CN117557221A - Method, device, equipment and readable medium for generating vehicle damage report - Google Patents
Method, device, equipment and readable medium for generating vehicle damage report Download PDFInfo
- Publication number
- CN117557221A CN117557221A CN202311538252.5A CN202311538252A CN117557221A CN 117557221 A CN117557221 A CN 117557221A CN 202311538252 A CN202311538252 A CN 202311538252A CN 117557221 A CN117557221 A CN 117557221A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- damage
- region
- image
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000006378 damage Effects 0.000 title claims abstract description 155
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 38
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012098 association analyses Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 208000027418 Wounds and injury Diseases 0.000 claims description 2
- 208000014674 injury Diseases 0.000 claims description 2
- 230000006735 deficit Effects 0.000 claims 2
- 230000001771 impaired effect Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 11
- 230000008901 benefit Effects 0.000 abstract description 6
- 238000007689 inspection Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003902 lesion Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013316 zoning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Finance (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the disclosure discloses a method, a device, electronic equipment and a readable medium for generating a vehicle damage report. One embodiment of the method comprises the following steps: acquiring vehicle information and a vehicle damage image set of a damaged vehicle; generating a vehicle damage appearance image of the damaged vehicle according to the vehicle damage image set; comparing the vehicle information, the vehicle damage appearance image and the input information of the damaged vehicle to obtain a comparison result; and responding to the comparison result meeting the preset condition, inputting the vehicle damage appearance image into a pre-trained damage detection model, and obtaining a damage evaluation report of the damaged vehicle. The implementation mode has the advantages of multidimensional detection, high efficiency, accuracy, objectivity, fairness, automatic processing, customization, expandability and the like, can improve auditing efficiency and accuracy, reduces risk and management cost of insurance companies, and provides better insurance service experience for clients.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a method, a device, electronic equipment and a readable medium for generating a vehicle damage report.
Background
The vehicle license verification and verification is one of important links of insurance companies for performing risk control on the underwriting targets in the vehicle insurance process. The insurance clients are mainly legal groups and individuals with various motor vehicles, and the insurance targets are mainly various types of automobiles, but also comprise special vehicles such as electric cars, battery cars and the like, motorcycles and the like.
However, the traditional auditing mode generally needs to rely on manpower to audit a large number of vehicle damage images, but the number of the vehicle damage images is large, the images often comprise accessory areas, accessory communication areas, accessory damage areas and the like, the association relation between each image also needs to be automatically checked by auditing personnel, in addition, the auditing standards and requirements of different areas, different vehicle types and different insurance companies are different, a large number of auditing experiences of the auditing personnel are required to be accumulated, the manual auditing mode also needs a large number of labor costs, the time-consuming efficiency is quite low, the auditing is easily influenced by subjective factors of the auditing personnel, various reasons lead to longer auditing process flow, and the auditing result accuracy is difficult to ensure.
Disclosure of Invention
The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose a method, an apparatus, an electronic device, and a computer-readable medium for generating a vehicle damage report, to solve the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a method for generating a vehicle damage report, the method comprising: acquiring vehicle information and a vehicle damage image set of a damaged vehicle; generating a vehicle damage appearance image of the damaged vehicle according to the vehicle damage image set; comparing the vehicle information with the vehicle damage appearance image with the input information of the damaged vehicle to obtain a comparison result; and responding to the comparison result to meet a preset condition, inputting the vehicle damage appearance image into a pre-trained damage detection model, and obtaining a damage evaluation report of the damaged vehicle.
In a second aspect, some embodiments of the present disclosure provide a device for generating a vehicle damage report, the device including: an acquisition unit configured to acquire vehicle information and a vehicle loss image set of a damaged vehicle; a first generation unit configured to generate a vehicle loss appearance image of the damaged vehicle from the vehicle loss image set; the comparison unit is configured to obtain a comparison result by using the vehicle information and the vehicle damage appearance image to compare with the input information of the damaged vehicle; and the second generation unit is configured to respond to the comparison result to meet a preset condition, input the vehicle damage appearance image into a pre-trained damage detection model and obtain a damage evaluation report of the damaged vehicle.
