CN112085721A - Damage assessment method, device and equipment for flooded vehicle based on artificial intelligence and storage medium - Google Patents
Damage assessment method, device and equipment for flooded vehicle based on artificial intelligence and storage medium Download PDFInfo
- Publication number
- CN112085721A CN112085721A CN202010930254.9A CN202010930254A CN112085721A CN 112085721 A CN112085721 A CN 112085721A CN 202010930254 A CN202010930254 A CN 202010930254A CN 112085721 A CN112085721 A CN 112085721A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle
- flooded
- flooded vehicle
- flooding
- 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
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 57
- 230000009466 transformation Effects 0.000 claims abstract description 25
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 43
- 238000005070 sampling Methods 0.000 claims description 22
- 230000000694 effects Effects 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000009499 grossing Methods 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 5
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000007726 management method Methods 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000006424 Flood reaction Methods 0.000 abstract 2
- 238000010606 normalization Methods 0.000 description 18
- 230000008569 process Effects 0.000 description 12
- 239000003086 colorant Substances 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 230000010365 information processing Effects 0.000 description 3
- 238000012417 linear regression Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- SAZUGELZHZOXHB-UHFFFAOYSA-N acecarbromal Chemical compound CCC(Br)(CC)C(=O)NC(=O)NC(C)=O SAZUGELZHZOXHB-UHFFFAOYSA-N 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the technical field of artificial intelligence, and discloses a flooded vehicle damage assessment method, a flooded vehicle damage assessment device, equipment and a storage medium based on artificial intelligence, wherein the method comprises the steps of receiving a claim settlement instruction which is sent by a user side and contains a unique identification of a flooded vehicle, obtaining feature data of the flooded vehicle and an image of the flooded vehicle from uploaded data of the user side, and obtaining a sharpened image through perspective transformation and sharpening; carrying out graying processing on the sharpened image to obtain a grayscale image, carrying out binarization processing on the grayscale image to identify an identification area of the grayscale image, and obtaining a target image; and then inputting the target image into the trained recognition model to obtain the flooding grade of the flooded vehicle, performing data association on the flooding grade and the characteristic data, recognizing the part of the flooded vehicle which needs damage assessment, and determining the damage condition of the flooded vehicle. The application also relates to blockchain techniques, the characteristic data being stored in blockchains. This application is through the accurate analysis to the car image that floods to improve the car that floods and decide to decrease the accuracy.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a damage assessment method, device, equipment and storage medium for a flooded vehicle based on artificial intelligence.
Background
With the rapid development of automobile industry and the improvement of living standard of people in China, the automobile ownership of resident families is rapidly increased. However, in the period of abundant rain water in summer, automobiles are flooded by water due to urban waterlogging or flooding in the whole country, and the automobile insurance claim settlement pressure is doubled in a short time, wherein the requirements on the time efficiency of a damage-determining link of the flooded automobiles and the pricing accuracy of a loss item list are high, and the claim settlement is reasonable.
The existing damage assessment method for the flooded car is characterized in that images of the flooded car are shot, image comparison is simply carried out to judge the damage condition of the flooded car, and then claim settlement is carried out on a client by claim settlement personnel according to the damage condition; however, for the flooded vehicle, the damage assessment of the flooded vehicle involves a plurality of parts of different vehicle types, the values of the different parts are different from the evaluation standard, the images are not further analyzed only by means of simple image comparison, and the damage condition of the vehicle is difficult to accurately obtain. Therefore, the damage assessment method for the flooded vehicle cannot accurately assess the damage condition of the flooded vehicle, and the damage assessment accuracy of the flooded vehicle is low. There is a need for a method for improving damage assessment accuracy of a submerged vehicle.
Disclosure of Invention
The embodiment of the application aims to provide a damage assessment method for a flooded vehicle based on artificial intelligence, and the damage assessment accuracy of the flooded vehicle is improved through accurate analysis of images of the flooded vehicle.
In order to solve the technical problem, an embodiment of the present application provides a damage assessment method for a submerged vehicle based on artificial intelligence, including:
receiving a claim settlement instruction which is sent by a user side and contains a unique identification of a flooded vehicle, and acquiring feature data and an image of the flooded vehicle from uploaded data of the user side according to the unique identification, wherein the feature data comprises a vehicle type of the flooded vehicle and component parameters of the flooded vehicle;
correcting the flooded vehicle image in a perspective transformation mode to obtain a basic image, and sharpening the basic image to obtain a sharpened image;
carrying out graying processing on the sharpened image to obtain a grayscale image, carrying out binarization processing on the grayscale image, identifying an identification area of the grayscale image, and obtaining a target image, wherein the identification area comprises a flooded vehicle contour and a water level line;
inputting the target image into a trained recognition model to obtain the flooding grade of the flooding vehicle;
and performing data association on the flooding grade and the characteristic data, identifying a part of the flooding vehicle which needs damage assessment, and determining the damage condition of the flooding vehicle according to the part which needs damage assessment.
Further, the correcting the image of the flooded vehicle by means of perspective transformation to obtain a basic image, and sharpening the basic image to obtain a sharpened image includes:
projecting the flooded vehicle image to a new viewing plane;
calculating the angle of the edge of the flooded car image deviating from the new view plane through a preset algorithm, and correcting the flooded car image through the angle to obtain the basic image;
and carrying out sharpening processing on the basic image to eliminate background lines of the basic image so as to obtain the sharpened image.
Further, the performing graying processing on the sharpened image to obtain a grayscale image, performing binarization processing on the grayscale image to identify an identification area of the grayscale image, and obtaining a target image includes:
carrying out graying processing on the sharpened image by adopting a component method to obtain a grayscale image;
performing gray value sampling based on the gray image to obtain a gray sampling value;
comparing the gray sampling value with a pre-selected threshold value, and taking the pixel with the gray sampling value larger than the pre-selected threshold value as an identification feature;
and combining all the identification features to obtain the identification area, and taking the identification area as the target image.
Further, the step of combining all the identification features to obtain the identification region, and taking the identification region as the target image further includes:
and enhancing the effect of flooding the car outline and the water line in the gray-scale image by an image enhancement technology.
Further, the correcting the image of the flooded vehicle by means of perspective transformation to obtain a basic image, and sharpening the basic image to obtain a sharpened image further includes:
and eliminating random noise of the image of the flooded vehicle by adopting a median smoothing mode.
