CN114241180A - Image detection method and device for vehicle damage claims, computer equipment and storage medium - Google Patents
Image detection method and device for vehicle damage claims, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114241180A CN114241180A CN202111539611.XA CN202111539611A CN114241180A CN 114241180 A CN114241180 A CN 114241180A CN 202111539611 A CN202111539611 A CN 202111539611A CN 114241180 A CN114241180 A CN 114241180A
- Authority
- CN
- China
- Prior art keywords
- detection
- picture
- shooting
- preset
- model
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 claims abstract description 66
- 238000013135 deep learning Methods 0.000 claims abstract description 42
- 238000013145 classification model Methods 0.000 claims abstract description 39
- 230000008569 process Effects 0.000 claims abstract description 29
- 230000008859 change Effects 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 38
- 238000012795 verification Methods 0.000 claims description 24
- 230000000007 visual effect Effects 0.000 claims description 13
- 238000013138 pruning Methods 0.000 claims description 7
- 238000013139 quantization Methods 0.000 claims description 6
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application belongs to the field of artificial intelligence, and relates to a picture detection method for car damage claims, which comprises the following steps: carrying out part detection on a vehicle to be shot through a preset part type deep learning detection model, if the detection is successful, shooting a picture, and otherwise, prompting to change the shooting angle or/and distance; classifying the shot pictures through a preset picture quality classification model; executing a claim settlement operation rule according to the output classification result, wherein the claim settlement operation rule is as follows: if the output classification result is reproduction, the claim settlement process is stopped, if the output classification result is fuzzy or inclined angle, re-shooting is prompted, and if the output classification result is normal, the claim settlement process is continued. The application also provides a picture detection device, computer equipment and storage medium of the car damage claim. The method and the device can greatly reduce the waste image rate of the input image and improve the robustness of the system.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a vehicle damage claim settlement picture detection method and device, computer equipment and a storage medium.
Background
In an automatic automobile damage claim settlement system, a computer vision related technology is generally used for processing claim settlement problems, only a vehicle owner needs to shoot a proper vehicle damage picture by using a mobile phone, the automatic claim settlement system can evaluate damage conditions through the vehicle damage picture, and then the vehicle owner is given proper claim settlement amount according to certain rules. The whole process can be completed in real time and fully automatically, so that the waiting time of the car owner is reduced, and the insurance company is helped to save a large amount of human resources.
In the prior art, the common abnormal pictures encountered in the vehicle damage detection include the following pictures: firstly, the angle, distance and position of the shot picture are different, for example, the shooting direction is not vertical to the plane of the vehicle, so that the same damage is different in the damage conditions presented at different shooting angles, and the detection of the later damage degree is difficult; for example, although the detection and classification of the damage are beneficial when the shooting distance is too close, the specific part of the damage cannot be known through the picture, and for vehicle damage settlement, the corresponding settlement degree of the same damage at different parts is different; for damage settlement, the area of damage is an important factor, and in picture damage assessment, the actual area of damage is generally estimated according to the proportion of the area of a damaged pixel to the area of a pixel of the whole part, and the actual area of damage cannot be directly calculated through a picture. Meanwhile, the copied picture is suspected of insurance fraud and is an absolutely forbidden exception, if the copied picture appears in the claim process, the claim settlement flow needs to be stopped immediately, and the blurred picture needs to be shot again.
The shooting condition of the automobile damage photo has direct influence on the accuracy of system claim settlement, and due to the diversity of the automobile damage condition, the diversity of the shooting environment and the diversity of the photo shot by the automobile owner, the damage photo input by the system has various conditions, and the characteristic directly causes the high waste image rate and the low robustness in the automobile damage claim settlement system.
Disclosure of Invention
The embodiment of the application aims to provide a picture detection method and device for vehicle damage claims, computer equipment and a storage medium, so as to solve the technical problems of high waste picture rate and low robustness in a vehicle damage claim system in the prior art.
