen, the mobile component segmentation model will be synchronously called. If the component segmentation model cannot recognize the component, the system will generate a prompt "Unable to recognize the component, please move away". If the component segmentation model called by the system can recognize the component, then combined with the damage detection frame and the mobile component segmentation model, the system can determine which component the damage is located on. Specifically, the system can convert the damaged edge and the component into coordinates in the same coordinate system, determine the specific component where the damage is located based on the intersection of the coordinates, and determine whether the vehicle component matches the beam area circled by the user, which can be determined by the system's internal algorithm. If it matches, the system can generate a prompt message to prompt the user to take outline photos of these components;

[0106] After the system detects damage, if the damage is not located in the middle area (the center of the damage is located in a rectangle that is one-fourth the length and width of the screen), a prompt message is generated to prompt the user "Please aim the star at the center of the damage". If the damage detected by the system is still not located in the middle area after 3 seconds without the system's damage detection frame shaking, the damaged component with the center of the damage closest to the center of the screen is selected and a prompt message for the corresponding component is generated. If the system cannot detect damage within 3 seconds without the system's damage detection frame shaking, the component segmentation model is called. If the system cannot recognize the vehicle component, a prompt "Unable to recognize the component, please move away" is generated; if the system can recognize the component, the current frame is retained, and the component with the largest area is selected for prompting. After obtaining the components identified in the above damage photo, the system can generate guidance information to guide the user to shoot the complete component.

[0107] After the shooting process is completed, the system will obtain the license plate, frame VIN code, photos of damaged vehicle parts and corresponding outline photos of vehicle parts, and transmit all the images taken to the background. Each damage detail photo and its corresponding part outline photo are grouped together. The damage category and repair plan are determined based on the two images, and the AI ​​damage assessment list is given in combination with the license plate and frame VIN code.

[0108] To summarize, the present application guides customers when they take damage assessment pictures during the damage assessment process. On the one hand, it can guide users who are not familiar with vehicle parts to take pictures of license plates and VIN codes for vehicle inspection. On the other hand, after the user takes a picture of recognizable damage, the guidance icon in the lower right corner can be used to supplement the picture with an outline photo of the corresponding part of the damage. At the same time, the outline photo of the part is matched with the detail photo of the damage one by one, so as to more accurately derive the accurate damage and repair plan of each part. On the other hand, the vehicle part segmentation model and the vehicle damage recognition model are built into the shooting process. When the user points the lens at a part or damage, it automatically recognizes and takes a screenshot, which saves the user's operation and avoids the erroneous shooting of users who are not familiar with the damage and parts of the car to a certain extent, thereby improving the accuracy of the AI ​​model damage assessment and laying the foundation for the ultimate realization of partial automatic damage assessment.

[0109] Reference Fig.10 , the embodiment of the present application also provides a vehicle damage assessment list determination system. The system may include an acquisition module 1001, a first processing module 1002, a second processing module 1003 and a third processing module 1004. Among them, the acquisition module 1001 is used to acquire a license plate image, a frame image and a first image of a virtual damage area of ​​a vehicle selected by a user, and generate a first guidance information for guiding the user to operate, so that the user places the second image in the damage detection frame according to the first guidance information; the second image includes one or more vehicle damages. The first processing module 1002 is used to determine the vehicle parts corresponding to the vehicle damage from the damage detection frame when it is detected that the vehicle damage is located in the first preset area of ​​the damage detection frame and the center of the vehicle damage coincides with the center of the damage detection frame. The second processing module 1003 is used to generate a second guidance information based on the vehicle parts and the first image, so that the user takes a contour image of the vehicle parts according to the second guidance information. The third processing module 1004 is used to determine the vehicle damage assessment list based on the license plate image, the frame image, the second image and the contour image.

[0110] It should be noted that the acquisition module 1001 can be any integrated circuit module or microprocessor module obtained by integrating a chip with a processing function and its peripheral circuits through existing integration technology. The first processing module 1002 can also be any integrated circuit module or microprocessor module obtained by integrating a chip with a processing function and its peripheral circuits through existing integration technology. The processing module can also include one or more memories. The second processing module 1003 can also be any integrated circuit module or microprocessor module obtained by integrating a chip with a processing function and its peripheral circuits through existing integration technology. The processing module can also include one or more memories. One or more memories can be used to store data such as mapping table information or retrieval results. The third processing module 1004 can also be any integrated circuit module or microprocessor module obtained by integrating a chip with a processing function and its peripheral circuits through existing integration technology. The processing module can also include one or more memories.

[0111] In some embodiments of the present application, the specific connection method and device settings of the acquisition module 1001 and the first processing module 1002, the first processing module 1002 and the second processing module 1003, and the third processing module 1004 and the second processing module 1003 are not limited.

[0112] Understandably, Figure 1 The contents of the vehicle damage assessment list determination method embodiment shown in the figure are applicable to the vehicle damage assessment list determination device embodiment. The functions specifically implemented by the vehicle damage assessment list determination device embodiment are the same as those of the embodiment shown in the figure. Figure 1 The vehicle damage list determination method embodiment shown is the same as that of the embodiment shown in FIG. Figure 1 The beneficial effects achieved by the vehicle damage assessment list determination embodiment shown are also the same.

[0113] Reference Fig.11 The embodiment of the present application also discloses a vehicle damage assessment list determination device, including:

[0114] at least one processor 1011;

[0115] At least one memory 1012, used to store at least one program;

[0116] When at least one program is executed by at least one processor 1011, at least one processor 1011 implements the following Figure 1 An embodiment of a method for determining a vehicle damage assessment list is shown.