Further, the performing data association between the flooding grade and the feature data, identifying a component of the flooded vehicle that needs damage assessment, and determining a damage condition of the flooded vehicle according to the component that needs damage assessment includes:
identifying the vehicle type of the flooded vehicle, performing data association on the vehicle type and the flooding grade, and acquiring historical part claim data of the vehicle type;
counting the parts needing damage assessment of the flooded vehicle according to the flooding grade and the historical part claim settlement data;
and determining the damage condition of the flooded vehicle according to the parts needing damage assessment.
Further, the receiving a claim settlement instruction which is sent by the user side and contains the unique identification of the flooded vehicle, and acquiring the feature data and the image of the flooded vehicle according to the unique identification further comprises:
identifying a license plate part and a VIN code part from the flooded vehicle image, identifying a license plate number from the license plate part, and identifying a VIN code from the VIN code part;
and judging whether the flooded vehicle is a guaranteed vehicle or not through the license plate number or the VIN code.
In order to solve the technical problem, the embodiment of the application provides a water logging car loss assessment device based on artificial intelligence, includes:
the system comprises a claim settlement instruction receiving module, a user side and a user terminal, wherein the claim settlement instruction receiving module is used for receiving a claim settlement instruction which is sent by the user side and contains a unique identification of a flooded vehicle, and acquiring feature data and a flooded vehicle image of the flooded vehicle from uploaded data of the user side according to the unique identification, wherein the feature data comprises a vehicle type of the flooded vehicle and component parameters of the flooded vehicle;
the sharpening image acquisition module is used for correcting the flooded vehicle image in a perspective transformation mode to obtain a basic image, and sharpening the basic image to obtain a sharpened image;
the target image determining module is used for carrying out graying processing on the sharpened image to obtain a grayscale image, carrying out binarization processing on the grayscale image to identify an identification area of the grayscale image to obtain a target image, wherein the identification area comprises a flooded vehicle outline and a water level line;
the flooding grade acquisition unit is used for inputting the target image into a trained recognition model to obtain a flooding grade of the flooding vehicle;
and the damaged condition determining module is used for performing data association on the flooding grade and the characteristic data, identifying a part of the flooded vehicle which needs damage assessment, and determining the damaged condition of the flooded vehicle according to the part of the flooded vehicle which needs damage assessment.
In order to solve the technical problems, the invention adopts a technical scheme that: a computer device is provided that includes, one or more processors; a memory for storing one or more programs for causing the one or more processors to implement any of the artificial intelligence based water flooded vehicle damage scenarios described above.
In order to solve the technical problems, the invention adopts a technical scheme that: a computer readable storage medium having a computer program stored thereon, which when executed by a processor implements an artificial intelligence based flooded vehicle damage assessment scheme as described in any one of the above.
In the scheme, the damage assessment method for the flooded car based on artificial intelligence is characterized in that characteristic data of the flooded car and a flooded car image are obtained, the flooded car image is corrected in a perspective transformation mode to obtain a basic image, the basic image is sharpened to obtain a sharpened image, the sharpened image is grayed to obtain a gray image, the gray image is subjected to binarization processing to identify an identification area of the gray image to obtain a target image, the flooded car image is accurately analyzed, the identification area is accurately identified, and a foundation is provided for subsequent damage assessment of the flooded car; and inputting the target image into the trained recognition model to obtain the flooding grade of the flooded vehicle, performing data association between the flooding grade and the characteristic data to recognize the part of the flooded vehicle which needs damage assessment, determining the damage condition of the flooded vehicle according to the part which needs damage assessment, realizing accurate analysis of the image of the flooded vehicle, determining the damage condition of the part of the flooded vehicle by combining the part information of the flooded vehicle, and being beneficial to improving the precision of damage assessment of the flooded vehicle.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is a schematic diagram of an application environment of a damage assessment method for a flooded vehicle based on artificial intelligence provided by an embodiment of the present application;
FIG. 2 is a flow chart of an implementation of a flooded vehicle damage assessment method based on artificial intelligence according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating an implementation of step S3 in the damage assessment method for a flooded vehicle based on artificial intelligence according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a damage assessment device of a flooded vehicle based on artificial intelligence provided in an embodiment of the present application;
fig. 5 is a schematic diagram of a computer device provided in an embodiment of the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
Referring to fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as a web browser application, a search-type application, an instant messaging tool, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that the damage assessment method for the flooded vehicle based on the artificial intelligence provided by the embodiment of the present application is generally executed by a server, and accordingly, a damage assessment device for the flooded vehicle based on the artificial intelligence is generally disposed in the server.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring to fig. 2, fig. 2 shows an embodiment of a damage assessment method for a flooded vehicle based on artificial intelligence.
It should be noted that, if the result is substantially the same, the method of the present invention is not limited to the flow sequence shown in fig. 2, and the method includes the following steps:
s1: and receiving a claim settlement instruction which is sent by the user side and contains the unique identification of the flooded vehicle, and acquiring feature data and an image of the flooded vehicle from uploaded data of the user side according to the unique identification.
Specifically, after the owner confirms that the vehicle is flooded, the vehicle is damaged, and when the owner needs to determine the damage of the vehicle, the owner can shoot the flooded vehicle on site in a specified mode, and upload the shot image of the flooded vehicle to the server. In the process of uploading the image of the flooded vehicle, the user side sends a claim settlement instruction containing the unique identification of the flooded vehicle to the server. The server receives a claim settlement instruction which is sent by the user side and contains the unique identification of the flooded car, analyzes the claim settlement instruction, and uploads data from the user side to obtain characteristic data and images of the flooded car.
The water flooding vehicle is a vehicle flooded by water. The invention relates to a damage assessment method for a flooded vehicle, which is used for assessing the damage of the flooded vehicle according to the damage condition of parts of the flooded vehicle.
Specifically, since the component configurations of the vehicles are different from vehicle type to vehicle type, the vehicle type and the component parameters of the submerged vehicle need to be determined. The service end receives a claim settlement instruction which is sent by the user end and contains the unique identification of the flooded vehicle, and obtains the characteristic data and the image of the flooded vehicle according to the unique identification, wherein the characteristic data comprises the vehicle type of the flooded vehicle and the component parameters of the flooded vehicle. The flooded vehicle image comprises a flooded vehicle panoramic image, a vehicle partial image and the like.