In order to solve the technical problem, an embodiment of the present application provides a picture detection method for car damage claims, which adopts the following technical scheme:
a picture detection method for car damage claims comprises the following steps:
carrying out part detection on a vehicle to be shot through a preset part type deep learning detection model, if the detection is successful, shooting a picture, and otherwise, prompting to change the shooting angle or/and distance;
classifying the shot pictures through a preset picture quality classification model, wherein output classification results of the picture quality classification model comprise copying, blurring, angle inclination and normality;
executing a claim settlement operation rule according to the output classification result, wherein the claim settlement operation rule is as follows: if the output classification result is reproduction, the claim settlement process is stopped, if the output classification result is fuzzy or inclined angle, re-shooting is prompted, and if the output classification result is normal, the claim settlement process is continued.
The method for detecting the part of the vehicle to be shot through the preset part category deep learning detection model further comprises the following steps:
adjusting the shooting distance according to a preset distance adjustment rule prompt, wherein the distance adjustment rule is as follows: if the vehicle or the part is not detected in the shooting visual field, prompting to adjust the shooting distance far; and prompting to adjust the shooting distance closer if more than two parts are detected in the shooting visual field or the occupation ratio of the detection frame is smaller than a set value.
Before the step of detecting the part of the vehicle to be shot through the preset part type deep learning detection model, the method further comprises the step of training the preset part type deep learning detection model, wherein the step of training the preset part type deep learning detection model comprises the following steps:
dividing the vehicle into a plurality of part categories according to preset parts;
the method comprises the following steps of adopting a plurality of vehicles and a plurality of pictures of a plurality of parts as a first training set, and extracting a set proportion in the first training set as a first verification set;
training the first verification set to form a part category deep learning detection model, verifying the part category deep learning detection model, if the verification passing rate is greater than a set threshold value, the verification is successful, otherwise, adjusting the first training set to retrain;
and compressing the part category deep learning detection model by adopting a quantization and network pruning method to obtain the compressed preset part category deep learning detection model.
Further, after classifying the shot picture through a preset picture quality classification model, the method further includes:
adding a type label to the output classification result of the picture;
counting the proportion of output classification results corresponding to the type labels in a set time period;
and judging whether the ratio is greater than a preset threshold value or not according to the type label, if so, outputting a shooting risk result, and otherwise, continuing to execute.
Further, the part category deep learning detection model is based on the ssd-mobilenet v2 framework.
Further, before the step of classifying the shot picture by the preset picture quality classification model, the method further includes training the preset picture quality classification model:
the picture after passing the part detection is used as a second training set, the picture comprises reproduction, blurring, angle inclination and normality, and a set proportion is extracted from the second training set to be used as a second verification set;
training the second training set by adopting a deep learning framework based on the mobilent-v 2 to form a picture quality classification model;
verifying the picture quality classification model by adopting a second verification set, wherein if the verification passing rate is greater than a set threshold value, the verification is successful, and otherwise, adjusting the second training set to retrain;
and compressing the image quality classification model by adopting a quantization and network pruning method to obtain the compressed preset image quality classification model.
In order to solve the technical problem, an embodiment of the present application further provides a picture detection device for car damage claim, which adopts the following technical scheme:
a picture detection device of car damage claim, comprising:
the part detection module is used for detecting the parts of the vehicle to be shot through a preset part type deep learning detection model, shooting pictures if the detection is successful, and prompting to change the shooting angle or/and distance if the detection is not successful;
the picture classification module is used for classifying the shot pictures through a preset picture quality classification model, and output classification results of the picture quality classification model comprise copying, blurring, angle inclination and normality; and
the execution module is used for executing a claim settlement operation rule according to the output classification result, wherein the claim settlement operation rule is as follows: if the output classification result is reproduction, the claim settlement process is stopped, if the output classification result is fuzzy or inclined angle, re-shooting is prompted, and if the output classification result is normal, the claim settlement process is continued.