In a third aspect, an embodiment of the present application provides an electronic device, where the network device includes: one or more processors; a storage means for storing one or more programs; the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a method as described in any of the implementations of the first aspect.
One of the above embodiments of the present disclosure has the following advantageous effects: the appearance damage in the vehicle photo can be detected, the consistency of vehicle information such as a vehicle number plate, a vehicle frame number and the like can be detected, and the consistency of the vehicle information input and the vehicle photo is checked. And auditing is carried out from multiple dimensions, and comprehensive inspection photo auditing service is provided. By using the damage detection model, key information and appearance damage in the vehicle photo can be rapidly and accurately identified, and auditing efficiency and accuracy are greatly improved. The auditing result is not influenced by personal subjective factors, and has higher objectivity and fairness. Misjudgment and dispute caused by human factors are reduced, and the auditing result is more reliable and credible. The whole auditing process can automatically control whether manual intervention is needed, so that the manpower resource and time cost are reduced, and auditing efficiency and consistency are improved. The damage detection model can be further trained and adjusted according to specific requirements so as to adapt to vehicle inspection standards and requirements of different areas, different vehicle types and different insurance companies, and has customization and expandability. The implementation mode has the advantages of multidimensional detection, high efficiency, accuracy, objectivity, fairness, automatic processing, customization, expandability and the like, can improve auditing efficiency and accuracy, reduces risk and management cost of insurance companies, and provides better insurance service experience for clients.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
FIG. 1 is a schematic illustration of one application scenario of a method of generating a vehicle damage report according to some embodiments of the present disclosure;
FIG. 2 is a flow chart of some embodiments of a method of generating a vehicle damage report according to the present disclosure;
FIG. 3 is a schematic structural view of some embodiments of a vehicle damage report generating device according to the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a schematic diagram of an application scenario of a method of generating a vehicle damage report according to some embodiments of the present disclosure.
As shown in fig. 1, the server 101 may obtain vehicle information 102 and a vehicle damage image set 103 of a damaged vehicle, then generate a vehicle damage appearance image 104 of the damaged vehicle according to the vehicle damage image set 103, then compare the vehicle information 102 and the vehicle damage appearance image 104 with input information of the damaged vehicle to obtain a comparison result 105, and input the vehicle damage appearance image 104 to a pre-trained damage detection model 106 in response to the comparison result 105 meeting a preset condition to obtain a damage evaluation report 107 of the damaged vehicle.
It is to be understood that the method for generating the vehicle damage report may be performed by a terminal device, or may be performed by the server 101, and the main body of the method may include a device formed by integrating the terminal device and the server 101 through a network, or may be performed by various software programs. The terminal device may be, among other things, various electronic devices with information processing capabilities including, but not limited to, smartphones, tablet computers, electronic book readers, laptop and desktop computers, and the like. The execution body may be embodied as a server 101, software, or the like. When the execution subject is software, the execution subject can be installed in the electronic device enumerated above. It may be implemented as a plurality of software or software modules, for example, for providing distributed services, or as a single software or software module. The present invention is not particularly limited herein.
It should be understood that the number of servers in fig. 1 is merely illustrative. There may be any number of servers, as desired for implementation.
With continued reference to fig. 2, a flow 200 of some embodiments of a method of generating a vehicle damage report according to the present disclosure is shown. The method for generating the vehicle damage report comprises the following steps:
in step 201, vehicle information and a vehicle damage image set of a damaged vehicle are acquired.
In some embodiments, the execution subject of the method for generating a vehicle damage report (for example, the server shown in fig. 1) may acquire the vehicle information and the vehicle damage image set of the damaged vehicle through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection may include, but is not limited to, 3G/4G connections, wiFi connections, bluetooth connections, wiMAX connections, zigbee connections, UWB (ultra wideband) connections, and other now known or later developed wireless connection means.