Further, step S1 further includes: detecting the image of the flooded vehicle, and detecting whether the image of the flooded vehicle is qualified, wherein the detected content comprises one or more of the following combinations: the image definition of the flooded vehicle, the shooting angle, the recognizable degree of the shot part and whether the image of the flooded vehicle is suspected to be tampered; and if the detected flooded vehicle image is unqualified, acquiring the flooded vehicle image again.
Specifically, the image of the flooded vehicle is detected, whether the image of the flooded vehicle is qualified or not is judged, and when the image of the flooded vehicle is unqualified, a user is prompted to upload the image of the flooded vehicle again. The acquired image content of the submerged vehicle comprises image definition, a shooting angle, recognizable degree of a shooting part, whether the image is suspected to be tampered and the like, for example, whether the image definition is in a configured definition range, whether the shooting angle is in a configured angle range, whether the recognizable degree of the shooting part is in a configured recognizable degree range and the like. And if the acquired vehicle image is qualified, executing the next step. Therefore, the influence of unqualified water flooding car images on subsequent damage assessment results can be avoided, and the accuracy of vehicle damage assessment is improved.
S2: and correcting the image of the flooded vehicle in a perspective transformation mode to obtain a basic image, and sharpening the basic image to obtain a sharpened image.
Specifically, since the submerged vehicle image may have different degrees of tilt, which affects the model identification result, the content image needs to be subjected to perspective transformation (correction), that is, the content image needs to be projected to a new viewing plane, so as to obtain a corrected image.
In this embodiment, the processing method of the perspective transformation includes, but is not limited to, performing the perspective transformation processing by using a perspectrive () function in OpenCv. OpenCV is a cross-platform computer vision library containing a large number of open source APIs (interfaces), and provides interfaces of languages such as Python, Ruby, MATLAB and the like, so that a lot of general algorithms in the aspects of image processing and computer vision are realized.
Furthermore, in order to make the edge, the contour line and the details of the image of the flooded vehicle clear, the image of the flooded vehicle after perspective needs to be sharpened to obtain a sharpened image so as to remove background lines and improve the identification accuracy.
In this embodiment, the sharpening method includes, but is not limited to, using any one of laplacian, sobel (weighted average difference) and Prewitt (average difference) operators commonly used in the prior art, taking the sobel operator method as an example, the following formula may be used to transform the corresponding pixel matrix M (i, j).
A＝|(M(i-1，j-1)+2M(i-1,j)+M(i-1,j+1))-(M(i+1,j-1)+2M(i+1,j)+M(i+1,j+1))|
B＝|(M(i-1，j-1)+2M(i,j-1)+M(i+1,j-1))-(M(i-1,j+1)+2M(i,j+1)+M(i+1,j+1))
S(i,j)＝A+B
Where M (i, j) represents a pixel matrix corresponding to the image after perspective. S (i, j) represents a pixel matrix corresponding to the image after perspective, a represents a weighting factor in the horizontal direction, and B represents a weighting factor in the vertical direction.
S3: and carrying out graying processing on the sharpened image to obtain a grayscale image, and carrying out binarization processing on the grayscale image to identify an identification area of the grayscale image to obtain a target image.
Specifically, since the content image may include a plurality of colors, the colors themselves are very susceptible to the influence of factors such as illumination, and the colors of the objects of the same type change very much, the colors themselves are difficult to provide key information, and thus, it is necessary to perform a graying process on the content image to obtain a grayscale map, so as to eliminate interference and reduce the complexity of the image and the information processing amount.
The grayscale processing is a process of converting a color image into a grayscale image, and aims to improve image quality and make the display effect of the image clearer. Grayscale processing includes, but is not limited to: component, maximum, average, weighted average, and the like.
Specifically, the binarization processing is to set the gray value of a pixel point on the image to be 0 or 255, that is, to present an obvious black-and-white effect to the whole image, and the binarization of the image greatly reduces the data volume in the image, so that the outline and the water level line of the flooded vehicle can be highlighted. In order to further remove the interference of the image background, binarization processing needs to be performed on the gray-scale image, an identification area is identified, and a target image is obtained.
After the server side obtains the gray level image, the sampled pixel value based on the gray level image is compared with a pre-selected threshold value, the pixel value of which the sampled pixel value is larger than or equal to the threshold value is set to be 255, and the pixel value of which the sampled pixel value is smaller than the threshold value is set to be 0. The sampled pixel value is the pixel value corresponding to each pixel point in the grayscale image. The size of the threshold value can influence the effect of the binarization processing of the gray level image, and when the threshold value is properly selected, the effect of the binarization processing of the gray level image is better; when the threshold value is selected improperly, the effect of the binarization processing of the gray level image is affected. For convenience of operation and simplification of the calculation process, the threshold value in the present embodiment is determined empirically by a developer.
The identification area is the outline of the flooded vehicle and the flooded water line.
S4: and inputting the target image into the trained recognition model to obtain the flooding grade of the flooding vehicle.
Specifically, the target image is input into the generative countermeasure network, and the model is divided according to the preset flooding grade to obtain the flooding grade of the flooding vehicle.
In one embodiment, the preset flooding level classification model is divided into seven levels: first-level, second-level low, second-level high, third-level low, third-level high, fourth-level and fifth-level. The preset flooding grade division model is that the grade of the flooding vehicle is the grade according to the vehicle type working dimension (different vehicle types and different replacement part working hours). This is due to the height of the flooding, which can cause different damage to parts of different vehicle types.
Among them, the Generative Adaptive Networks (GAN) is a deep learning model, and is one of the most promising methods for unsupervised learning in complex distribution in recent years. The model passes through (at least) two modules in the framework: the mutual game learning of the Generative Model (Generative Model) and the Discriminative Model (Discriminative Model) yields a reasonably good output. The discriminant model requires input variables that are predicted by some model. Generative models are the random generation of observed data given some kind of implicit information. In the embodiment, the flooding grade of the flooded vehicle is obtained by inputting the target image into the generative confrontation network, by mutually gaming the generative model and the discriminant model, and dividing the models according to the preset flooding grade.
S5: and performing data association on the flooding grade and the characteristic data, identifying the parts of the flooding vehicle which need damage assessment, and determining the damage condition of the flooding vehicle according to the parts which need damage assessment.