Further, the position detection module further comprises a distance adjustment unit for adjusting the shooting distance according to a preset distance adjustment rule, wherein the distance adjustment rule is as follows: if the vehicle or the part is not detected in the shooting visual field, prompting to adjust the shooting distance far; and prompting to adjust the shooting distance closer if more than two parts are detected in the shooting visual field or the occupation ratio of the detection frame is smaller than a set value.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
a computer device comprising a memory and a processor, the memory having stored therein computer readable instructions, the processor implementing the steps of the method for photo detection of a car damage claim as described above when executing the computer readable instructions.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
a computer readable storage medium having computer readable instructions stored thereon, which when executed by a processor, implement the steps of the car damage claim photo detection method as described above.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:
according to the method, the part detection is carried out on the vehicle to be shot through a preset part type deep learning detection model, if the detection is successful, a picture is shot, and if not, the shooting angle or/and the shooting distance are prompted to be changed; classifying the shot pictures through a preset picture quality classification model, and screening out duplicated pictures, fuzzy pictures, angle inclination pictures and normal pictures; and executing the claim settlement operation rule according to the screened output classification result, stopping the claim settlement process if the output classification result is reproduction, prompting to shoot again if the output classification result is fuzzy or inclined angle, and continuing the claim settlement process if the output classification result is normal.
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 an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for photo detection of a car damage claim according to the present application;
FIG. 3 is a flowchart of one embodiment of step S201 in FIG. 2;
FIG. 4 is a flowchart of one embodiment of step S202 in FIG. 2;
FIG. 5 is a schematic diagram of an embodiment of a photo detection device for claims in accordance with the subject application;
FIG. 6 is a schematic block diagram of one embodiment of a computer device according to 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.
As shown in 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 various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, 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, e-book readers, MP3 players (Moving Picture experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), 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 image detection method for the car damage claim provided in the embodiment of the present application is generally executed by a server, and accordingly, the image detection apparatus for the car damage claim is generally disposed in the terminal device.
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.
With continued reference to fig. 2, a flow diagram of one embodiment of a method for photo detection of a car damage claim is shown, in accordance with the present application. The picture detection method of the car damage claim comprises the following steps:
step S201, the part detection is carried out on the vehicle to be shot through a preset part type deep learning detection model, if the detection is successful, the picture is shot, and otherwise, the shooting angle or/and the distance are prompted to be changed.
In this embodiment, the electronic device (for example, the server shown in fig. 1) on which the image detection method of the car damage claim is operated may implement data exchange with the terminal device through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection means may include, but is not limited to, a 3G/4G connection, a WiFi connection, a bluetooth connection, a WiMAX connection, a Zigbee connection, a uwb (ultra wideband) connection, and other wireless connection means now known or developed in the future.
The problem of shooting angle and shooting distance can be solved through the step, when the shooting angle is abnormal or the distance is improper, proper car position frames cannot be detected in the shooting visual field, and then the real-time detection result and the terminal equipment are interacted to guide a user to shoot proper pictures.
In this embodiment, before the step of performing the part detection on the vehicle to be photographed by using the preset part category deep learning detection model, the method further includes training the preset part category deep learning detection model, and as shown in fig. 3, the specific training step includes:
and step S2010, dividing the vehicle into a plurality of part categories according to preset parts.
Specifically, the vehicle is generally classified into 15 categories such as front, rear, left and right doors, front, rear, left and right fender panels, front, rear, front and rear covers, front, rear bumpers, left and right floor bulkheads, and a roof, in part.
In step S2011, a plurality of images of a plurality of vehicles and a plurality of parts are used as a first training set, and a set ratio is extracted from the first training set as a first verification set, where the ratio can be set as needed.
Specifically, pictures used in daily automobile loss assessment business are selected (and the shooting angles and shooting distances of the selected pictures meet requirements), and 6 ten thousand pictures of 15 different parts are selected as a first training set.
Step S2012, the first verification set is trained to form a part category deep learning detection model, the part category deep learning detection model is verified, if the verification passing rate is greater than the set threshold, the verification is successful, otherwise, the first training set is adjusted to perform retraining.
Specifically, a deep learning detection model based on an ssd-mobilenet v2 frame is adopted to realize detection of 15 types of parts, the detection speed of 3 frames per second can be realized in terminal equipment, and the requirement of a mobile terminal on real-time detection is basically met.