Specifically, the vehicle information generally includes information such as a vehicle number plate, a frame number, and a vehicle model number of the damaged vehicle. The aforementioned set of lesion images is typically referred to as an image of a lesion vehicle. Here, the vehicle damage image set may be composed of a damaged portion image and an undamaged portion image.
And 202, generating a vehicle damage appearance image of the damaged vehicle according to the vehicle damage image set.
In some embodiments, the executing body may generate the vehicle damage appearance image of the damaged vehicle according to the vehicle damage image set. Specifically, the vehicle damage appearance image generally refers to an image generated by stitching and combining images of different parts of the damaged vehicle in the vehicle damage image set.
It should be noted that, image noise reduction, image enhancement and image identification are generally performed on the collected vehicle damage image set before the vehicle damage appearance image is generated: the collected vehicle inspection photo is preprocessed in the modes of image denoising, image enhancement, image identification and the like, so that the accuracy and the reliability of subsequent processing are improved.
In some optional implementations of some embodiments, the executing body may perform region division on the vehicle loss image in the vehicle loss image set by using a semantic segmentation manner to obtain a region image set; determining the region relevance between the region boundaries in the region image set; carrying out feature extraction on the regional image set by adopting a scale invariant feature transformation algorithm of a custom scale space to obtain a local regional feature set; optimizing the feature direction definition of the local region features in the local region feature set and generating feature points to obtain a feature point set; and carrying out region association analysis on the region image set according to the region association and the characteristic point set, and splicing the region images in the region image set according to a region association analysis result to obtain the vehicle damage appearance image.
In some optional implementations of some embodiments, the executing body may introduce, for a feature direction of the local region feature, a feature direction of region weighted superposition in a scale space based on a main feature direction as an included angle feature direction, where the feature direction is determined by re-determining a gaussian difference in a region after weighting adjustment is performed on different regions in the scale space in the region image by using a scale space filter; determining a Hamiltonian distance according to the main characteristic direction and the included angle characteristic direction; and generating characteristic points according to the included angle characteristic direction, the main characteristic direction and the Ha Midu distance to obtain a characteristic point set.
Specifically, the executing body can determine the corresponding relation between the adjacent photos by matching the characteristic points of the adjacent photos, combine the obtained vehicle photos in a specific mode, and splice the photos at all angles together by using a splicing algorithm to form a complete vehicle appearance image.
As an example: the picture matching algorithm adopts an improved SIFT algorithm:
1. according to the special scene of vehicle appearance detection, the local feature detection scheme in SIFT is optimized, and the scale space for feature extraction is redefined (the scale space of standard SIFT is only the pixel distance of an image): based on the standard area division of the vehicle fittings, two concepts of a communication area of the vehicle fittings and a damaged area of the vehicle fittings are introduced, the weighted proportion of the scale space is 0.6:1:1.2, and the calculation of characteristic angular points is defined in a weighted mode.
Different scale spaces cannot detect extreme points using the same window. Small windows are used for small corner points and only large windows are used for large corner points. A scale-space filter is used for this purpose. The general SIFT algorithm (Scale-invariant feature transform, scale-invariant feature transform algorithm) uses global DOG (Differnent of Gaussian, gaussian difference). For example: the concept of zoning is introduced here, i.e. three zones are superimposed: and weighting the vehicle accessory standard area, the vehicle accessory communication area and the vehicle accessory damage area, wherein the weighting proportion is 0.6:1:1.2, and recalculating DOG in the area after weighting adjustment.
2. The characteristic direction definition of the local area is optimized, the characteristic direction of an included angle is introduced on the basis of the main direction, the direction of the standard algorithm is the main direction and forms an included angle of 90 degrees, the characteristic direction of the regional concept is introduced as the other axis direction except the main direction, and the characteristic direction is matched and adjusted to be Hamiltonian distance. The direction is defined by the characteristic direction of region weighted superposition in the scale space, the characteristic point generation is carried out on the basis, the Hamiltonian distance defined by the main direction and the included angle direction is adopted for measuring the distribution of the characteristic points, and the traditional Euler distance is not used.