Specifically, due to different flooding levels, damage assessment parts required by the flooding vehicle are different, so that data association needs to be performed according to different flooding vehicle types and flooding levels, and further, the damage assessment parts are counted. After acquiring the information of all the parts of the flooded vehicle which need to be damaged, acquiring the damage condition of the parts in the past, and finally confirming the damage condition of the flooded vehicle.
For example, if the flooding level is three-level low, the vehicle model is a haver H6 vehicle model, and in the preset flooding level classification model, the flooding level with three-level low, and the parts of the haver H6 which need damage determination may be the engine, the seat, the chassis, the battery and the like of the haver H6 vehicle model. And the damage assessment statistics of the parts of different vehicle types is realized according to the flooding grade by performing data association on the flooding grade and the characteristic data.
In the embodiment, the characteristic data of the flooded car and the flooded car image are obtained, the flooded car image is corrected in a perspective transformation mode to obtain a basic image, the basic image is sharpened to obtain a sharpened image, the sharpened image is subjected to gray processing to obtain a gray image, the gray image is subjected to binarization processing to identify an identification area of the gray image to obtain a target image, the flooded car image is accurately analyzed, the identification area is accurately identified, and a foundation is provided for subsequent flooded car damage assessment; and inputting the target image into the trained recognition model to obtain the flooding grade of the flooded vehicle, performing data association between the flooding grade and the characteristic data to recognize the part of the flooded vehicle which needs damage assessment, determining the damage condition of the flooded vehicle according to the part which needs damage assessment, realizing accurate analysis of the image of the flooded vehicle, determining the damage condition of the part of the flooded vehicle by combining the part information of the flooded vehicle, and being beneficial to improving the precision of damage assessment of the flooded vehicle.
Further, step S2 includes:
and projecting the image of the flooded car to a new view plane.
Specifically, in the process of carrying out perspective transformation on the image of the flooded vehicle, the image of the flooded vehicle needs to be projected to a new view plane, so that the deviation angle of the image of the flooded vehicle can be conveniently calculated subsequently, and the image can be corrected.
And calculating the angle of the edge of the image of the flooded vehicle deviating from the new view plane through a preset algorithm, and correcting the image of the flooded vehicle through the angle to obtain a basic image.
The preset algorithm includes, but is not limited to: linear regression algorithms, Hough algorithms and Rando transformation algorithms. In the present embodiment, a linear regression algorithm is preferable. The linear regression algorithm can detect a series of boundary points of the upper edge of the flooded car image, and then the boundary straight line of the edge is fitted through the least square method, so that the inclination angle of the image is determined, and the inclination angle is the angle of the edge of the flooded car image deviating from a new view plane.
And carrying out sharpening processing on the basic image to eliminate background lines of the basic image so as to obtain a sharpened image.
Specifically, in order to make the edge, the contour line and the details of the image of the flooded vehicle clear, the image of the flooded vehicle after perspective transformation needs to be sharpened to obtain a sharpened image, so as to remove background lines and improve the identification accuracy.
In the embodiment, the image of the flooded vehicle is projected to a new view plane, the image of the flooded vehicle is corrected and sharpened, the image of the flooded vehicle is further processed, image interference items are eliminated, the image processing precision of the flooded vehicle is improved, and the damage determination precision of the flooded vehicle is further provided.
Referring to fig. 3, fig. 3 shows an embodiment of step S3, where in step S3, the sharpened image is grayed to obtain a grayscale image, and the grayscale image is binarized to identify an identification area of the grayscale image to obtain a target image, and details are as follows:
s31: and carrying out graying processing on the sharpened image by adopting a component method to obtain a grayscale image.
Specifically, in order to reduce the influence of color on extraction of critical information of an image, a component method is selected, and a gray image is obtained by performing gray processing on a sharpened image. This can eliminate interference and reduce the complexity of the image and the amount of information processing.
The component method is mainly characterized in that any one of three channels of a color image is taken as a gray value of a gray image, and one channel is selected according to practical application. Wherein, the color image three-channel refers to the separate red, green and blue parts. That is, a complete image is composed of three channels, red, green, and blue. These three channels work together to produce a complete image.
S32: and carrying out gray value sampling based on the gray image to obtain a sampling value.
Specifically, due to the fact that the gray values on the gray map are different, the gray value sampling needs to be carried out on the gray map, and the outline and the water level line of the flooded vehicle can be conveniently identified in the follow-up process.
Specifically, because the damaged parts of the submerged vehicle need to be counted, and all the parts of each fixed vehicle type are relatively fixed, the damaged parts can be counted as long as the parameter information of the parts of the submerged vehicle and the water level line of the submerged vehicle are obtained. Therefore, the outline and the water level line of the flooded vehicle need to be identified, so that the damaged parts of the flooded vehicle can be conveniently counted in the following process.
The water level line refers to a horizontal line which is superposed with the water flooded vehicle on the upper plane of the water flooded vehicle.
S33: the gray sampling value is compared with a pre-selected threshold value, and pixels with the gray sampling values larger than the pre-selected threshold value are used as identification features.
Specifically, a sampled pixel value based on the gray image is compared with a pre-selected threshold, and a pixel value of which the sampled pixel value is greater than or equal to the pre-selected threshold is set to be 255, that is, the sampled pixel value is used as an identification feature; pixel values less than a preselected threshold are set to 0, i.e., they are used as background features. The sampled pixel value is the pixel value corresponding to each pixel point in the grayscale image. The size of the threshold value can influence the effect of the binarization processing of the gray level image, and when the threshold value is properly selected, the effect of the binarization processing of the gray level image is better; when the threshold value is selected improperly, the effect of the binarization processing of the gray level image is affected.
S34: and combining all the identification features to obtain an identification area, and taking the identification area as a target image.
Specifically, each identification feature corresponds to the outline and the water level line of the submerged vehicle, so all the identification features are combined to obtain the outline and the water level line of the complete submerged vehicle, and the identification area is used as a target image.
In the embodiment, the sharpened image is subjected to graying processing by adopting a component method to obtain a grayscale image, grayscale value sampling is carried out on the basis of the grayscale image to obtain a sampling value, the grayscale sampling value is compared with a pre-selected threshold value, pixels with the grayscale sampling values larger than the pre-selected threshold value are used as identification features, all the identification features are combined to obtain an identification area, the identification area is used as a target image, accurate processing of the image of the flooded vehicle is realized, the high-precision identification area is identified, the damaged part of the flooded vehicle can be identified subsequently, and the accuracy of damage determination of the flooded vehicle is improved.