And S2013, compressing the part category deep learning detection model by adopting a quantization and network pruning method to obtain the compressed preset part category deep learning detection model.
Specifically, the size of the model is compressed by using a quantification (quantilizaiton) and network pruning method, so that the size of the model is about 2m under the condition of ensuring the identification precision, and the deployment requirement of the system on terminal equipment is ensured.
Step S202, classifying the shot pictures through a preset picture quality classification model, wherein output classification results of the picture quality classification model comprise copying, blurring, angle inclination and normality.
In this embodiment, before the step of classifying the captured picture by using a preset picture quality classification model, the method further includes training the preset picture quality classification model, and as shown in fig. 4, the specific training step includes:
step S2020, the picture after passing the part detection is used as a second training set, the picture comprises a copy, a blur, an angle inclination and a normal, a set proportion is extracted from the second training set to be used as a second verification set, and the proportion can be set according to requirements.
Step S2021, training the second training set by using a deep learning framework based on the mobilenet-v2 to form a picture quality classification model.
And step S2022, verifying the picture quality classification model by using a second verification set, wherein if the verification passing rate is greater than a set threshold, the verification is successful, and otherwise, adjusting the second training set for retraining.
Step S2023, compressing the image quality classification model by using quantization and network pruning methods, so that the size of the model is about 2m under the condition of ensuring the identification precision, and the deployment requirement of the system on terminal equipment is ensured.
In this embodiment, after classifying the captured picture through a preset picture quality classification model, the method further includes:
and adding a type label to the output classification result of the picture. By adding the type label, the calculation amount can be simplified, and the calculation efficiency is improved.
And counting the proportion of the output classification result corresponding to the type label in a set time period. That is, the proportion of the output classification result corresponding to the statistical type tag in a set time period (which may be one shooting cycle, for example, 1 hour, or a time period set by the user) may be: the proportion of the reproduced photos to the total photos, or the proportion of the blurred photos to the total photos, or the proportion of the angularly tilted photos to the total photos, or the proportion of the normal photos to the total photos.
And judging whether the ratio is greater than a preset threshold value or not according to the type label, if so, outputting a shooting risk result, and otherwise, continuing to execute.
Specifically, the type of the photo can be judged by the type tag, if the type of the photo is copying, when the occupation ratio is larger than a set threshold, the copying risk can be directly output at the terminal device to remind a user of normative shooting, if the type of the photo is fuzzy, when the occupation ratio is larger than the set threshold (different from the set threshold in copying), the fuzzy risk can also be directly output at the terminal device, if the type of the photo is angular inclination, when the occupation ratio is larger than the set threshold (different from the set threshold in copying), the angular inclination risk can also be directly output at the terminal device, and if the type of the photo is normal, the risk is not prompted.
Step S203, executing a claim settlement operation rule according to the output classification result, where the claim settlement operation rule is: if the output classification result is reproduction, the claim settlement process is stopped, if the output classification result is fuzzy or inclined angle, re-shooting is prompted, and if the output classification result is normal, the claim settlement process is continued.
In the embodiment, the part detection is carried out on the vehicle to be shot through the preset part type deep learning detection model, if the detection is successful, the picture is shot, otherwise, the shooting angle or/and distance is prompted to be changed, and the non-vehicle image, the long-range view or the short-range view can be filtered; classifying the shot pictures through a preset picture quality classification model, and screening out duplicated pictures, fuzzy pictures, angle inclination pictures and normal pictures; and executing the claim settlement operation rule according to the screened output classification result, stopping the claim settlement process if the output classification result is reproduction, prompting to shoot again if the output classification result is fuzzy or inclined angle, and continuing the claim settlement process if the output classification result is normal.