Splicing algorithm: the logic used by the splicing algorithm is
1) Identifying standard area division of vehicle accessories on different photos, and performing segmeasurement;
2) And according to the logical relevance between the vehicle region division boundaries, carrying out relevance analysis on the vehicle appearance images according to the logical relevance and feature point matching SIFT processing.
And 203, comparing the vehicle information, the vehicle damage appearance image and the input information of the damaged vehicle to obtain a comparison result.
In some embodiments, the executing body may compare the vehicle information and the vehicle damage appearance image with the input information of the damaged vehicle to obtain a comparison result.
Here, the input information of the damaged vehicle generally refers to information that the damaged vehicle has left when it is applied, and specifically, the input information may be image information of the vehicle, or may be information such as a vehicle number plate, a frame number, and a vehicle model number of the vehicle.
Here, the comparison method generally refers to comparing the input information of the damaged vehicle with the acquired vehicle information and the set of damage images, and the comparison result often refers to whether the information is consistent.
As an example, the executing body may compare the vehicle data information collected by the vehicle information input: verifying the format of the number plate, the length of the frame number, the check position, the standardization of the vehicle model and the like; and matching the corresponding relation among the number plate, the frame number and the vehicle model, using a vehicle model and frame number VIN matching algorithm, and matching the number plate, the frame number and the vehicle model by using a new energy vehicle matching logic to ensure the consistency among the number plate, the frame number and the vehicle model. If the matching results are consistent, the information is considered to be accurate and consistent; if not, there may be information errors or tampering.
As yet another example, the above-described execution subject may compare whether the vehicle exterior photograph covers all the components: in order to ensure that the combination of the appearance photos of the vehicle is complete, each accessory area of the vehicle corresponding to the model in the database can be detected in the combination photo of the vehicle after image classification and target detection are used, namely; by identifying and locating individual components in the vehicle appearance (e.g., lights, wheels, windows, etc.) and comparing with the vehicle appearance information, it is confirmed whether the vehicle appearance covers all of the components.
And 204, inputting the vehicle damage appearance image to a pre-trained damage detection model to obtain a damage evaluation report of the damaged vehicle in response to the comparison result meeting a preset condition.
In some embodiments, in response to the comparison result meeting a preset condition, the execution subject may input the vehicle damage appearance image into a pre-trained damage detection model to obtain a damage evaluation report of the damaged vehicle.
Here, the above-mentioned preset condition generally means that the comparison results are consistent. The damage-assessment report may be a damage rating for the vehicle-damage-appearance image. The damage evaluation report may be an obtained damage evaluation report obtained by integrating vehicle information, a vehicle damage image set, a vehicle damage appearance image, input information, a comparison result and a damage rating and outputting the integrated damage evaluation report as structured data, and may include: overall conclusion; major problem points (if not meeting the vehicle inspection standard); detailed report-graphically, visually annotate the location and extent of injury, and provide a textual description and assessment report.
For the business meeting the vehicle inspection standard, auditors of the insurance company can accurately judge the problem points through the results and reports provided by the system, such as whether the vehicle photos provided by the clients are the photos of the vehicles recorded by the system and the appearance damage condition of the vehicles, so as to make corresponding insurance underwriting decisions.
Specifically, the damage detection model is generally used for representing the correspondence between the vehicle damage appearance image and the damage evaluation report.
In some optional implementations of some embodiments, the executing body may input the vehicle damage appearance image to a damage area detection model in the damage detection model, to obtain a damage area image; and inputting the damage region image into a damage degree detection model in a damage detection model to obtain a damage evaluation report of the damaged vehicle.
In some optional implementations of some embodiments, the damage area detection model is obtained by training an initial model with a yolov5m model structure and a BBox algorithm as the initial model, with a sample vehicle damage appearance image as an input, and with a sample damage area image as a desired output, where an output layer size in the initial model is 1200 x 1200.