Further, step S31 further includes:
and carrying out normalization processing on the gray level image by adopting a gray level normalization mode.
Specifically, since the steps adopt various image processing means, the means may cause changes of some properties of the image of the submerged vehicle. Such as the area and perimeter of a flooded vehicle, is inherently of a constant nature for coordinate rotation. In general, the effect of certain factors or transformations on some properties of the flooded car image can be eliminated or reduced by normalization processing, and thus can be selected as a basis for measuring the image and making certain features of the image a standard form of the image with invariant properties given the transformation. For example, for remote sensing pictures with uncontrollable illumination, normalization of the gray level histogram is necessary for image analysis. The normalization process is to limit the data within a certain range after the data is processed. The gray normalization processing refers to limiting the gray value of the image within a certain range.
The normalization processing means includes but is not limited to: grayscale normalization, geometric normalization, and transform normalization. In the embodiment, a gray scale normalization method is adopted.
The grayscale normalization process includes, but is not limited to: mean variance normalization and gray scale transformation normalization. In the present embodiment, a manner of gray scale transformation normalization is preferable, in which the gray scale transformation normalization is to expand the gray scale distribution in the original image to an image having the entire gray scale by using a gray scale stretching method.
In the embodiment, a gray level normalization mode is adopted to perform normalization processing on the gray level map, so that the submerged vehicle image is further processed, the processing precision of the submerged vehicle image is improved, and the damage assessment precision of the submerged vehicle is further provided.
Further, step S34 includes:
and the effect of flooding the car outline and the water line in the gray-scale image is enhanced by an image enhancement technology.
Specifically, because the outline and the water level line in the image of the submerged vehicle need to be accurately identified, the identification effect is enhanced through an image enhancement technology. The visual effect of the image of the flooded vehicle is improved by selectively enhancing and suppressing the information in the image of the flooded vehicle, or the image is converted into a form more suitable for machine processing, so that the outline and water level line of the flooded vehicle can be extracted or identified.
Image enhancement techniques include, but are not limited to, contrast stretching, logarithmic transformation, density layering, histogram equalization, and the like. In a specific embodiment, the method of contrast broadening, histogram equalization and the like is adopted for repeated use, so that the image effect of the submerged vehicle is enhanced.
In the embodiment, the image enhancement technology is used for enhancing the effect of the outline and the water level line of the water flooded vehicle in the gray-scale image, further processing the image of the water flooded vehicle, improving the image processing precision of the water flooded vehicle and further providing the damage assessment precision of the water flooded vehicle.
Further, step S2 further includes:
and eliminating random noise of the image of the flooded car by adopting a median smoothing mode.
Specifically, in order to eliminate random noise in the image of the flooded vehicle and reduce interference of the random noise on identification of the image of the flooded vehicle, a smoothing technology is adopted to further eliminate the random noise. The basic requirement of the smoothing technique is to eliminate noise without obscuring the outline of the image of the flooded vehicle and the flooded vehicle.
The smoothing technique includes, but is not limited to, a median smoothing method, a local averaging method, a k-nearest neighbor averaging method, a spatial frequency domain band-pass filtering method, and the like. In the embodiment, a median smoothing mode is selected to eliminate random noise of the flooded vehicle image.
The median smoothing, also called median filtering, means that for each pixel, in a window centered on the pixel, the median brightness value of the neighboring pixel is taken to replace the brightness value of the pixel. The median filtering can effectively retain the edge information of the image and relatively reduce the blurring degree of the image while suppressing noise.
Wherein the random noise is a noise resulting from the accumulation of a large number of fluctuating disturbances randomly generated in time, the values of which cannot be predicted at a given instant
In the embodiment, a median smoothing mode is adopted, random noise of the image of the flooded vehicle is eliminated, the image of the flooded vehicle is further processed, the image processing precision of the flooded vehicle is improved, and therefore damage assessment precision of the flooded vehicle is improved.
Further, step S5 includes:
the method comprises the steps of identifying the vehicle type of the flooded vehicle, carrying out data association on the vehicle type and the flooding grade, and obtaining historical part claim settlement data of the vehicle type.
Specifically, each fixed vehicle model constitutes the same part of the vehicle, so the vehicle model of the flooded vehicle needs to be identified. The method for identifying the vehicle type of the flooded vehicle can be used for identifying the image of the flooded vehicle and can also be used for obtaining the image by sending a claim settlement instruction by a user. And performing data association on the vehicle type and the flooding grade, acquiring historical part claim settlement data of the vehicle type, and providing a basis for determining the damage condition of the flooded vehicle in the subsequent steps.
And counting the parts needing damage assessment of the flooding vehicle according to the flooding grade and the historical part claim settlement data.
Specifically, the vehicle model making dimensions (different vehicle models and different replacement part working hours) are used, big data are used for analysis and statistics, historical part claim settlement data are obtained, such as historical water flooding case damage assessment records of the A vehicle model, a part working hour item list with a high replacement proportion is classified and associated according to the water flooding grade, parts and working hour prices are brought in, bottom layer data of the damage assessment items of the A vehicle model are combined, and parts needing damage assessment are determined finally.
And determining the damage condition of the submerged vehicle according to the parts needing damage assessment.
Specifically, the parts of the flooded vehicle, which need to be damaged, are determined, and the damage condition of the flooded vehicle can be determined after the loss is counted.
In the embodiment, the vehicle type and the flooding grade are subjected to data association by identifying the vehicle type of the flooded vehicle, historical part claim data of the vehicle type are obtained, parts of the flooded vehicle which need damage assessment are counted according to the flooding grade and the historical part claim data, damage conditions of the flooded vehicle are determined according to the parts which need damage assessment, statistics of all damaged parts of the flooded vehicle is achieved, the damage conditions are determined, and improvement of accuracy of damage assessment of the flooded vehicle is facilitated.
Further, step S1 further includes:
and identifying a license plate part and a VIN code part from the flooded vehicle image, identifying a license plate number from the license plate part, and identifying the VIN code from the VIN code part.