In some optional implementation manners of this embodiment, the performing, by using the preset part category deep learning detection model, part detection on the vehicle to be photographed further includes:
adjusting the shooting distance according to a preset distance adjustment rule prompt, wherein the distance adjustment rule is as follows: if the vehicle or the part is not detected in the shooting visual field, the distance of the camera is generally considered to be too short, and the shooting distance is prompted to be adjusted far; if the shooting distance is considered to be too far when more than two parts are detected in the shooting visual field or the occupation ratio of the detection frame is smaller than a set value, the shooting distance is prompted to be adjusted to be close.
By this step, the input picture can be prevented from having a close-up view or a distant view.
It should be emphasized that, in order to further ensure the privacy and security of the photo detection information of the car damage claim, the photo detection information of the car damage claim may also be stored in a node of a block chain.
The block chain referred by the application 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.
The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The application can be applied to the field of intelligent medical treatment, and therefore the construction of a smart city is promoted.
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 hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, the processes of the embodiments of the methods described above can be included. 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).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to fig. 5, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a car damage claim detecting device, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device may be applied to various electronic devices.
As shown in fig. 5, the image detecting apparatus 500 for vehicle damage claim according to this embodiment includes: a part detection module 501, a picture classification module 502 and an execution module 503. Wherein:
the part detection module 501 is configured to perform part detection on a vehicle to be shot through a preset part category deep learning detection model, shoot a picture if the detection is successful, and prompt to change a shooting angle or/and a shooting distance if the detection is not successful.
The picture classification module 502 is configured to classify the shot pictures through a preset picture quality classification model, where output classification results of the picture quality classification model include copying, blurring, angle inclination, and normality.
The executing module 503 is configured to execute a claim settlement operation rule according to the output classification result, where the claim settlement operation rule is: if the output classification result is reproduction, the claim settlement process is stopped, if the output classification result is fuzzy or inclined angle, re-shooting is prompted, and if the output classification result is normal, the claim settlement process is continued.
In this embodiment, the portion detecting module 501 further includes a distance adjusting unit, configured to adjust the shooting distance according to a preset distance adjusting rule, where the distance adjusting rule is: if the vehicle or the part is not detected in the shooting visual field, prompting to adjust the shooting distance far; and prompting to adjust the shooting distance closer if more than two parts are detected in the shooting visual field or the occupation ratio of the detection frame is smaller than a set value.
In the embodiment, the part detection is carried out on the vehicle to be shot through the preset part type deep learning detection model, if the detection is successful, the picture is shot, otherwise, the shooting angle or/and distance is prompted to be changed, and the non-vehicle image, the long-range view or the short-range view can be filtered; classifying the shot pictures through a preset picture quality classification model, and screening out duplicated pictures, fuzzy pictures, angle inclination pictures and normal pictures; and executing the claim settlement operation rule according to the screened output classification result, stopping the claim settlement process if the output classification result is reproduction, prompting to shoot again if the output classification result is fuzzy or inclined angle, and continuing the claim settlement process if the output classification result is normal.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 6, fig. 6 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 6 comprises a memory 61, a processor 62, a network interface 63 communicatively connected to each other via a system bus. It is noted that only a computer device 6 having components 61-63 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 can be a desktop computer, a notebook, a palm computer, a cloud server and 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 61 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 memory 61 may be an internal storage unit of the computer device 6, such as a hard disk or a memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, 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, which are provided on the computer device 6. Of course, the memory 61 may also comprise both an internal storage unit of the computer device 6 and an external storage device thereof. In this embodiment, the memory 61 is generally used for storing an operating system installed on the computer device 6 and various types of application software, such as computer readable instructions of a picture detection method for car damage claim. Further, the memory 61 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 62 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 62 is typically used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is configured to execute computer readable instructions stored in the memory 61 or process data, such as computer readable instructions for executing the picture detection method of the car damage claim.
The network interface 63 may comprise a wireless network interface or a wired network interface, and the network interface 63 is typically used for establishing a communication connection between the computer device 6 and other electronic devices.