In some optional implementations of some embodiments, the damage degree detection model is obtained by training a depth residual error network adopting a res-101 structure as an initial model, taking a sample damage region image as an input, and taking a sample damage evaluation report as a desired output.
Here, by adopting a deep-learning multi-target damage detection model (yolo+resnet two-step method), namely, firstly locking a target area from the whole image by using Yolo BBox, then extracting the target area of the image and then performing classification processing by using a corresponding Resnet model, wherein Yolo uses yolov5m structure for training, improving the size of Input to 1200 x 1200, resnet uses res-101 structure, the damage area in a vehicle photo can be automatically identified and marked, and the damage degree is evaluated by comparing the vehicle inspection standards of insurance companies, and corresponding damage grade and damage repair amount are estimated.
One of the above embodiments of the present disclosure has the following advantageous effects: the appearance damage in the vehicle photo can be detected, the consistency of vehicle information such as a vehicle number plate, a vehicle frame number and the like can be detected, and the consistency of the vehicle information input and the vehicle photo is checked. And auditing is carried out from multiple dimensions, and comprehensive inspection photo auditing service is provided. By using the damage detection model, key information and appearance damage in the vehicle photo can be rapidly and accurately identified, and auditing efficiency and accuracy are greatly improved. The auditing result is not influenced by personal subjective factors, and has higher objectivity and fairness. Misjudgment and dispute caused by human factors are reduced, and the auditing result is more reliable and credible. The whole auditing process can automatically control whether manual intervention is needed, so that the manpower resource and time cost are reduced, and auditing efficiency and consistency are improved. The damage detection model can be further trained and adjusted according to specific requirements so as to adapt to vehicle inspection standards and requirements of different areas, different vehicle types and different insurance companies, and has customization and expandability. The implementation mode has the advantages of multidimensional detection, high efficiency, accuracy, objectivity, fairness, automatic processing, customization, expandability and the like, can improve auditing efficiency and accuracy, reduces risk and management cost of insurance companies, and provides better insurance service experience for clients.
With further reference to fig. 3, as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of a vehicle damage report generating apparatus, which correspond to those method embodiments shown in fig. 2, and which are particularly applicable to various electronic devices.
As shown in fig. 3, the vehicle damage report generating apparatus 300 of some embodiments includes: an acquisition unit 301, a first generation unit 302, an alignment unit 303, and a second generation unit 304. Wherein the acquiring unit 301 is configured to acquire vehicle information and a vehicle damage image set of a damaged vehicle; a first generation unit 302 configured to generate a vehicle loss appearance image of the damaged vehicle from the vehicle loss image set; a comparison unit 303 configured to obtain a comparison result by comparing the vehicle information and the vehicle damage appearance image with the input information of the damaged vehicle; and the second generating unit 304 is configured to input the vehicle damage appearance image to a pre-trained damage detection model to obtain a damage evaluation report of the damaged vehicle in response to the comparison result meeting a preset condition.
It will be appreciated that the elements described in the apparatus 300 correspond to the various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting benefits described above with respect to the method are equally applicable to the apparatus 300 and the units contained therein, and are not described in detail herein.
One of the above embodiments of the present disclosure has the following advantageous effects: the appearance damage in the vehicle photo can be detected, the consistency of vehicle information such as a vehicle number plate, a vehicle frame number and the like can be detected, and the consistency of the vehicle information input and the vehicle photo is checked. And auditing is carried out from multiple dimensions, and comprehensive inspection photo auditing service is provided. By using the damage detection model, key information and appearance damage in the vehicle photo can be rapidly and accurately identified, and auditing efficiency and accuracy are greatly improved. The auditing result is not influenced by personal subjective factors, and has higher objectivity and fairness. Misjudgment and dispute caused by human factors are reduced, and the auditing result is more reliable and credible. The whole auditing process can automatically control whether manual intervention is needed, so that the manpower resource and time cost are reduced, and auditing efficiency and consistency are improved. The damage detection model can be further trained and adjusted according to specific requirements so as to adapt to vehicle inspection standards and requirements of different areas, different vehicle types and different insurance companies, and has customization and expandability. The implementation mode has the advantages of multidimensional detection, high efficiency, accuracy, objectivity, fairness, automatic processing, customization, expandability and the like, can improve auditing efficiency and accuracy, reduces risk and management cost of insurance companies, and provides better insurance service experience for clients.