Specifically, in order to prevent a vehicle that is not under insurance from being maliciously damaged, the image of the flooded vehicle needs to be identified, so as to determine whether the vehicle of the image of the flooded vehicle is an insurance vehicle.
The VIN code is a Vehicle Identification Number (or frame Number), abbreviated as VIN, and is a set of seventeen letters or numbers, and is used for a unique set of numbers on an automobile, and can identify data such as manufacturer, engine, chassis serial Number and other performances of the automobile.
And judging whether the flooded vehicle is a insurance vehicle or not through the license plate number or the VIN code.
Specifically, when the license plate number or the VIN code exists in the insurance record, the flooded vehicle is judged to be the insurance vehicle, otherwise, the flooded vehicle is judged not to be the insurance vehicle. And when the flooded vehicle is judged not to be the insurance vehicle, the subsequent damage assessment step is not carried out.
In the embodiment, the license plate part and the VIN code part are identified from the flooded vehicle image, the license plate number is identified from the license plate part, the VIN code is identified from the VIN code part, and whether the flooded vehicle is a insured vehicle is judged through the license plate number or the VIN code, so that the vehicle which is not insured is prevented from being maliciously damaged.
It is emphasized that the feature data may also be stored in a node of a blockchain in order to further ensure privacy and security of the feature data.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the computer program is executed. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
Referring to fig. 4, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a damage assessment apparatus for a flooded vehicle based on artificial intelligence, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be applied to various electronic devices.
As shown in fig. 4, the damage assessment device for a flooded vehicle based on artificial intelligence in this embodiment includes: a claim settlement instruction receiving module 61, a sharpened image obtaining module 62, a target image determining module 63, a flooding level obtaining unit 64 and a damage condition determining module 65, wherein:
the claim settlement instruction receiving module 61 is used for receiving a claim settlement instruction which is sent by a user side and contains the unique identification of the flooded vehicle, and acquiring feature data and an image of the flooded vehicle from uploaded data of the user side according to the unique identification, wherein the feature data comprises the vehicle type of the flooded vehicle and the component parameters of the flooded vehicle;
the sharpened image acquisition module 62 is configured to correct the flooded vehicle image in a perspective transformation manner to obtain a basic image, and sharpen the basic image to obtain a sharpened image;
the target image determining module 63 is configured to perform graying processing on the sharpened image to obtain a grayscale image, perform binarization processing on the grayscale image, and identify an identification area of the grayscale image to obtain a target image, where the identification area includes a flooded vehicle contour and a water line;
the flooding grade acquiring unit 64 is used for inputting the target image into the trained recognition model to obtain a flooding grade of the flooding vehicle;
and the damaged condition determining module 65 is used for performing data association on the flooding grade and the characteristic data, identifying the parts of the flooded vehicle which need damage assessment, and determining the damaged condition of the flooded vehicle according to the parts which need damage assessment.
Further, the sharpened image acquisition module 62 includes:
the image projection unit is used for projecting the flooded car image to a new view plane;
the basic image unit is used for calculating the angle of the edge of the flooded vehicle image deviating from the new view plane through a preset algorithm, and correcting the flooded vehicle image through the angle to obtain a basic image;
and the sharpening processing unit is used for eliminating background lines of the basic image by sharpening the basic image to obtain a sharpened image.
Further, the target image determination module 63 includes:
the gray image acquisition unit is used for carrying out gray processing on the sharpened image by adopting a component method to obtain a gray image;
the gray value sampling unit is used for carrying out gray value sampling based on the gray map to obtain a gray sampling value;
the identification feature acquisition unit is used for comparing the gray sampling value with a pre-selected threshold value and taking the pixel with the gray sampling value larger than the pre-selected threshold value as an identification feature;
and the identification feature combination unit is used for combining all the identification features to obtain an identification area, and taking the identification area as a target image. Further, the identifying feature obtaining unit further includes:
and the image enhancement unit is used for enhancing the effect of flooding the car outline and the water line in the gray-scale image by an image enhancement technology.
Further, the sharpened image acquisition module 62 further includes:
and the random noise elimination module is used for eliminating the random noise of the image of the flooded vehicle in a median smoothing mode.
Further, the damage condition determining module 65 includes:
the data association unit is used for identifying the vehicle type of the flooded vehicle, performing data association on the vehicle type and the flooding grade, and acquiring historical part claim data of the vehicle type;
the component counting unit is used for counting the components needing damage assessment of the flooded vehicle according to the flooding grade and the historical component claim settlement data;
and the situation determining unit is used for determining the damage situation of the water flooded vehicle according to the parts needing damage assessment.
Further, the claim settlement instruction receiving module 61 further includes:
the image recognition module is used for recognizing a license plate part and a VIN code part from the water flooded vehicle image, recognizing a license plate number from the license plate part and recognizing the VIN code from the VIN code part;
and the vehicle judging module is used for judging whether the flooded vehicle is a insurance vehicle or not through the license plate number or the VIN code.
It is emphasized that the feature data may also be stored in a node of a blockchain in order to further ensure privacy and security of the feature data.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 5, fig. 5 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 7 comprises a memory 71, a processor 72, a network interface 73, communicatively connected to each other by a system bus. It is noted that only a computer device 7 having three components memory 71, processor 72, network interface 73 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 71 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 71 may be an internal storage unit of the computer device 7, such as a hard disk or a memory of the computer device 7. In other embodiments, the memory 71 may also be an external storage device of the computer device 7, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device 7. Of course, the memory 71 may also comprise both an internal storage unit of the computer device 7 and an external storage device thereof. In this embodiment, the memory 71 is generally used for storing an operating system installed in the computer device 7 and various application software, such as program codes of a flooded car damage assessment method based on artificial intelligence. Further, the memory 71 may also be used to temporarily store various types of data that have been output or are to be output.
The network interface 73 may comprise a wireless network interface or a wired network interface, and the network interface 73 is typically used to establish a communication connection between the computer device 7 and other electronic devices.