According to the method, the part detection is carried out on the vehicle to be shot through the preset part type deep learning detection model, if the detection is successful, the picture is shot, otherwise, the shooting angle or/and the shooting distance are prompted to be changed, and the non-vehicle image, the long-range view or the short-range view can be filtered; classifying the shot pictures through a preset picture quality classification model, and screening out duplicated pictures, fuzzy pictures, angle inclination pictures and normal pictures; and executing the claim settlement operation rule according to the screened output classification result, stopping the claim settlement process if the output classification result is reproduction, prompting to shoot again if the output classification result is fuzzy or inclined angle, and continuing the claim settlement process if the output classification result is normal.
The present application provides another embodiment, which is to provide a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the method for detecting a picture of a damage claim as described above.
According to the method, the part detection is carried out on the vehicle to be shot through the preset part type deep learning detection model, if the detection is successful, the picture is shot, otherwise, the shooting angle or/and the shooting distance are prompted to be changed, and the non-vehicle image, the long-range view or the short-range view can be filtered; classifying the shot pictures through a preset picture quality classification model, and screening out duplicated pictures, fuzzy pictures, angle inclination pictures and normal pictures; and executing the claim settlement operation rule according to the screened output classification result, stopping the claim settlement process if the output classification result is reproduction, prompting to shoot again if the output classification result is fuzzy or inclined angle, and continuing the claim settlement process if the output classification result is normal.
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 according to the embodiments of the present application.
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 picture detection method for car damage claims is characterized by comprising the following steps:
carrying out part detection on a vehicle to be shot through a preset part type deep learning detection model, if the detection is successful, shooting a picture, and otherwise, prompting to change the shooting angle or/and distance;
classifying the shot pictures through a preset picture quality classification model, wherein output classification results of the picture quality classification model comprise copying, blurring, angle inclination and normality;
executing a claim settlement operation rule according to the output classification result, wherein the claim settlement operation rule is as follows: if the output classification result is reproduction, the claim settlement process is stopped, if the output classification result is fuzzy or inclined angle, re-shooting is prompted, and if the output classification result is normal, the claim settlement process is continued.
2. The vehicle damage claim picture detection method according to claim 1, wherein the step of detecting the part of the vehicle to be photographed through a preset part category deep learning detection model further comprises:
adjusting the shooting distance according to a preset distance adjustment rule prompt, wherein the distance adjustment rule is as follows: if the vehicle or the part is not detected in the shooting visual field, prompting to adjust the shooting distance far; and prompting to adjust the shooting distance closer if more than two parts are detected in the shooting visual field or the occupation ratio of the detection frame is smaller than a set value.
3. The method for detecting claims on vehicle according to claim 1, wherein before the step of detecting the location of the vehicle to be photographed by the preset location classification deep learning detection model, the method further comprises training the preset location classification deep learning detection model, and the step of training the preset location classification deep learning detection model comprises:
dividing the vehicle into a plurality of part categories according to preset parts;
the method comprises the following steps of adopting a plurality of vehicles and a plurality of pictures of a plurality of parts as a first training set, and extracting a set proportion in the first training set as a first verification set;
training the first verification set to form a part category deep learning detection model, verifying the part category deep learning detection model, if the verification passing rate is greater than a set threshold value, the verification is successful, otherwise, adjusting the first training set to retrain;
and compressing the part category deep learning detection model by adopting a quantization and network pruning method to obtain the compressed preset part category deep learning detection model.
4. The method for detecting the vehicle damage claim picture according to claim 1, wherein the step of classifying the captured picture according to a preset picture quality classification model further comprises:
adding a type label to the output classification result of the picture;
counting the proportion of output classification results corresponding to the type labels in a set time period;
and judging whether the ratio is greater than a preset threshold value or not according to the type label, if so, outputting a shooting risk result, and otherwise, continuing to execute.
5. The photo detection method of claims against car damage according to claim 3, wherein the part category deep learning detection model is a deep learning detection model based on the ssd-mobilenet v2 framework.