Referring now to fig. 4, a schematic diagram of an electronic device (e.g., server in fig. 1) 400 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 4 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.
As shown in fig. 4, the electronic device 400 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 401, which may perform various suitable actions and processes according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage means 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the electronic device 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
In general, the following devices may be connected to the I/O interface 405: input devices 406 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 407 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 408 including, for example, magnetic tape, hard disk, etc.; and a communication device 409. The communication means 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 shows an electronic device 400 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 4 may represent one device or a plurality of devices as needed.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 409, or from storage 408, or from ROM 402. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing device 401.
It should be noted that, in some embodiments of the present disclosure, the computer readable medium may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring vehicle information and a vehicle damage image set of a damaged vehicle; generating a vehicle damage appearance image of the damaged vehicle according to the vehicle damage image set; comparing the vehicle information with the vehicle damage appearance image with the input information of the damaged vehicle to obtain a comparison result; and responding to the comparison result to meet a preset condition, inputting the vehicle damage appearance image into a pre-trained damage detection model, and obtaining a damage evaluation report of the damaged vehicle.
Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor includes an acquisition unit, a first generation unit, an alignment unit, and a second generation unit. The names of these units do not constitute limitations on the unit itself in some cases, and the acquisition unit may also be described as "a unit that acquires vehicle information and a set of vehicle damage images of a damaged vehicle", for example.
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.
The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.
Claims (10)
1. A method of generating a vehicle damage report, comprising:
acquiring vehicle information and a vehicle damage image set of a damaged vehicle;
generating a vehicle damage appearance image of the damaged vehicle according to the vehicle damage image set;
comparing the vehicle information with the vehicle damage appearance image with the input information of the damaged vehicle to obtain a comparison result;
and responding to the comparison result to meet a preset condition, inputting the vehicle damage appearance image into a pre-trained damage detection model, and obtaining a damage evaluation report of the damaged vehicle.
2. The method of claim 1, wherein the generating a vehicle impairment appearance image of the impaired vehicle from the set of vehicle impairment images comprises:
performing region division on the vehicle loss images in the vehicle loss image set in a semantic segmentation mode to obtain a region image set;
determining the region relevance between the region boundaries in the region image set;
carrying out feature extraction on the regional image set by adopting a scale invariant feature transformation algorithm of a custom scale space to obtain a local regional feature set;
optimizing the feature direction definition of the local region features in the local region feature set and generating feature points to obtain a feature point set;
and carrying out region association analysis on the region image set according to the region association and the feature point set, and splicing the region images in the region image set according to a region association analysis result to obtain the vehicle damage appearance image.
3. The method according to claim 2, wherein optimizing the feature direction definition of the local region features in the local region feature set and generating feature points to obtain a feature point set includes:
introducing a characteristic direction of region weighted superposition in a scale space as an included angle characteristic direction based on a main characteristic direction for the characteristic direction of the local region, wherein the characteristic direction is determined by re-determining Gaussian difference in a region after weighting adjustment is carried out on different regions in the scale space in a region image by adopting a scale space filter;
determining a Hamiltonian distance according to the main characteristic direction and the included angle characteristic direction;
and generating characteristic points according to the included angle characteristic direction, the main characteristic direction and the Hamiltonian distance to obtain a characteristic point set.