[0117] It is understandable that if Figure 1 The vehicle damage assessment list determination method embodiment shown in the figure is applicable to the computer device embodiment. The functions specifically implemented by the computer device embodiment are similar to those in the example Figure 1 The vehicle damage list determination method embodiment shown is the same as that shown in the embodiment, and the beneficial effects achieved are the same as those shown in the embodiment. Figure 1 The beneficial effects achieved by the vehicle damage assessment list determination method embodiment shown are also the same.

[0118] The present application also discloses a computer-readable storage medium in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the following Figure 1 An embodiment of a method for determining a vehicle damage assessment list is shown.

[0119] It is understandable that if Figure 1 The vehicle damage assessment list determination method embodiment shown in the figure is applicable to the computer-readable storage medium embodiment. The functions specifically implemented by the computer-readable storage medium embodiment are similar to those in the embodiment shown in the figure. Figure 3 The vehicle damage list determination method embodiment shown is the same as that shown in the embodiment, and the beneficial effects achieved are the same as those shown in the embodiment. Figure 1 The beneficial effects achieved by the vehicle damage assessment list determination method embodiment shown are also the same.

[0120] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the application is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part described as a larger operation is performed independently.

[0121] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present application. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional techniques of the engineer. Therefore, those skilled in the art can implement the present application set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the attached claims and their equivalents.

[0122] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0123] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0124] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0125] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0126] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0127] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0128] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

[0129] In the description of this specification, the description with reference to the terms "one embodiment", "another embodiment" or "certain embodiments" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0130] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A method for determining a vehicle damage assessment list, characterized in that: include: Acquire a license plate image, a frame image, and a first image of a virtual damage area of ​​a vehicle taken by a user, and generate first guidance information for guiding the user to place a second image in a damage detection frame according to the first guidance information; the second image includes one or more vehicle damages; When it is detected that the vehicle damage is located within a first preset area of ​​the damage detection frame, and the center of the vehicle damage coincides with the center of the damage detection frame, determining a vehicle component corresponding to the vehicle damage from the damage detection frame; generating second guidance information according to the vehicle component and the first picture, so that the user takes a contour picture of the vehicle component according to the second guidance information; A vehicle damage assessment list is determined based on the license plate image, the frame image, the second image, and the outline image.

2. A method for determining a vehicle damage assessment list according to claim 1, characterized in that: The generating second guidance information according to the vehicle component and the first picture includes: Determining an actual area corresponding to the vehicle damage in the vehicle component; When the virtual damage area of ​​the vehicle is the same as the actual area, second guidance information corresponding to the vehicle component is generated.

3. A method for determining a vehicle damage assessment list according to claim 1, characterized in that: The determining, from the damage detection frame, a vehicle component corresponding to the vehicle damage comprises: Determine n first edge coordinates of the vehicle damage in the damage detection frame and a set of second coordinates of all the vehicle components in the damage detection frame, where n is a positive integer; The vehicle component corresponding to the vehicle damage is determined according to the first edge coordinates and all sets of the second coordinates.

4. A method for determining a vehicle damage assessment list according to claim 3, characterized in that: The determining the vehicle component corresponding to the vehicle damage according to the first edge coordinate and all the second coordinate sets includes: When the n first edge coordinates are the same as the corresponding second coordinates in the second coordinate set, determining the vehicle component corresponding to the second coordinate set as the vehicle component corresponding to the vehicle damage; When ni first edge coordinates are the same as the corresponding second coordinates in one second coordinate set, and i first edge coordinates are the same as the corresponding second coordinates in another second coordinate set, the second coordinate set in which the corresponding second coordinates are the same as ni first edge coordinates is determined as one of the vehicle components corresponding to the vehicle damage, and another second coordinate set in which the corresponding second coordinates are the same as i first edge coordinates is determined as another of the vehicle components corresponding to the vehicle damage; wherein i is a positive integer, and n is greater than i.

5. A method for determining a vehicle damage assessment list according to claim 1, characterized in that: The method further comprises: When damage to any of the vehicles in the second image is not detected, third guidance information is generated to enable the user to reposition the second image according to the third guidance information.

6. A method for determining a vehicle damage assessment list according to claim 1, characterized in that: The method further comprises: When it is detected that the vehicle damage is not located within the first preset area of ​​the damage detection frame, fourth guidance information is generated to enable the user to coincide the center of the vehicle damage with the center of the damage detection frame according to the fourth guidance information.

7. A method for determining a vehicle damage assessment list according to claim 1, characterized in that: Determining the vehicle damage assessment list according to the license plate image, the frame image, the second image, and the outline image includes: Determining vehicle model characteristics according to the license plate image and the frame image; The vehicle model features, the second image and the contour image are input into a trained vehicle damage assessment model to determine a vehicle damage assessment list.

8. A vehicle damage assessment list determination system, characterized in that: include: an acquisition module, used to acquire a license plate image, a frame image, and a first image of a virtual damage area of ​​a vehicle selected by a user, and generate first guidance information for guiding the user to place a second image in a damage detection frame according to the first guidance information; the second image includes one or more vehicle damages; A first processing module, configured to determine a vehicle component corresponding to the vehicle damage from the damage detection frame when it is detected that the vehicle damage is located within a first preset area of ​​the damage detection frame and the center of the vehicle damage coincides with the center of the damage detection frame; A second processing module, configured to generate second guidance information according to the vehicle component and the first picture, so that the user can take a contour picture of the vehicle component according to the second guidance information; The third processing module is used to determine the vehicle damage assessment list based on the license plate image, the frame image, the second image and the outline image.

9. A vehicle damage assessment list determination device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the vehicle damage assessment list determination method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program, when executed by the processor, is used to implement the vehicle damage assessment list determination method as described in any one of claims 1-7.

Images