6. The method for detecting vehicle damage claims according to any one of claims 1-5, wherein before the step of classifying the captured picture by a preset picture quality classification model, the method further comprises training the preset picture quality classification model, and the step of training the preset picture quality classification model comprises:
the picture after passing the part detection is used as a second training set, the picture comprises reproduction, blurring, angle inclination and normality, and a set proportion is extracted from the second training set to be used as a second verification set;
training the second training set by adopting a deep learning framework based on the mobilent-v 2 to form a picture quality classification model;
verifying the picture quality classification model by adopting a second verification set, wherein if the verification passing rate is greater than a set threshold value, the verification is successful, and otherwise, adjusting the second training set to retrain;
and compressing the image quality classification model by adopting a quantization and network pruning method to obtain the compressed preset image quality classification model.
7. The utility model provides a picture detection device of car damage claim, its characterized in that includes:
the part detection module is used for detecting the parts of the vehicle to be shot through a preset part type deep learning detection model, shooting pictures if the detection is successful, and prompting to change the shooting angle or/and distance if the detection is not successful;
the picture classification module is used for classifying the shot pictures through a preset picture quality classification model, and output classification results of the picture quality classification model comprise copying, blurring, angle inclination and normality; and
the execution module is used for executing a claim settlement operation rule according to the output classification result, wherein the claim settlement operation rule is as follows: if the output classification result is reproduction, the claim settlement process is stopped, if the output classification result is fuzzy or inclined angle, re-shooting is prompted, and if the output classification result is normal, the claim settlement process is continued.
8. The device for detecting the vehicle damage claim picture according to claim 7, wherein the portion detecting module further comprises a distance adjusting unit for adjusting the shooting distance according to a preset distance adjusting rule, wherein the distance adjusting rule is as follows: if the vehicle or the part is not detected in the shooting visual field, prompting to adjust the shooting distance far; and prompting to adjust the shooting distance closer if more than two parts are detected in the shooting visual field or the occupation ratio of the detection frame is smaller than a set value.
9. A computer device comprising a memory and a processor, the memory having stored therein computer readable instructions, wherein the processor when executing the computer readable instructions implements the steps of the method for photo-detection of claims from a car damage claim as recited in any one of claims 1 to 6.
10. A computer readable storage medium, having computer readable instructions stored thereon, which when executed by a processor, implement the steps of the photo detection method of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111539611.XA CN114241180A (en) | 2021-12-15 | 2021-12-15 | Image detection method and device for vehicle damage claims, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111539611.XA CN114241180A (en) | 2021-12-15 | 2021-12-15 | Image detection method and device for vehicle damage claims, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114241180A true CN114241180A (en) | 2022-03-25 |
Family
ID=80757021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111539611.XA Pending CN114241180A (en) | 2021-12-15 | 2021-12-15 | Image detection method and device for vehicle damage claims, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114241180A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372651A (en) * | 2016-08-22 | 2017-02-01 | 平安科技（深圳）有限公司 | Picture quality detection method and device |
| CN108734702A (en) * | 2018-04-26 | 2018-11-02 | 平安科技（深圳）有限公司 | Vehicle damages determination method, server and storage medium |
| CN110245552A (en) * | 2019-04-29 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Interaction processing method, device, equipment and the client of vehicle damage image taking |
| CN110660000A (en) * | 2019-09-09 | 2020-01-07 | 平安科技（深圳）有限公司 | Data prediction method, device, equipment and computer readable storage medium |
| CN111340640A (en) * | 2020-05-22 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Insurance claim settlement material auditing method, device and equipment |
| CN112348686A (en) * | 2020-11-24 | 2021-02-09 | 德联易控科技(北京)有限公司 | Claim settlement picture acquisition method and device and communication equipment |
| CN112418009A (en) * | 2020-11-06 | 2021-02-26 | 中保车服科技服务股份有限公司 | Image quality detection method, terminal device and storage medium |
| CN113033372A (en) * | 2021-03-19 | 2021-06-25 | 北京百度网讯科技有限公司 | Vehicle damage assessment method and device, electronic equipment and computer readable storage medium |
| CN113038018A (en) * | 2019-10-30 | 2021-06-25 | 支付宝(杭州)信息技术有限公司 | Method and device for assisting user in shooting vehicle video |
-
2021
- 2021-12-15 CN CN202111539611.XA patent/CN114241180A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372651A (en) * | 2016-08-22 | 2017-02-01 | 平安科技（深圳）有限公司 | Picture quality detection method and device |
| CN108734702A (en) * | 2018-04-26 | 2018-11-02 | 平安科技（深圳）有限公司 | Vehicle damages determination method, server and storage medium |
| CN110245552A (en) * | 2019-04-29 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Interaction processing method, device, equipment and the client of vehicle damage image taking |
| CN110660000A (en) * | 2019-09-09 | 2020-01-07 | 平安科技（深圳）有限公司 | Data prediction method, device, equipment and computer readable storage medium |
| CN113038018A (en) * | 2019-10-30 | 2021-06-25 | 支付宝(杭州)信息技术有限公司 | Method and device for assisting user in shooting vehicle video |
| CN111340640A (en) * | 2020-05-22 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Insurance claim settlement material auditing method, device and equipment |
| CN112418009A (en) * | 2020-11-06 | 2021-02-26 | 中保车服科技服务股份有限公司 | Image quality detection method, terminal device and storage medium |
| CN112348686A (en) * | 2020-11-24 | 2021-02-09 | 德联易控科技(北京)有限公司 | Claim settlement picture acquisition method and device and communication equipment |
| CN113033372A (en) * | 2021-03-19 | 2021-06-25 | 北京百度网讯科技有限公司 | Vehicle damage assessment method and device, electronic equipment and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 刘小榴等: "商品拍摄与图片处理", vol. 1, 30 September 2020, 北京理工大学出版社, pages: 97 * |
| 双锴: "自然语言处理", vol. 1, 31 August 2021, 北京邮电大学出版社, pages: 222 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111310562B (en) | Vehicle driving risk management and control method based on artificial intelligence and related equipment thereof | |
| WO2022126970A1 (en) | Method and device for financial fraud risk identification, computer device, and storage medium | |
| WO2021135879A1 (en) | Vehicle data monitoring method and apparatus, computer device, and storage medium | |
| CN112329659A (en) | Weak supervision semantic segmentation method based on vehicle image and related equipment thereof | |
| CN110795714A (en) | Identity authentication method and device, computer equipment and storage medium | |
| CN109409241A (en) | Video checking method, device, equipment and readable storage medium storing program for executing | |
| CN112101520A (en) | Risk assessment model training method, business risk assessment method and other equipment | |
| CN112016502B (en) | Safety belt detection method, safety belt detection device, computer equipment and storage medium | |
| CN113239910B (en) | Certificate identification method, device, equipment and storage medium | |
| CN112330331A (en) | Identity verification method, device and equipment based on face recognition and storage medium | |
| CN112686243A (en) | Method and device for intelligently identifying picture characters, computer equipment and storage medium | |
| CN111178357A (en) | License plate recognition method, system, device and storage medium | |
| CN114550051A (en) | Vehicle loss detection method and device, computer equipment and storage medium | |
| CN114663871A (en) | Image recognition method, training method, device, system and storage medium | |
| CN114861241A (en) | Anti-peeping screen method based on intelligent detection and related equipment thereof | |
| CN114550052A (en) | Vehicle accident handling method and device, computer equipment and storage medium | |
| CN114282258A (en) | Screen capture data desensitization method and device, computer equipment and storage medium | |
| CN114140649A (en) | Bill classification method, bill classification device, electronic apparatus, and storage medium | |
| CN112434746A (en) | Pre-labeling method based on hierarchical transfer learning and related equipment thereof | |
| CN112396060A (en) | Identity card identification method based on identity card segmentation model and related equipment thereof | |
| CN114241180A (en) | Image detection method and device for vehicle damage claims, computer equipment and storage medium | |
| CN113362249B (en) | Text image synthesis method, text image synthesis device, computer equipment and storage medium | |
| CN115700845A (en) | Face recognition model training method, face recognition device and related equipment | |
| CN115757075A (en) | Task abnormity detection method and device, computer equipment and storage medium | |
| CN114549221A (en) | Vehicle accident loss processing method and device, computer equipment and storage 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 |