4. The method of claim 1, wherein the inputting the vehicle damage appearance image into a pre-trained damage detection model in response to the comparison result meeting a preset condition, to obtain a damage assessment report of the damaged vehicle, comprises:
inputting the vehicle damage appearance image into a damage area detection model in a damage detection model to obtain a damage area image;
and inputting the damage region image into a damage degree detection model in a damage detection model to obtain a damage evaluation report of the damaged vehicle.
5. The method of claim 4, wherein the damage region detection model is obtained by training an initial model by using a yolov5m model structure and combining a BBox algorithm as the initial model, using a sample vehicle damage appearance image as an input and using a sample damage region image as a desired output, wherein the output layer size in the initial model is 1200 x 1200.
6. The method of claim 4, wherein the damage degree detection model is obtained by training a depth residual error network with res-101 structure as an initial model, taking a sample damage region image as an input, and taking a sample damage evaluation report as a desired output.
7. An apparatus for generation of a vehicle injury report, comprising:
an acquisition unit configured to acquire vehicle information and a vehicle loss image set of a damaged vehicle;
a first generation unit configured to generate a vehicle loss appearance image of the damaged vehicle from the vehicle loss image set;
the comparison unit is configured to compare the vehicle information, the vehicle damage appearance image and the input information of the damaged vehicle to obtain a comparison result;
the second generation unit is configured to respond to the comparison result to meet a preset condition, input the vehicle damage appearance image into a pre-trained damage detection model and obtain a damage evaluation report of the damaged vehicle.
8. The apparatus of claim 7, wherein the first generation unit is further configured to:
performing region division on the vehicle loss images in the vehicle loss image set in a semantic segmentation mode to obtain a region image set;
determining the region relevance between the region boundaries in the region image set;
carrying out feature extraction on the regional image set by adopting a scale invariant feature transformation algorithm of a custom scale space to obtain a local regional feature set;
optimizing the feature direction definition of the local region features in the local region feature set and generating feature points to obtain a feature point set;
and carrying out region association analysis on the region image set according to the region association and the feature point set, and splicing the region images in the region image set according to a region association analysis result to obtain the vehicle damage appearance image.
9. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-6.
10. A computer readable medium having stored thereon a computer program, wherein the program when executed by a processor implements the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311538252.5A CN117557221A (en) | 2023-11-17 | 2023-11-17 | Method, device, equipment and readable medium for generating vehicle damage report |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311538252.5A CN117557221A (en) | 2023-11-17 | 2023-11-17 | Method, device, equipment and readable medium for generating vehicle damage report |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117557221A true CN117557221A (en) | 2024-02-13 |
Family
ID=89812293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311538252.5A Pending CN117557221A (en) | 2023-11-17 | 2023-11-17 | Method, device, equipment and readable medium for generating vehicle damage report |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117557221A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325531A (en) * | 2018-09-17 | 2019-02-12 | 平安科技（深圳）有限公司 | Car damage identification method, device, equipment and storage medium based on image |
| CN109410218A (en) * | 2018-10-08 | 2019-03-01 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating vehicle damage information |
| CN110276258A (en) * | 2019-05-21 | 2019-09-24 | 智慧互通科技有限公司 | A kind of method and system identifying vehicle appearance |
| CN110647853A (en) * | 2019-09-27 | 2020-01-03 | 支付宝(杭州)信息技术有限公司 | Computer-implemented vehicle damage assessment method and device |
| CN112330685A (en) * | 2020-12-28 | 2021-02-05 | 北京达佳互联信息技术有限公司 | Image segmentation model training method, image segmentation device and electronic equipment |