The present application provides a computer-readable storage medium having stored thereon a server maintenance program, the server maintenance program being executable by at least one processor to cause the at least one processor to perform the steps of an artificial intelligence based water flooded vehicle damage assessment method as described above.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method of the embodiments of the present application.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. A damage assessment method for a flooded vehicle based on artificial intelligence is characterized by comprising the following steps:
receiving a claim settlement instruction which is sent by a user side and contains a unique identification of a flooded vehicle, and acquiring feature data and an image of the flooded vehicle from uploaded data of the user side according to the unique identification, wherein the feature data comprises a vehicle type of the flooded vehicle and component parameters of the flooded vehicle;
correcting the flooded vehicle image in a perspective transformation mode to obtain a basic image, and sharpening the basic image to obtain a sharpened image;
carrying out graying processing on the sharpened image to obtain a grayscale image, carrying out binarization processing on the grayscale image, identifying an identification area of the grayscale image, and obtaining a target image, wherein the identification area comprises a flooded vehicle contour and a water level line;
inputting the target image into a trained recognition model to obtain the flooding grade of the flooding vehicle;
and performing data association on the flooding grade and the characteristic data, identifying a part of the flooding vehicle which needs damage assessment, and determining the damage condition of the flooding vehicle according to the part which needs damage assessment.
2. The artificial intelligence-based flooded vehicle damage assessment method according to claim 1, wherein the correcting the flooded vehicle image by means of perspective transformation to obtain a base image, and the sharpening the base image to obtain a sharpened image comprises:
projecting the flooded vehicle image to a new viewing plane;
calculating the angle of the edge of the flooded car image deviating from the new view plane through a preset algorithm, and correcting the flooded car image through the angle to obtain the basic image;
and carrying out sharpening processing on the basic image to eliminate background lines of the basic image so as to obtain the sharpened image.
3. The artificial intelligence-based water flooded vehicle damage assessment method according to claim 1, wherein the graying the sharpened image to obtain a grayscale map, and the binarizing the grayscale map to identify the identification area of the grayscale map to obtain the target image comprises:
carrying out graying processing on the sharpened image by adopting a component method to obtain a grayscale image;
performing gray value sampling based on the gray image to obtain a gray sampling value;
comparing the gray sampling value with a pre-selected threshold value, and taking the pixel with the gray sampling value larger than the pre-selected threshold value as an identification feature;
and combining all the identification features to obtain the identification area, and taking the identification area as the target image.
4. The artificial intelligence-based water flooded vehicle damage assessment method according to claim 3, wherein the combining all the identification features to obtain the identification area, and the using the identification area as the target image further comprises:
and enhancing the effect of flooding the car outline and the water line in the gray-scale image by an image enhancement technology.
5. The artificial intelligence-based flooded vehicle damage assessment method according to claim 1, wherein the correcting the flooded vehicle image by means of perspective transformation to obtain a base image, and performing sharpening processing on the base image to obtain a sharpened image further comprises:
and eliminating random noise of the image of the flooded vehicle by adopting a median smoothing mode.
6. The artificial intelligence based damage assessment method for a flooded vehicle as recited in claim 1, wherein said data associating said flooding level with said characteristic data, identifying a damage requiring component of said flooded vehicle, and determining a damage condition of said flooded vehicle based on said damage requiring component comprises:
identifying the vehicle type of the flooded vehicle, performing data association on the vehicle type and the flooding grade, and acquiring historical part claim data of the vehicle type;
counting the parts needing damage assessment of the flooded vehicle according to the flooding grade and the historical part claim settlement data;
and determining the damage condition of the flooded vehicle according to the parts needing damage assessment.
7. The artificially-intelligent-based damage assessment method for flooded vehicles according to any one of claims 1 to 6, wherein the receiving of the claim settlement instruction containing the unique identifier of the flooded vehicle sent by the user side and the obtaining of the feature data and the image of the flooded vehicle according to the unique identifier further comprises:
identifying a license plate part and a VIN code part from the flooded vehicle image, identifying a license plate number from the license plate part, and identifying a VIN code from the VIN code part;
and judging whether the flooded vehicle is a guaranteed vehicle or not through the license plate number or the VIN code.
8. The utility model provides a water logging car decides to decrease device based on artificial intelligence which characterized in that includes:
the system comprises a claim settlement instruction receiving module, a user side and a user terminal, wherein the claim settlement instruction receiving module is used for receiving a claim settlement instruction which is sent by the user side and contains a unique identification of a flooded vehicle, and acquiring feature data and a flooded vehicle image of the flooded vehicle from uploaded data of the user side according to the unique identification, wherein the feature data comprises a vehicle type of the flooded vehicle and component parameters of the flooded vehicle;
the sharpening image acquisition module is used for correcting the flooded vehicle image in a perspective transformation mode to obtain a basic image, and sharpening the basic image to obtain a sharpened image;
the target image determining module is used for carrying out graying processing on the sharpened image to obtain a grayscale image, carrying out binarization processing on the grayscale image to identify an identification area of the grayscale image to obtain a target image, wherein the identification area comprises a flooded vehicle outline and a water level line;
the flooding grade acquisition unit is used for inputting the target image into a trained recognition model to obtain a flooding grade of the flooding vehicle;
and the damaged condition determining module is used for performing data association on the flooding grade and the characteristic data, identifying a part of the flooded vehicle which needs damage assessment, and determining the damaged condition of the flooded vehicle according to the part of the flooded vehicle which needs damage assessment.
9. A computer device comprising a memory having stored therein a computer program and a processor that when executed implements the artificial intelligence based water flooded vehicle damage method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the artificial intelligence based water flooded vehicle damage management method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010930254.9A CN112085721A (en) | 2020-09-07 | 2020-09-07 | Damage assessment method, device and equipment for flooded vehicle based on artificial intelligence and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010930254.9A CN112085721A (en) | 2020-09-07 | 2020-09-07 | Damage assessment method, device and equipment for flooded vehicle based on artificial intelligence and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112085721A true CN112085721A (en) | 2020-12-15 |
Family
ID=73733134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010930254.9A Pending CN112085721A (en) | 2020-09-07 | 2020-09-07 | Damage assessment method, device and equipment for flooded vehicle based on artificial intelligence and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112085721A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112712077A (en) * | 2020-12-30 | 2021-04-27 | 中冶赛迪重庆信息技术有限公司 | Steel flow contour determination method, system, terminal and medium |
| CN112749735A (en) * | 2020-12-30 | 2021-05-04 | 中冶赛迪重庆信息技术有限公司 | Converter tapping steel flow identification method, system, medium and terminal based on deep learning |
| CN113838022A (en) * | 2021-09-22 | 2021-12-24 | 清华珠三角研究院 | Method, system and device for identifying abnormal working conditions of automobile and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766805A (en) * | 2017-09-29 | 2018-03-06 | 阿里巴巴集团控股有限公司 | Lift the method, apparatus and server of car damage identification image recognition result |
| CN108446618A (en) * | 2018-03-09 | 2018-08-24 | 平安科技（深圳）有限公司 | Car damage identification method, device, electronic equipment and storage medium |
| CN109242006A (en) * | 2018-08-23 | 2019-01-18 | 阿里巴巴集团控股有限公司 | The method and device of identification vehicle damage based on vehicle classification |
| CN109934263A (en) * | 2019-01-31 | 2019-06-25 | 德联易控科技(北京)有限公司 | Vehicle identification method, device, electronic equipment and computer readable storage medium |
| CN110147719A (en) * | 2019-04-09 | 2019-08-20 | 平安科技（深圳）有限公司 | Car damage identification method, device, computer equipment and storage medium |
| CN110443814A (en) * | 2019-07-30 | 2019-11-12 | 北京百度网讯科技有限公司 | Damage identification method, device, equipment and the storage medium of vehicle |
| CN110705361A (en) * | 2019-09-06 | 2020-01-17 | 中国平安财产保险股份有限公司 | Intelligent damage assessment method and device for vehicle, computer system and readable storage medium |
| CN111311540A (en) * | 2020-01-13 | 2020-06-19 | 平安科技（深圳）有限公司 | Vehicle damage assessment method and device, computer equipment and storage medium |
-
2020
- 2020-09-07 CN CN202010930254.9A patent/CN112085721A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766805A (en) * | 2017-09-29 | 2018-03-06 | 阿里巴巴集团控股有限公司 | Lift the method, apparatus and server of car damage identification image recognition result |
| CN108446618A (en) * | 2018-03-09 | 2018-08-24 | 平安科技（深圳）有限公司 | Car damage identification method, device, electronic equipment and storage medium |
| CN109242006A (en) * | 2018-08-23 | 2019-01-18 | 阿里巴巴集团控股有限公司 | The method and device of identification vehicle damage based on vehicle classification |
| CN109934263A (en) * | 2019-01-31 | 2019-06-25 | 德联易控科技(北京)有限公司 | Vehicle identification method, device, electronic equipment and computer readable storage medium |
| CN110147719A (en) * | 2019-04-09 | 2019-08-20 | 平安科技（深圳）有限公司 | Car damage identification method, device, computer equipment and storage medium |
| CN110443814A (en) * | 2019-07-30 | 2019-11-12 | 北京百度网讯科技有限公司 | Damage identification method, device, equipment and the storage medium of vehicle |
| CN110705361A (en) * | 2019-09-06 | 2020-01-17 | 中国平安财产保险股份有限公司 | Intelligent damage assessment method and device for vehicle, computer system and readable storage medium |
| CN111311540A (en) * | 2020-01-13 | 2020-06-19 | 平安科技（深圳）有限公司 | Vehicle damage assessment method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| A6工作室魏然: "【实用】水淹车定损标准及注意事项", 《HTTPS://WWW.SOHU.COM/A/139639763_155848》, 10 May 2017 (2017-05-10), pages 1 - 7 * |
| 吴浩: "机动车水灾事故的查勘与定损", 《商》, no. 22, 15 June 2014 (2014-06-15), pages 291 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112712077A (en) * | 2020-12-30 | 2021-04-27 | 中冶赛迪重庆信息技术有限公司 | Steel flow contour determination method, system, terminal and medium |
| CN112749735A (en) * | 2020-12-30 | 2021-05-04 | 中冶赛迪重庆信息技术有限公司 | Converter tapping steel flow identification method, system, medium and terminal based on deep learning |
| CN112712077B (en) * | 2020-12-30 | 2023-04-07 | 中冶赛迪信息技术(重庆)有限公司 | Steel flow contour determination method, system, terminal and medium |
| CN112749735B (en) * | 2020-12-30 | 2023-04-07 | 中冶赛迪信息技术(重庆)有限公司 | Converter tapping steel flow identification method, system, medium and terminal based on deep learning |
| CN113838022A (en) * | 2021-09-22 | 2021-12-24 | 清华珠三角研究院 | Method, system and device for identifying abnormal working conditions of automobile and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148130B (en) | Method and device for detecting part defects | |
| CN107545239B (en) | Fake plate detection method based on license plate recognition and vehicle characteristic matching | |
| CN112085721A (en) | Damage assessment method, device and equipment for flooded vehicle based on artificial intelligence and storage medium | |
| CN110781885A (en) | Text detection method, device, medium and electronic equipment based on image processing | |
| US20210166015A1 (en) | Certificate image extraction method and terminal device | |
| CN111695410A (en) | Violation reporting method and device, computer equipment and storage medium | |
| CN110287787B (en) | Image recognition method, image recognition device and computer-readable storage medium | |
| CN110378254B (en) | Method and system for identifying vehicle damage image modification trace, electronic device and storage medium | |
| CN110502977B (en) | Building change classification detection method, system, device and storage medium | |
| CN114387591A (en) | License plate recognition method, system, equipment and storage medium | |
| CN111860027A (en) | Two-dimensional code identification method and device | |
| CN111695609A (en) | Target damage degree determination method, target damage degree determination device, electronic device, and storage medium | |
| CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
| CN116188024A (en) | Medical safety payment system | |
| CN112749735B (en) | Converter tapping steel flow identification method, system, medium and terminal based on deep learning | |
| CN112784494B (en) | Training method of false positive recognition model, target recognition method and device | |
| CN114049540A (en) | Method, device, equipment and medium for detecting marked image based on artificial intelligence | |
| CN111199240A (en) | Training method of bank card identification model, and bank card identification method and device | |
| CN110135274B (en) | Face recognition-based people flow statistics method | |
| CN111402185B (en) | Image detection method and device | |
| CN111353324A (en) | Method for reading two-dimensional code of dot matrix in glass | |
| CN110751623A (en) | Joint feature-based defect detection method, device, equipment and storage medium | |
| CN115359003A (en) | Two-step tunnel gray image crack identification method, system, medium and equipment | |
| CN113792671A (en) | Method and device for detecting face synthetic image, electronic equipment and medium | |
| CN114663899A (en) | Financial bill processing method, device, equipment and medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201215 |