| CN114565763A (en) * | 2022-02-28 | 2022-05-31 | 北京百度网讯科技有限公司 | Image segmentation method, apparatus, device, medium, and program product |
| CN115131564A (en) * | 2022-07-13 | 2022-09-30 | 平安科技（深圳）有限公司 | Vehicle component damage detection method based on artificial intelligence and related equipment |
| CN116128484A (en) * | 2023-03-08 | 2023-05-16 | 邦邦汽车销售服务(北京)有限公司 | Method and system for determining remaining maintenance time of automobile based on neural network |
-
2023
- 2023-11-17 CN CN202311538252.5A patent/CN117557221A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325531A (en) * | 2018-09-17 | 2019-02-12 | 平安科技（深圳）有限公司 | Car damage identification method, device, equipment and storage medium based on image |
| CN109410218A (en) * | 2018-10-08 | 2019-03-01 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating vehicle damage information |
| CN110276258A (en) * | 2019-05-21 | 2019-09-24 | 智慧互通科技有限公司 | A kind of method and system identifying vehicle appearance |
| CN110647853A (en) * | 2019-09-27 | 2020-01-03 | 支付宝(杭州)信息技术有限公司 | Computer-implemented vehicle damage assessment method and device |
| CN112330685A (en) * | 2020-12-28 | 2021-02-05 | 北京达佳互联信息技术有限公司 | Image segmentation model training method, image segmentation device and electronic equipment |
| CN114565763A (en) * | 2022-02-28 | 2022-05-31 | 北京百度网讯科技有限公司 | Image segmentation method, apparatus, device, medium, and program product |
| CN115131564A (en) * | 2022-07-13 | 2022-09-30 | 平安科技（深圳）有限公司 | Vehicle component damage detection method based on artificial intelligence and related equipment |
| CN116128484A (en) * | 2023-03-08 | 2023-05-16 | 邦邦汽车销售服务(北京)有限公司 | Method and system for determining remaining maintenance time of automobile based on neural network |
Non-Patent Citations (2)
| Title |
|---|
| 吴良斌: "《SAR图像处理与目标识别》", 31 January 2013, 航空工业出版社, pages: 82 - 85 * |
| 王峰;尤红建;傅兴玉;许宁;: "应用于多源SAR图像匹配的级联SIFT算法", 电子学报, no. 03, 15 March 2016 (2016-03-15), pages 548 - 554 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3520045B1 (en) | Image-based vehicle loss assessment method, apparatus, and system, and electronic device | |
| US11244435B2 (en) | Method and apparatus for generating vehicle damage information | |
| CN108427939B (en) | Model generation method and device | |
| US11392792B2 (en) | Method and apparatus for generating vehicle damage information | |
| US20180293664A1 (en) | Image-based vehicle damage determining method and apparatus, and electronic device | |
| CN112085952A (en) | Vehicle data monitoring method and device, computer equipment and storage medium | |
| US20230289887A1 (en) | Optical Fraud Detector for Automated Detection Of Fraud In Digital Imaginary-Based Automobile Claims, Automated Damage Recognition, and Method Thereof | |
| CN110941978B (en) | Face clustering method and device for unidentified personnel and storage medium | |
| CN111415336B (en) | Image tampering identification method, device, server and storage medium | |
| CN109977832B (en) | Image processing method, device and storage medium | |
| CN112270309A (en) | Vehicle access point equipment snapshot quality evaluation method and device and readable medium | |
| CN109389169A (en) | Method and apparatus for handling image | |
| CN112465783B (en) | Image tampering detection method and device | |
| CN114663871A (en) | Image recognition method, training method, device, system and storage medium | |
| CN111932363A (en) | Identification and verification method, device, equipment and system for authorization book | |
| CN116932919B (en) | Information pushing method, device, electronic equipment and computer readable medium | |
| CN108470179B (en) | Method and apparatus for detecting an object | |
| CN113255516A (en) | Living body detection method and device and electronic equipment | |
| CN111340015A (en) | Positioning method and device | |
| CN113158773B (en) | Training method and training device for living body detection model | |
| CN113221762B (en) | Cost balance decision method, insurance claim decision method, apparatus and equipment | |
| CN114332993A (en) | Face recognition method and device, electronic equipment and computer readable storage medium | |
| CN112287905A (en) | Vehicle damage identification method, device, equipment and storage medium | |
| CN112287923A (en) | Card information identification method, device, equipment and storage medium | |
| CN117557221A (en) | Method, device, equipment and readable medium for generating vehicle damage report |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |