WO2019062743A1 - 提升车辆定损图像识别结果的方法、装置及服务器 - Google Patents
提升车辆定损图像识别结果的方法、装置及服务器 Download PDFInfo
- Publication number
- WO2019062743A1 WO2019062743A1 PCT/CN2018/107526 CN2018107526W WO2019062743A1 WO 2019062743 A1 WO2019062743 A1 WO 2019062743A1 CN 2018107526 W CN2018107526 W CN 2018107526W WO 2019062743 A1 WO2019062743 A1 WO 2019062743A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- accessory
- vehicle
- list
- damaged component
- preliminary
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 91
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 72
- 238000012545 processing Methods 0.000 claims abstract description 62
- 230000015654 memory Effects 0.000 claims description 32
- 230000008569 process Effects 0.000 claims description 28
- 230000001174 ascending effect Effects 0.000 claims 3
- 238000003860 storage Methods 0.000 description 18
- 230000006870 function Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 14
- 230000006872 improvement Effects 0.000 description 9
- 238000013527 convolutional neural network Methods 0.000 description 8
- 239000000463 material Substances 0.000 description 7
- 238000004590 computer program Methods 0.000 description 6
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 229910052709 silver Inorganic materials 0.000 description 5
- 239000004332 silver Substances 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002085 persistent effect Effects 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 229910052736 halogen Inorganic materials 0.000 description 1
- 125000005843 halogen group Chemical group 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 229910052724 xenon Inorganic materials 0.000 description 1
- FHNFHKCVQCLJFQ-UHFFFAOYSA-N xenon atom Chemical compound [Xe] FHNFHKCVQCLJFQ-UHFFFAOYSA-N 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
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Definitions
- the embodiment of the present specification belongs to the technical field of vehicle fixed loss image data processing, and in particular, to a method, device and server for improving a vehicle damage image recognition result.
- the accuracy of the identification of the damaged component mainly depends on the algorithm/model for identifying the damage image, through various models/
- the algorithm identifies the image of the vehicle loss (including image data such as pictures and videos), obtains the damage location and degree, and then obtains the damage result according to the corresponding maintenance strategy.
- the model/algorithm used in the industry mainly collects the appearance data of various vehicle models in advance, and then uses the constructed vehicle accessory damage algorithm to identify the damage components and the degree of damage in the fixed-loss image.
- the embodiment of the present specification aims to provide a method, a device and a server for improving the image recognition result of a fixed loss image of a vehicle, which can effectively improve the accuracy and recognition efficiency of the vehicle damage image recognition result, and reduce the overall image algorithm recognition period and cost.
- the method, device and server for improving the vehicle damage image recognition result provided by the embodiments of the present specification are implemented by the following methods:
- a method for improving a vehicle damage image recognition result comprising:
- the preliminary damaged component comprising: performing a recognition process on the fixed loss image by using a preset image recognition algorithm to obtain a damaged component of the vehicle;
- the accessory list includes an accessory identification number corresponding to the vehicle accessory data
- the matching component identification number of the vehicle accessory is output.
- An apparatus for improving a vehicle damage image recognition result comprising:
- An algorithm processing module configured to acquire a preliminary damaged component of the vehicle, the preliminary damaged component comprising: performing a recognition process on the fixed-loss image by using a preset image recognition algorithm to obtain a damaged component of the vehicle;
- An accessory list processing module configured to acquire a list of accessories of the vehicle, and convert the vehicle accessory data in the accessory list into a corresponding accessory identification number
- a matching module configured to match the preliminary damaged component in the accessory list, and determine that the preliminary damaged component corresponds to a vehicle accessory in the accessory list;
- the recognition result output module is configured to output the matched accessory identification number of the vehicle accessory.
- An apparatus for improving a vehicle damage image recognition result includes a processor and a memory for storing processor executable instructions, the processor implementing the instructions to:
- the preliminary damaged component comprising: performing a recognition process on the fixed loss image by using a preset image recognition algorithm to obtain a damaged component of the vehicle;
- the matching component identification number of the vehicle accessory is output.
- a server comprising at least one processor and a memory storing processor executable instructions, the processor implementing the instructions to:
- the preliminary damaged component comprising: performing a recognition process on the fixed loss image by using a preset image recognition algorithm to obtain a damaged component of the vehicle;
- the matching component identification number of the vehicle accessory is output.
- the method, device and server for improving the image recognition result of the vehicle damage are provided by the embodiment of the present specification, and the preliminary damaged component can be obtained by using the image recognition algorithm to obtain the preliminary damaged component information. More accurate vehicle part numbers in the parts list.
- the fixed loss image is encoded by the algorithm and combined with the accessory list to output a more accurate part number, which can effectively improve the accuracy of the image recognition result and improve the image recognition accuracy.
- the implementation provided by the present specification can be combined with the accessory data identification information of the damaged accessory of the vehicle to be refined into the individual individual vehicle, and the output result is more accurate, which greatly facilitates the positioning/purchasing of the accessory and reduces the overall damage image.
- the recognition cost and learning period of the recognition algorithm greatly improve the efficiency and accuracy of the vehicle's fixed-loss image recognition processing.
- FIG. 1 is a schematic flow chart of an embodiment of a method for improving a vehicle damage image recognition result according to the present specification
- FIG. 2 is a schematic flow chart of another embodiment of a method for improving a vehicle damage image recognition result provided by the present specification
- FIG. 3 is a schematic diagram of a process flow of an implementation scenario of performing fixed loss image processing by using the solution of the embodiment of the present specification
- FIG. 4 is a block diagram showing a structure of an apparatus for improving a vehicle damage image recognition result provided by the present specification
- FIG. 5 is a schematic structural diagram of a module of another embodiment of the apparatus provided by the present specification.
- FIG. 6 is a schematic structural diagram of a module of another embodiment of the apparatus provided by the present specification.
- FIG. 7 is a schematic structural diagram of an embodiment of the server provided by the present specification.
- the existing vehicles are divided into various types. Even for the same model, it is often caused by different factory time, different configurations (such as high, medium and low configurations), and even with the customization of manufacturers. Parts in the same part may vary widely, even completely different parts.
- the front bumper of the comfort configuration is integral
- the front bumper of the luxury configuration is three-stage.
- there is a trim on the bumper of the mid-range model and there is no trim on the bumper of the low-profile model.
- Existing processing schemes that rely solely on image recognition technology to identify damaged parts of a vehicle are difficult to identify the above differences or require image recognition algorithms and sample data with higher cost and longer learning period.
- the vehicle identification number also referred to as the accessory OE number, which refers to the number of parts of the vehicle model produced by the vehicle manufacturer
- the accessory OE number refers to the number of parts of the vehicle model produced by the vehicle manufacturer
- the embodiment provided by one or more embodiments in the present specification can acquire the accessory list information of the fixed-loss vehicle by using the unique vehicle identification code of the vehicle, and then combine with the image recognition algorithm to significantly improve the recognition algorithm of the fixed-loss image algorithm.
- the accuracy of the loss component results greatly reduces the additional learning cost and learning cycle of the image recognition algorithm/model.
- the method for improving the vehicle damage image recognition result may obtain an accessory list of the currently processed vehicle after initially obtaining the damaged component of the vehicle by using the image recognition algorithm, and further determine the damaged component based on the accessory list.
- the accessory information in the accessories list For example, when it is recognized by the image recognition model that the damaged component is a bumper, it is possible to know which type of vehicle is equipped with a bumper according to the vehicle identification code (assuming that the bumpers of differently configured vehicles are different), for example, insurance. Whether there are trims or the like outside the bar.
- the vehicle component corresponding to the damaged component in the accessory list can then be used as the identified damaged component of the vehicle, for example, the damaged component is "with smoked black taillight" or "bumper: bright silver ABS plated trim".
- the accessory identification number of the vehicle accessory may be obtained according to the accessory list, and the accessory identification number may be used for accurate procurement, or may be fed back to the vehicle user or other related parties such as an insurance company in combination with other information, so as to be based on the accessory identification number. More precise processing of vehicle damage is performed.
- FIG. 1 is a schematic flowchart diagram of an embodiment of a method for improving a vehicle damage image recognition result provided by the present specification.
- the present specification provides method operation steps or device structures as shown in the following embodiments or figures, there may be more or partial merged fewer operational steps in the method or device based on conventional or no inventive labor. Or module unit.
- the execution order of the steps or the module structure of the device is not limited to the execution order or the module structure shown in the embodiment or the drawings.
- the device, server or terminal product of the method or module structure When the device, server or terminal product of the method or module structure is applied, it may be executed sequentially or in parallel according to the method or module structure shown in the embodiment or the drawing (for example, parallel processor or multi-thread processing). Environment, even including distributed processing, server cluster implementation environment).
- the method provided in the embodiments of the present disclosure can be used in a server for performing vehicle damage image recognition processing, a client that performs on-site photographing for fixed-loss image processing (such as a mobile terminal installed with a loss-loss service application), or other electronic devices, and can implement the method.
- the identification process of the damage image is obtained, and the component identification number of the damaged component of the vehicle can be obtained in combination with the accessory list of the vehicle.
- the processing on the server side may be used as an implementation scenario.
- the method may include:
- S2 Acquiring a preliminary damaged component of the vehicle, the preliminary damaged component comprising performing a recognition process on the fixed loss image by using a preset image recognition algorithm to obtain a damaged component of the vehicle.
- the server may obtain the fixed loss image of the vehicle, and may specifically include the manner in which the mobile terminal captures the image transmitted to the server in the field, and may also include the image acquired from the mobile storage device, the remote storage device, or other third-party service platform.
- the images described in the implementation of this specification may be a generic term for various graphics and images, generally referred to as visually pleasing images, and may generally include images on paper media, negatives or photographs, televisions, projectors, or computer screens.
- the fixed-loss image may specifically include a single-shot captured vehicle picture or a captured video (a video may be regarded as a collection of consecutive images).
- the server may perform identification processing using the fixed loss image of the vehicle to determine the damaged component and the degree of damage in the fixed loss image, and the specific server may output the data of the name of the initially damaged component and the degree of damage, such as preliminary acceptance.
- the component damage recognition model for identifying the damaged component of the vehicle in the fixed-loss image may be constructed in advance using the designed image recognition algorithm. After the component damage recognition model is trained in the previous sample, the damage location and the damage type of the vehicle accessory in the component image can be identified.
- the image recognition algorithm may include some network model algorithms and variants of the deep neural network, and the processing algorithm of the generated component damage recognition model is constructed after the sample training.
- an algorithm model for image recognition can be constructed based on a Convolutional Neural Network (CNN) and a Region Proposal Network (RPN), combined with a pooling layer and a fully connected layer, and the server obtains a fixed loss. After the image, the algorithm model can be used to identify the damage image to identify the initially damaged component of the vehicle in the loss image.
- CNN Convolutional Neural Network
- RPN Region Proposal Network
- the image recognition algorithm described above can select a similar model or algorithm.
- various models and variants based on convolutional neural networks and regional suggestion networks can be used, such as Faster R-CNN, YOLO, Mask-FCN, and the like.
- the convolutional neural network (CNN) can use any CNN model, such as ResNet, Inception, VGG, etc. and its variants.
- the preliminary damaged component described in this embodiment can be understood as data information such as the name, the type of damage, the degree of the damaged component outputted by the image recognition algorithm, and the preliminary damaged component is not yet combined. A list of accessories for the vehicle is subjected to further accessory identification processing.
- S4 Obtain a list of accessories of the vehicle, where the accessory list includes an accessory identification number corresponding to the vehicle accessory data.
- the vehicle identification code of the vehicle which is also called a VIN code (Vehicle Identification Number)
- VIN code Vehicle Identification Number
- the obtaining the accessory list of the vehicle may include:
- the acquired accessory list data information of the vehicle is queried using the vehicle identification code of the vehicle.
- the list of accessories generally includes detailed and comprehensive descriptions of the various accessories of the vehicle. Specifically, different configuration levels of the same vehicle may correspond to different accessory lists, different production years or months of the same model may correspond to different accessory lists, Or different displacements, manual/automatic transmissions, and even the same model of vehicles sold on the Internet and in physical stores can correspond to different parts lists, individual or company-specific vehicles with separate corresponding parts list.
- the accessory list may include accessory data of each accessory on the vehicle, such as the accessory name, model, specification, characteristics, etc.
- the accessory list further includes a component identification number corresponding to the vehicle accessory, and the accessory identification number may be
- the OE number of the accessory is usually the number of the spare parts of the model produced by the OEM (automaker). This number can be used to accurately purchase accessories in the market.
- the timing of acquiring the vehicle accessory list may include acquiring the vehicle identification code of the currently processed vehicle after obtaining the preliminary damaged component for the fixed-loss image recognition process, and then querying the vehicle accessory list according to the vehicle identification code. It is also possible to transmit a lossy image to a server or a server to obtain a list of vehicle accessories during the processing of the lossy image recognition.
- the preliminary damaged component is obtained by the image recognition algorithm, and then the accurate accessory identification number of the damaged component of the vehicle is output in combination with the acquired accessory list, and some embodiments of the present specification acquire the vehicle accessory list information.
- the timing is not limited.
- the manner in which the accessory list information is obtained may include an implementation obtained from an alliance party.
- the vehicle identification code of the currently processed vehicle Obtaining the vehicle identification code of the currently processed vehicle, and obtaining detailed and comprehensive vehicle configuration information corresponding to the vehicle according to the vehicle identification code of the vehicle. Further, the previously identified preliminary damaged components may be matched in the accessory list to inquire whether there is a vehicle accessory corresponding to the initially damaged component.
- the matching the preliminary damaged component in the accessory list determines that the preliminary damaged component corresponds to a vehicle accessory in the accessory list Can include:
- S60 Query whether there is a vehicle accessory in the accessory list that determines the characteristic attribute of the initially damaged component, and if so, the queried vehicle accessory is used as a vehicle accessory corresponding to the initially damaged component.
- the fixed damage image of the vehicle C1 can be acquired, and the preliminary damaged component obtained by the image recognition algorithm is a “bumper”. Then, the vehicle identification code VIN code of the vehicle C1 can be acquired as “WXXXXXX0512”, and the configuration table (accessory list) of the vehicle C1 can be acquired by the VIN code. Assuming that the vehicle C1 is in different configuration levels, the configuration of the bumper is different. For example, the bumper of the medium-high model has a trim strip, and the bumper of the high-profile model only has a bright silver ABS trim.
- the accessory data of the bumper of the vehicle C1 in the accessory list can be queried according to the accessory list of the vehicle C1: "Bumper: with bright silver ABS trim”.
- the vehicle accessory data "bumper: with bright silver ABS trim" in the queried accessory list can be used as the determined vehicle accessory corresponding to the initially damaged component.
- the attribute information may further include, for example, determining whether the front bumper is a three-stage or a single type, determining whether the headlight is a halogen lamp or a xenon lamp, whether the sub-driving door has a safety curtain, and the like.
- the embodiments provided in this manual can further confirm some personalized configuration information in the damaged parts from the parts list, and improve the final loss image. The accuracy of the identification of damaged parts.
- the initial damaged component is the front bumper, but the bumper of the corresponding model is divided into right and left front right bumper and right front bumper. Therefore, in another embodiment of the method of the present specification, after identifying the initially damaged component, if there is a plurality of classifications of the insured component in the corresponding accessory list, the initial output of the image recognition algorithm may be received. The image of the damaged component is again subjected to recognition processing to further identify one of the plurality of classifications to which the preliminary damaged component belongs in the accessory list. Specifically, the matching the preliminary damaged component in the accessory list to determine that the preliminary damaged component corresponds to the vehicle accessory in the accessory list may include:
- Some or all of the accessory information in the accessory list may be divided into different grades, and the vehicle parts of the different damaged parts may be divided from the accessory installation position, material, assembly, etc., including not only the classification of different positions.
- the left front bumper, the right front bumper, the upper and lower parts of a certain accessory, etc. in other embodiments, some different classifications of the preliminary damaged components may also include different models, different colors, classifications of different materials, and the like.
- the damage image corresponding to the preliminary damaged component may be identified again to determine the corresponding damaged component.
- the damage image corresponding to the preliminary damaged component may be re-entered into the image recognition algorithm described above, that is, the preliminary damaged component may be again used by an image recognition algorithm that identifies the initially damaged component.
- the corresponding fixed loss image is subjected to recognition processing.
- an image recognition algorithm different from the image algorithm for identifying the initially damaged component may be used for processing, for example, an algorithm for identifying the left and right position, material, color, etc.
- the fixed damage image with further different classifications in the accessory category of the preliminary damaged component can be combined with the vehicle accessory data for multiple or multiple ways of recognition processing, and the key recognition processing of such a fixed loss image can be further improved. A more accurate recognition result of damaged parts in the fixed loss image is obtained.
- FIG. 2 is a schematic flow chart of another embodiment of a method for improving a vehicle damage image recognition result provided by the present specification.
- the party may further include:
- the initial damaged component identified by the image recognition algorithm is a rear fender
- the rear fender assembly includes the rear fender, and in some implementations, the vehicle's accessory does not have a separate rear fender. If the rear fender is to be replaced, the entire rear fender assembly needs to be replaced. Accessories.
- the vehicle accessories included in the damaged parts of the mirror can be searched for the vehicle parts of the mirror housing.
- the vehicle accessory can be used as a damaged component of the vehicle.
- the accessory list generally includes the accessory identification number of the vehicle accessory.
- the accessory identification number of the vehicle accessory can be obtained by combining the accessory list.
- the accessory identification number can be used to accurately locate the accessory, facilitate market purchase or obtain market price, or feed back to the vehicle user or other related parties such as an insurance company in combination with other information, and the insurance company or the third party service platform can further identify the number based on the accessory.
- Accurate vehicle damage processing For example, the price data of the vehicle accessory is inquired by using the accessory identification number, or the fixed loss information of the vehicle or the like is further determined based on the price data of the inquired vehicle accessory.
- the damaged component of the vehicle C1 is determined to be “bumper: with a bright silver ABS trim” by the accessory list information, and the OE number of the accessory can be obtained (the OE number of the accessory is a component identification).
- the number type is F1DU-10300-AK, and the price of the accessory can be queried according to the OE number to the price library.
- FIG. 3 is a schematic diagram of a process flow of an implementation scenario of performing vehicle damage processing using the solution of the embodiment of the present specification.
- the client can send the fixed loss image to the server, and the server obtains the initially damaged component through the image recognition algorithm, and outputs the Chinese name of the initially damaged component.
- a list of accessories of the vehicle is obtained by combining the VIN code of the vehicle, and the preliminary damaged accessory is matched with the vehicle accessory in the accessory list to obtain a vehicle accessory corresponding to the preliminary damaged component.
- the vehicle accessory can then be converted to the corresponding OE number output.
- the output OE number can continue to be processed by the server, such as querying the price library, or sending it to a car insurance company or other third party service provider for loss processing.
- the processed terminal device may include a separate processing server, or may include an interactive implementation of an implementation with a server of another friend, or a related process in which the damaged component or accessory identification number identified by the server is sent to another server for loss determination.
- the method for improving the vehicle damage image recognition result can obtain the preliminary damaged component information through the image recognition algorithm, and obtain the preliminary damaged component in the accessory list by combining the vehicle accessory list. Precise vehicle part number.
- the fixed loss image is encoded by the algorithm and combined with the accessory list to output a more accurate part number, which can effectively improve the accuracy of the image recognition result and improve the image recognition accuracy.
- the implementation provided by the present specification can be combined with the accessory data identification information of the damaged accessory of the vehicle to be refined into the individual individual vehicle, and the output result is more accurate, which greatly facilitates the positioning/purchasing of the accessory and reduces the overall damage image.
- the recognition cost and learning period of the recognition algorithm greatly improve the efficiency and accuracy of the vehicle's fixed-loss image recognition processing.
- the present specification also provides an apparatus for improving the vehicle damage image recognition result.
- the apparatus may include a system (including a distributed system), software (applications), modules, components, servers, clients, quantum computers, etc., using the methods described in the embodiments of the present specification, in conjunction with necessary implementation hardware.
- the apparatus in one embodiment provided by this specification is as described in the following embodiments.
- the term "unit” or "module” may implement a combination of software and/or hardware of a predetermined function.
- FIG. 4 is a schematic diagram of a module structure of an apparatus for improving a vehicle damage image recognition result provided by the present specification. As shown in FIG. 4, the method may include:
- the algorithm processing module 101 may be configured to acquire a preliminary damaged component of the vehicle, where the preliminary damaged component includes performing a recognition process on the fixed-loss image by using a preset image recognition algorithm to obtain a damaged component of the vehicle;
- the accessory list processing module 102 may be configured to obtain a list of accessories of the vehicle, and convert the vehicle accessory data in the accessory list into a corresponding accessory identification number;
- the matching module 103 can be configured to match the preliminary damaged component in the accessory list, and determine that the preliminary damaged component corresponds to a vehicle accessory in the accessory list;
- the recognition result output module 104 can be configured to output the matched accessory identification number of the vehicle accessory.
- the parts can be accurately positioned to facilitate market purchase or market price, or combined with other information to feedback to vehicle users or other related parties such as insurance companies, insurance companies or
- the tripartite service platform can perform vehicle damage processing more accurately based on the accessory identification number.
- the accessory list acquired in the accessory list processing module 102 may include: the accessory list data information of the vehicle acquired by using the vehicle identification code of the vehicle.
- the matching module 103 may include:
- the feature accessory module 1031 may be configured to query whether there is a vehicle accessory in the accessory list that determines the characteristic attribute of the initially damaged component, and if so, the queried vehicle accessory is used as a vehicle corresponding to the initially damaged component Accessories.
- the matching module 103 includes:
- the re-identification module 1032 may be configured to: if there is at least two sub-assembly classifications of the preliminary damaged component in the accessory list, perform re-identification processing on the damage-reduced image corresponding to the preliminary damaged component Until the unique vehicle accessory corresponding to the preliminary damaged component is determined in the sub-assembly classification, or the upper limit of the number of recognition processing of the fixed-loss image is reached.
- the specific re-identification module 1032 may re-enter the fixed-loss image corresponding to the preliminary damaged component into the algorithm processing module 101, and use the image recognition algorithm that identifies the initially damaged component to again correspond to the preliminary damaged component.
- the fixed loss image is subjected to recognition processing.
- an image recognition algorithm different from the image algorithm for identifying the initially damaged component may be used, for example, an algorithm for identifying processing of the left and right position, material, color, and the like of the component.
- the dashed lines in Figure 5 indicate embodiments that are communicable in other embodiments.
- Figure 6 is a block diagram showing the structure of another embodiment of the apparatus provided in the present specification. As shown in Figure 6, in another embodiment of the apparatus, the apparatus may further include:
- the relationship accessory matching module 105 can be configured to find, in the accessory list, a vehicle having a component inclusion relationship with the preliminary damaged component when the vehicle accessory corresponding to the preliminary damaged component is not matched in the accessory list An accessory, and the found vehicle accessory as the vehicle component of the preliminary damaged component corresponding to the accessory list.
- the method for improving the vehicle damage image recognition result provided by the embodiment of the present specification may be implemented by a processor executing a corresponding program instruction in a computer, such as using a C++ language of a Windows operating system on a PC side, or other such as Linux, android, The necessary hardware implementation of the application design language set corresponding to the iOS system, and the processing logic implementation based on quantum computers.
- the apparatus may include a processor and a memory for storing processor executable instructions, where the processor executes When the instruction is implemented:
- the preliminary damaged component comprising: performing a recognition process on the fixed loss image by using a preset image recognition algorithm to obtain a damaged component of the vehicle;
- the matching component identification number of the vehicle accessory is output.
- the device for improving the image recognition result of the vehicle damage is provided by the embodiment of the present specification, and the information of the preliminary damaged component can be obtained by the image recognition algorithm, and the accessory list of the preliminary damaged component is obtained by combining the accessory list of the vehicle. More accurate vehicle part number.
- the accuracy of the image recognition result can be effectively improved, and the image recognition accuracy can be improved.
- the implementation provided by the present specification can be combined with the accessory data identification information of the damaged accessory of the vehicle to be refined into the individual individual vehicle, and the output result is more accurate, which greatly facilitates the positioning/purchasing of the accessory and reduces the overall damage image.
- the recognition cost and learning period of the recognition algorithm greatly improve the efficiency and accuracy of the vehicle's fixed-loss image recognition processing.
- the device or method described above can be used in various electronic devices to improve the image recognition result of the vehicle, and can improve the accuracy of the image recognition result, reduce the learning cost and cycle of the server algorithm, and output accurate for the user. Damaged component information to enhance the user experience.
- the server may include at least one processor and a memory storing processor executable instructions, and the memory may be a volatile memory or a nonvolatile memory.
- a computer storage medium of a memory that, when executed by the processor, can:
- the preliminary damaged component comprising: performing a recognition process on the fixed loss image by using a preset image recognition algorithm to obtain a damaged component of the vehicle;
- the matching component identification number of the vehicle accessory is output.
- the specific structure of the server may further include other processing hardware, such as a GPU (Graphics Processing Uni), a bus, and the like.
- processing hardware such as a GPU (Graphics Processing Uni), a bus, and the like.
- the computer readable storage medium may include physical means for storing information, which may be digitized and stored in a medium utilizing electrical, magnetic or optical means.
- the computer readable storage medium of this embodiment may include: means for storing information by means of electrical energy, such as various types of memories, such as RAM, ROM, etc.; means for storing information by magnetic energy means, such as hard disk, floppy disk, magnetic tape, magnetic Core memory, bubble memory, U disk; means for optically storing information such as CD or DVD.
- electrical energy such as various types of memories, such as RAM, ROM, etc.
- magnetic energy means such as hard disk, floppy disk, magnetic tape, magnetic Core memory, bubble memory, U disk
- means for optically storing information such as CD or DVD.
- quantum memories graphene memories, and the like.
- server may further include other embodiments according to the description of the method or the device embodiment.
- reference may be made to the description of the method embodiments, and details are not described herein.
- a method, device, and server for improving a vehicle damage image recognition result may obtain the information of a preliminary damaged component by using an image recognition algorithm, and obtain the A more accurate vehicle part number for the initial damaged part in the parts list.
- the fixed loss image is encoded by the algorithm and combined with the accessory list to output a more accurate part number, which can effectively improve the accuracy of the image recognition result and improve the image recognition accuracy.
- the implementation provided by the present specification can be combined with the accessory data identification information of the damaged accessory of the vehicle to be refined into the individual individual vehicle, and the output result is more accurate, which greatly facilitates the positioning/purchasing of the accessory and reduces the overall damage image.
- the recognition cost and learning period of the recognition algorithm greatly improve the efficiency and accuracy of the vehicle's fixed-loss image recognition processing.
- embodiments of the present specification refers to the algorithm for identifying the initially damaged component, the hierarchical division of the accessory list, the re-recognition processing of the damaged image, the inquiry of the accessory price by using the accessory identification number, and the like, the image recognition, acquisition, and the like are performed by the algorithm of the CNN network.
- Descriptions of interactions, calculations, judgments, etc. are not limited to situations that must conform to industry communication standards, standard image data processing protocols, network models, computer processing, and database rules or embodiments of the present specification.
- Certain industry standards or implementations that have been modified in a manner that uses a custom approach or an embodiment described above may also achieve the same, equivalent, or similar, or post-deformation implementation effects of the above-described embodiments.
- Embodiments obtained by applying such modified or modified data acquisition, storage, judgment, processing, etc. may still fall within the scope of alternative embodiments of the present specification.
- PLD Programmable Logic Device
- FPGA Field Programmable Gate Array
- HDL Hardware Description Language
- the controller can be implemented in any suitable manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (eg, software or firmware) executable by the (micro)processor.
- computer readable program code eg, software or firmware
- examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic.
- the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding.
- Such a controller can therefore be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component.
- a device for implementing various functions can be considered as a software module that can be both a method of implementation and a structure within a hardware component.
- the system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function.
- a typical implementation device is a computer.
- the computer can be, for example, a personal computer, a laptop computer, a car-mounted human-machine interaction device, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet.
- the above devices are described as being separately divided into various modules by function.
- the functions of the modules may be implemented in the same software or software, or the modules that implement the same function may be implemented by multiple sub-modules or a combination of sub-units.
- the device embodiments described above are merely illustrative.
- the division of the unit is only a logical function division.
- there may be another division manner for example, multiple units or components may be combined or integrated. Go to another system, or some features can be ignored or not executed.
- the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
- the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding.
- the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
- the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
- These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
- the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
- a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
- processors CPUs
- input/output interfaces network interfaces
- memory volatile and non-volatile memory
- the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
- RAM random access memory
- ROM read only memory
- Memory is an example of a computer readable medium.
- Computer readable media includes both permanent and non-persistent, removable and non-removable media.
- Information storage can be implemented by any method or technology.
- the information can be computer readable instructions, data structures, modules of programs, or other data.
- Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
- computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
- embodiments of the present specification can be provided as a method, system, or computer program product.
- embodiments of the present specification can take the form of an entirely hardware embodiment, an entirely software embodiment or a combination of software and hardware.
- embodiments of the present specification can take the form of a computer program product embodied on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
- Embodiments of the present description can be described in the general context of computer-executable instructions executed by a computer, such as a program module.
- program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types.
- Embodiments of the present specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network.
- program modules can be located in both local and remote computer storage media including storage devices.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Multimedia (AREA)
- Technology Law (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
本说明书实施例公开了一种提升车辆定损图像识别结果的方法、装置及服务器。所述方法包括：获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；获取所述车辆的配件列表，所述配件列表中包括车辆配件数据对应的配件识别编号；将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；输出匹配到的所述车辆配件的配件识别编号。定损车辆的配件列表信息与图像识别结合起来可以明显提升定损图像识别受损部件识别结果的准确度，大大降低图像识别算法/模型额外的学习成本和周期。
Description
本说明书实施例方案属于车辆定损图像数据处理的技术领域，尤其涉及一种提升车辆定损图像识别结果的方法、装置及服务器。
随着车辆保有量的逐年增加，各保险公司的车险业务量也随之增加。如何快速、准确的为用户提供车辆定损服务是目前各车型行业重点研究的方向。
在对车辆定损处理时通常需要通过对定损图像的识别来确定车辆的受损部件，而受损部件识别的准确度主要依赖对定损图像进行识别的算法/模型，通过各种模型/算法对车辆损失的图像(包含图片和视频等影像资料)进行识别，获得损伤部位和程度，然后根据相应的维修策略得到定损结果。目前业内所使用的模型/算法主要是预先收集各种车型的外观数据进行学习，然后利用构建的车辆配件损伤算法识别定损图像中的损伤部件和损伤程度。为了保障识别精度，通常尽可能多的获取各种车辆的外观图像数据作为样本图像进行训练，而且模型算法的训练和参数优化过程周期通常较长，整体实现成本较大。并且单纯的依赖模型算法识别图像中的受损部件，其部件识别的准确性也会受限于收集车辆外观图像数据的多少。因此，在车辆图定损图像识别的处理中，还需要一种实施成本更低、识别结果更加准确的处理方案。
发明内容
本说明书实施例目的在于提供一种提升车辆定损图像识别结果的方法、装置及服务器，可以有效提高车辆定损图像识别结果的精度和识别效率，降低整体图像算法识别周期和成本。
本说明书实施例提供的一种提升车辆定损图像识别结果的方法、装置及服务器是包括以下方式实现的：
一种提升车辆定损图像识别结果的方法，所述方法包括：
获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；
获取所述车辆的配件列表，所述配件列表中包括车辆配件数据对应的配件识别编号；
将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；
输出匹配到的所述车辆配件的配件识别编号。
一种提升车辆定损图像识别结果的装置，所述装置包括：
算法处理模块，用于获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；
配件列表处理模块，用于获取所述车辆的配件列表，将所述配件列表中的车辆配件数据转换为相应的配件识别编号；
匹配模块，用于将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；
识别结果输出模块，用于输出匹配到的所述车辆配件的配件识别编号。
一种提升车辆定损图像识别结果的装置，包括处理器以及用于存储处理器可执行指令的存储器，所述处理器执行所述指令时实现：
获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；
获取所述车辆的配件列表，将所述配件列表中的车辆配件数据转换为相应的配件识别编号；
将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；
输出匹配到的所述车辆配件的配件识别编号。
一种服务器，包括至少一个处理器和存储处理器可执行指令的存储器，所述处理器执行所述指令时实现：
获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；
获取所述车辆的配件列表，将所述配件列表中的车辆配件数据转换为相应的配件识别编号；
将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；
输出匹配到的所述车辆配件的配件识别编号。
本说明书实施例提供的一种提升车辆定损图像识别结果的方法、装置及服务器，可以通过图像的识别算法得到初步的受损部件的信息后，结合车辆的配件列表得到所述初步受损部件的在配件列表中更加精确的车辆配件编号。对定损图像通过算法识别后结合配件列表输出更加准确的配件编号，可以有效提升图像识别结果的准确性，提高图像识别精度。本说明书提供的实施方案，可以结合细化到单个个体车辆的配件数据信息输出车辆的受损配件的配件识别编号，输出结果更加精准，极大的利于配件定位/采购，降低了整体定损图像识别算法的识别成本和学习周期，大大提高了车辆定损图像识别处理的效率和准确性。
为了更清楚地说明本说明书实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本说明书中记载的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本说明书所述一种提升车辆定损图像识别结果的方法实施例的流程示意图；
图2是本说明书提供的另一种提升车辆定损图像识别结果的方法实施例的流程示意图；
图3是利用本说明书实施例方案进行定损图像处理的一个实施场景的处理 流程示意图；
图4是本说明书提供的一种提升车辆定损图像识别结果装置实施例的模块结构示意图；
图5是本说明书提供的所述装置另一个实施例的模块结构示意图；
图6是本说明书提供的所述装置另一个实施例的模块结构示意图；
图7是本说明书提供的所述服务器的一个实施例的结构示意图。
为了使本技术领域的人员更好地理解本说明书中的技术方案，下面将结合本说明书实施例中的附图，对本说明书实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本说明书中的一部分实施例，而不是全部的实施例。基于本说明书中的一个或多个实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都应当属于本说明书实施例保护的范围。
现有中车辆的划分多种多样，即使是同一车型，也常常会因不同年出厂时间、不同配置(如高、中、低配置)，甚至与厂商的个性化定制等因素，使得同一车型的同一部位的部件可能存在较大差异，甚至是完整不同的配件。例如，同一款车型的保险杠中，舒适性配置的前保险杠为整体式，而豪华型配置的前保险杠为三段式。或者，中配车型的保险杠上有饰条，而低配车型的保险杠上无饰条。现有的单纯依赖图像识别技术对车辆受损部位进行识别的处理方案难以上述差异的识别或者需要成本更高、学习周期更长的图像识别算法和样本数据。当前汽车制造越来越标准化，获取车辆的配件识别编号(也可以称为配件OE号，指车辆制造商对其生产车型的零配件的编号。)，便可以在市场上精准的采购配件。虽然车型有差异，但通常制造商都会保留有每个出厂的车辆的配置信息。因此，本说明书中一个或多个实施例提供的实施方案，可以利用车辆唯一的车辆识别码获取定损车辆的配件列表信息，然后与图像识别算法结合起来，可以明显提升定损图像算法识别受损部件结果的准确度，大大降低图像识 别算法/模型额外的学习成本和学习周期。
本说明书实施例提供的提升车辆定损图像识别结果的方法，可以在利用图像识别算法初步获取车辆的受损部件后，再获取当前处理车辆的配件列表，基于所述配件列表进一步确定受损部件对应在配件列表中的配件信息。例如，当通过图像识别模型识别出受损部件是保险杠时，则可以根据车辆识别码得知是哪种车型配置的保险杠(假设不同配置的车型的保险杠是有差别的)，例如保险杠外是否有饰条等。然后可以将受损部件对应在配件列表中的车辆配件作为识别出的车辆的受损部件，例如受损部件为“带有熏黑色尾灯”或者“保险杠：亮银色ABS电镀饰条”等。同时可以根据所述配件列表获取所述车辆配件的配件识别编号，该配件识别编号可以用于精确采购，或者结合其他信息反馈给车辆用户或保险公司等其他关联方，以基于该配件识别编号可以更加精确的进行车辆定损的相关处理。
具体的，图1是本说明书提供的所述一种提升车辆定损图像识别结果的方法实施例的流程示意图。虽然本说明书提供了如下述实施例或附图所示的方法操作步骤或装置结构，但基于常规或者无需创造性的劳动在所述方法或装置中可以包括更多或者部分合并后更少的操作步骤或模块单元。在逻辑性上不存在必要因果关系的步骤或结构中，这些步骤的执行顺序或装置的模块结构不限于本说明书实施例或附图所示的执行顺序或模块结构。所述的方法或模块结构的在实际中的装置、服务器或终端产品应用时，可以按照实施例或者附图所示的方法或模块结构进行顺序执行或者并行执行(例如并行处理器或者多线程处理的环境、甚至包括分布式处理、服务器集群的实施环境)。
本说明书实施例提供的方法可以用于车辆定损图像识别处理的服务器、现场拍照进行定损图像处理的客户端(如安装有定损服务应用的移动终端)或其他电子设备中，可以实现对定损图像的识别处理，并可以结合车辆的配件列表得到车辆准确的受损部件的配件识别编号。具体的一个示例中可以以服务器一侧的处理为实施场景进行说明，如图1所示，本说明书提供的一种提升车辆定损图像识别结果的方法的实施例中，所述方法可以包括：
S2：获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件。
服务器可以获取车辆的定损图像，具体的可以包括移动终端现场拍摄传输给服务器的图像的获取方式，也可以包括从移动存储设备、远程存储设备或其他第三方服务平台获取的图像。本说明书实施中所描述图像可以为各种图形和影像的总称，通常指具有视觉效果的画面，一般可以包括纸介质上的、底片或照片上的、电视、投影仪或计算机屏幕上的画面。在本实施例中，所述的定损图像具体的可以包括单张拍摄获取的车辆图片或者拍摄的视频(一段视频可以视为连续图像的集合)。服务器可以利用车辆的定损图像进行识别处理，确定所述定损图像中的受损部件和受损程度，具体的服务器可以输出初步受损部件的名称、受损程度的相关数据，如初步受损部件的中文标签，受损程度的类型(轻微、严重等)或分值(50％、80％等。)
在本实施例中，可以预先采用设计的图像识别算法构建用于识别定损图像中车辆受损部件的部件损伤识别模型。该部件损伤识别模型经过前期的样本训练后，可以识别出所述部件图像中车辆配件的损伤部位和损伤类型。本实施例中，所述的图像识别算法可以包括采用深度神经网络的一些网络模型算法以及变种，经过样本训练后构建生成的部件受损识别模型的处理算法。具体的一个示例中，可以基于卷积神经网络Convolutional Neural Network，CNN)和区域建议网络(Region Proposal Network，RPN)，结合池化层、全连接层等构建图像识别的算法模型，服务器获取定损图像后，可以利用该算法模型对所述定损图像进行识别，识别出定损图像中所述车辆的初步受损部件。
上述所述的图像识别算法可以选择同类模型或者算法。例如，可以使用基于卷积神经网络和区域建议网络的多种模型和变种，如Faster R-CNN、YOLO、Mask-FCN等。其中的卷积神经网络(CNN)可以用任意CNN模型，如ResNet、Inception,VGG等及其变种。本实施例中所述的初步受损部件可以理解为通过图像识别算法进行处理后输出的受损部件的名称、受损类型、程度等数据信息，此时的所述初步受损部件还未结合车辆的配件列表进行进一步的配件识别处 理。
S4：获取所述车辆的配件列表，所述配件列表中包括车辆配件数据对应的配件识别编号。
上述中通过图像识别算法得到的初步受损部件的信息常常会出现识别出了是某个车型的部件，如保险杠、前车门、尾灯等，但由于不同配置的车型在一些部件上存在差异或者外观、形状有较大差异。因此，本说明书实施例提供的实施方案中，可以根据当前处理的车辆的关联信息(如车主身份信息)得到所述车辆的车辆识别码，也称为VIN码(Vehicle Identification Number，车辆识别码)，它是每辆车唯一的识别标识。然后根据所述车辆识别码获取当前处理车辆的配件列表。因此，一种实施例中，所述获取所述车辆的配件列表可以包括：
利用所述车辆的车辆识别码查询获取的所述车辆的配件列表数据信息。
所述的配件列表通常包括了详细和全面描述了车辆的各个配件的信息，具体的，同一车型不同配置级别可以对应不同的配件列表、同一车型不同的生产年份或月份可以对应不同的配件列表，或者不同排量、手动/自动变速箱，甚至网上和实体店出售的同一型号的车辆都可以对应不同的配件列表、个人或公司等专门定制的车辆有单独对应的配件列表等情况。
所述配件列表中可以包括该车辆上各个配件的配件数据，如配件名称、型号、规格、特性等，一般的，配件列表中还包括了车辆配件对应的配件识别编号，该配件识别编号可以为配件OE号，通常是指主机厂(整车厂)对其生产车型的零配件的编号，该编号可以在市场上精准采购配件。
需要说明的是，所述获取车辆配件列表的时机可以包括在对定损图像识别处理得到初步受损部件之后再去获取当前处理车辆的车辆识别码，然后根据车辆识别码查询到车辆配件列表。也可以定损图像传输给服务器或者服务器在定损图像识别的处理过程中获取得到车辆配件列表。在本说明书实施例中，通过图像识别算法获得初步受损部件，然后结合获取的配件列表输出准确的车辆受损部件的配件识别编号，本说明书的一些实施例对所述车辆配件列表信息的获取时机不做限定。另外，所述配件列表信息的获取方式可以包括从友盟方获取 的实施方式。
S6：将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件。
获取当前处理车辆的车辆识别码，可以根据该车辆的车辆识别码获取车辆对应的详细、全面的车辆配置信息。进一步的，可以将前述识别到的初步受损部件在所述配件列表中进行匹配，查询是否有与所述初步受损部件对应的车辆配件。
具体的根据配件列表确定查询所述初步受损部件对应的车辆配件时，如果配件列表中有进一步表示该初步受损部件的其他特征属性的信息，例如初步受损部件具体的规格、是否包含其他配饰等与同车型的其他车辆的区别特征。如果有这样的特征属性，则可以将配件列表中对应的配件信息替换为所述初步受损部件，即将所述识别出的配件列表中的车辆配件作为与所述初步受损部件对应的车辆配件。因此，本说明书提供的所述方法的另一个实施例中，所述将所述初步受损部件在所述配件列表中进行匹配确定所述初步受损部件对应在所述配件列表中的车辆配件可以包括：
S60：查询所述配件列表中是否有确定所述初步受损部件特征属性的车辆配件，若有，则将查询到的车辆配件作为与所述初步受损部件对应的车辆配件。
具体的一个示例中，可以获取车辆C1的定损图像，通过图像识别算法得到的初步受损部件为“保险杠”。然后可以获取车辆C1的车辆识别码VIN码为“WXXXXXXX0512”，通过该VIN码可以获取该车辆C1的配置表(配件列表)。假设车辆C1在不同配置级别中，保险杠的配置是有区别的，例如中高配车型的保险杠带有饰条，并仅高配车型的保险杠带有的是亮银色ABS饰条。通过定损图像识别得到的初步受损部件为“保险杠”后，可以根据该车辆C1的配件列表查询到该车辆C1的保险杠在配件列表中的配件数据是“保险杠：带有亮银色ABS饰条”。此时可以将查询到的配件列表中的车辆配件数据“保险杠：带有亮银色ABS饰条”作为确定的与所述初步受损部件对应的车辆配件。
当然，其他的示例中，所述的属性信息还可以包括例如确定前保险杠是三 段式还是整体式、确定大灯是卤素灯还是氙气灯、副驾车门是否带有安全气帘等。当不同配置、不同批次的同一款车型的受损部件存在差异时，利用本说明书提供的实施例则可以从配件列表中进一步确认受损部件中的一些个性化配置信息，提高定损图像最终受损部件的识别精度。
另一个实施场景中，所述的配件列表中除了可以有进一步确定所述初步识别配件其他特征数的信息，对于一些部件而言，车辆配置中还存在不同配置位置的多级分类。例如识别出初步受损部件是前保险杠，但对应车型的保险杠是分左右的，右左前保险杠、右前保险杠。因此，本说明书所述方法的另一个实施例中，在识别出初步受损部件后，若对应的配件列表中存在多个该受保部件的分类，则可以将前述图像识别算法输出的初步受损部件的图像再次进行识别处理，进一步识别出该初步受损部件在所述配件列表中所属多个分类中的一个。具体的，所述将所述初步受损部件在所述配件列表中进行匹配确定所述初步受损部件对应在所述配件列表中的车辆配件可以包括：
S61：若在所述配件列表中存在至少两个所述初步受损部件的子级配件分类时，则对所述初步受损部件所对应的定损图像再次进行识别处理，直至在所述子级配件分类中确定出所述初步受损部件对应的唯一车辆配件，或达到定损图像的识别处理次数上限。
所述的配件列表中的部分或全部配件信息可以划分为不同的分级，可以从配件安装位置、材料、总成等划分所述的初步受损部件不同分类的车辆配件，不仅包括不同位置的分类，如左前保险杠、右前保险杠，某个配件的上下之分等，其他的实施例中，一些所述初步受损部件的不同分类也可以包括不同型号、不同颜色、不同材质的分类等。
当前述图像识别算法的处理过程中未能识别出车辆在这种不同分类上的区别时，可以将所述初步受损部件所对应的定损图像再次进行识别，以确定该初步受损部件对应在所述配件列表中的车辆配件。一种实施方式中，可以将所述初步受损部件所对应的定损图像再次输入前述所述的图像识别算法，即可以采用识别初步受损部件的图像识别算法再次对所述初步受损部件对应的定损图像 进行识别处理。当然，再次识别处理时也可以根据需求进行一些参数的调整。其他的实施方式中，也可以采用与所述识别初步受损部件的图像算法不同的图像识别算法进行处理，例如针对部件左右位置、材质、颜色等识别处理的算法，具体的可以根据配件列表中同一配件类型的不同位置、材质、颜色等分类进行相应的算法设置。这样，可以结合车辆配件数据对所述初步受损部件在配件类别中有进一步不同分类的定损图像做多次或多种方式的识别处理，对此类定损图像进行重点识别处理，可以更加得到更加准确的定损图像中受损部件的识别结果。
图2是本说明书提供的另一种提升车辆定损图像识别结果的方法实施例的流程示意图。另一种实施方式中，如果配件类别中没有匹配到受损部件对应的车辆配件，例如定损图像重新识别后也无法查找到，或者基于当前受损部件的名称或部件的分类级别找不到配件列表中对应的车辆配件，则可以表示配件列表中没有该类型的初步受损部件。则此时可以在所述配件列表中向上一级或下一级查找与所述受损部件存在包含关系的配件。具体的，本说明书所述方法的另一个实施例中，所述方还可以包括：
S70：若在所述配件列表中未匹配到所述初步受损部件对应的车辆配件，则在所述配件列表中查找与所述初步受损部件有配件包含关系的车辆配件，并以查找到的车辆配件作为所述初步受损部件对应在所述配件列表中的车辆配件。
具体的一个示例中，例如，通过图像识别算法识别出的初步受损部件为后翼子板，在配件列表中找不到后翼子板时，可以查找后翼子板总成，所述的后翼子板总成包含所述后翼子板，在一些实施场景中，车辆的配件没有单独的后翼子板，如果要更换后翼子板，则需要更换整个后翼子板总成的配件。类似的，找不到倒车镜时，则可以向倒车镜受损部件所包括的车辆配件进行查找，找倒车镜壳的车辆配件。
S8：输出匹配到的所述车辆配件的配件识别编号。
当确定所述车辆对应在所述配件列表中的车辆配件后，可以将该车辆配件作为所述车辆的受损部件。所述的配件列表中通常包括车辆配件的配件识别编 号，本实施例中可以结合配件列表获取车辆配件的配件识别编号。所述配件识别编号可以用于精确定位配件，便于市场采购或获取市场价格，或者结合其他信息反馈给车辆用户或保险公司等其他关联方，保险公司或第三方服务平台可以基于该配件识别编号更加精确的进行车辆定损处理。例如利用所述配件识别编号查询所述车辆配件的价格数据，或者进一步的基于查询到的车辆配件的价格数据确定所述车辆的定损信息等。
具体的一个示例中，例如通过配件列表信息确定车辆C1的受损部件为“保险杠：带有亮银色ABS饰条”，同时可以获取该配件的OE号(配件的OE号是一种配件识别编号类型)为F1DU-10300-AK，可以根据该OE号到价格库中查询该配件的价格。
图3是利用本说明书实施例方案进行车辆定损处理的一个实施场景的处理流程示意图。客户端可以将定损图像发送给服务器，服务器通过图像识别算法得到初步受损部件，输出初步受损部件的中文名。然后结合车辆的VIN码得到该车辆的配件列表，将所述初步受损配件与配件列表中的车辆配件进行匹配，得到所述初步受损部件对应的车辆配件。然后可以将车辆配件转换为相应的OE号输出。输出的OE号可以继续由服务器进行处理，例如查询价格库，也可以发送给车险公司或其他第三方服务方进行定损处理。
本领域技术人员能够理解到，可以将本说明书实施例提供方案的应用到多种车辆定损的实施场景中，如保险公司或修理厂的车辆定损，或者4S门店、云服务器提供的车辆定损服务，或者服务器或客户端应用提供的定损图像识别处理。处理的终端设备可以包括单独的处理服务器，也可以包括与其他友商的服务器交互通信完成实施方案，或者服务器识别的受损部件或配件识别编号发送给另一个服务器进行定损的相关处理。
本说明书实施例提供的提升车辆定损图像识别结果的方法，可以通过图像的识别算法得到初步的受损部件的信息后，结合车辆的配件列表得到所述初步受损部件的在配件列表中更加精确的车辆配件编号。对定损图像通过算法识别后结合配件列表输出更加准确的配件编号，可以有效提升图像识别结果的准确 性，提高图像识别精度。本说明书提供的实施方案，可以结合细化到单个个体车辆的配件数据信息输出车辆的受损配件的配件识别编号，输出结果更加精准，极大的利于配件定位/采购，降低了整体定损图像识别算法的识别成本和学习周期，大大提高了车辆定损图像识别处理的效率和准确性。
基于上述所述的提升车辆定损图像识别结果的方法，本说明书还提供一种提升车辆定损图像识别结果的装置。所述的装置可以包括使用了本说明书实施例所述方法的系统(包括分布式系统)、软件(应用)、模块、组件、服务器、客户端、量子计算机等并结合必要的实施硬件的装置。基于同一创新构思，本说明书提供的一种实施例中的装置如下面的实施例所述。由于装置解决问题的实现方案与方法相似，因此本说明书实施例具体的装置的实施可以参见前述方法的实施，重复之处不再赘述。以下所使用的，术语“单元”或者“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。具体的，图4是本说明书提供的一种提升车辆定损图像识别结果的装置实施例的模块结构示意图，如图4所示，可以包括：
算法处理模块101，可以用于获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；
配件列表处理模块102，可以用于获取所述车辆的配件列表，将所述配件列表中的车辆配件数据转换为相应的配件识别编号；
匹配模块103，可以用于将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；
识别结果输出模块104，可以用于输出匹配到的所述车辆配件的配件识别编号。
确定车辆的受损部件并获得该受损部件的配件识别编号，可以精确定位配件，便于市场采购或获取市场价格，或者结合其他信息反馈给车辆用户或保险公司等其他关联方，保险公司或第三方服务平台可以基于该配件识别编号更加 精确的进行车辆定损处理。所述装置的另一个实施例中，所述配件列表处理模块102中获取的配件列表可以包括：利用所述车辆的车辆识别码查询获取的所述车辆的配件列表数据信息。
所述装置另一个实施例中，所述匹配模块103可以包括：
特征配件模块1031，可以用于查询所述配件列表中是否有确定所述初步受损部件特征属性的车辆配件，若有，则将查询到的车辆配件作为与所述初步受损部件对应的车辆配件。
图5是本说明书提供的所述装置另一个实施例的模块结构示意图，如图5所示，所述装置的另一个实施例中，所述匹配模块103包括：
重识别模块1032，可以用于若在所述配件列表中存在至少两个所述初步受损部件的子级配件分类时，则对所述初步受损部件所对应的定损图像再次进行识别处理，直至在所述子级配件分类中确定出所述初步受损部件对应的唯一车辆配件，或达到定损图像的识别处理次数上限。
具体的所述重识别模块1032可以将所述初步受损部件所对应的定损图像再次输入算法处理模块101中，采用识别初步受损部件的图像识别算法再次对所述初步受损部件对应的定损图像进行识别处理。其他的实施方式中，也可以采用与所述识别初步受损部件的图像算法不同的图像识别算法进行处理，例如针对部件左右位置、材质、颜色等识别处理的算法。图5中虚线表示在其他的实施例中可以连通的实施方式。
图6是本说明书提供的所述装置另一个实施例的模块结构示意图，如图6所示，所述装置的另一个实施例中，所述装置还可以包括：
关系配件匹配模块105，可以用于在所述配件列表中未匹配到所述初步受损部件对应的车辆配件时，在所述配件列表中查找与所述初步受损部件有配件包含关系的车辆配件，并以查找到的车辆配件作为所述初步受损部件对应在所述配件列表中的车辆配件。
本说明书实施例提供的提升车辆定损图像识别结果的方法可以在计算机中由处理器执行相应的程序指令来实现，如使用windows操作系统的c++语言在 PC端实现，或其他例如Linux、android、iOS系统相对应的应用设计语言集合必要的硬件实现，以及基于量子计算机的处理逻辑实现等。具体的，本说明书提供的一种提升车辆定损图像识别结果的装置的一种实施例中，所述装置可以包括处理器以及用于存储处理器可执行指令的存储器，所述处理器执行所述指令时实现：
获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；
获取所述车辆的配件列表，将所述配件列表中的车辆配件数据转换为相应的配件识别编号；
将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；
输出匹配到的所述车辆配件的配件识别编号。
需要说明的是，本说明书实施例上述所述的装置根据相关方法实施例的描述还可以包括其他的实施方式，具体的实现方式可以参照方法实施例的描述，在此不作一一赘述。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于硬件+程序类实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
上述对本说明书特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。
本说明书实施例提供的一种提升车辆定损图像识别结果的装置，可以通过图像的识别算法得到初步的受损部件的信息后，结合车辆的配件列表得到所述初步受损部件的在配件列表中更加精确的车辆配件编号。对定损图像通过算法 识别后结合配件列表输出更加准确的配件编号，可以有效提升图像识别结果的准确性，提高图像识别精度。本说明书提供的实施方案，可以结合细化到单个个体车辆的配件数据信息输出车辆的受损配件的配件识别编号，输出结果更加精准，极大的利于配件定位/采购，降低了整体定损图像识别算法的识别成本和学习周期，大大提高了车辆定损图像识别处理的效率和准确性。
上述所述的装置或方法可以用于各种电子设备中，实现对提升车辆定损图像识别结果的，可以提升图像识别结果的准确性，降低了服务器算法学习成本和周期，为用户输出精准的受损部件信息，提升用户体验。图7是本说明书提供的服务器的一个实施例的结构示意图，所述的服务器可以包括至少一个处理器和存储处理器可执行指令的存储器，所述的存储器可以为易失性存储器或非易失性存储器的计算机存储介质，所述处理器执行所述指令时可以实现：
获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；
获取所述车辆的配件列表，将所述配件列表中的车辆配件数据转换为相应的配件识别编号；
将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；
输出匹配到的所述车辆配件的配件识别编号。
上述所述服务器具体的结构中，还可以包括其他的处理硬件，例如GPU(Graphics Processing Uni，图形处理单元)、总线等。
所述计算机可读存储介质可以包括用于存储信息的物理装置，可以将信息数字化后再以利用电、磁或者光学等方式的媒体加以存储。本实施例所述的计算机可读存储介质有可以包括：利用电能方式存储信息的装置如，各式存储器，如RAM、ROM等；利用磁能方式存储信息的装置如，硬盘、软盘、磁带、磁芯存储器、磁泡存储器、U盘；利用光学方式存储信息的装置如，CD或DVD。当然，还有其他方式的可读存储介质，例如量子存储器、石墨烯存储器等等。
需要说明的，上述所述的服务器根据方法或装置实施例的描述还可以包括 其他的实施方式，具体的实现方式可以参照方法实施例的描述，在此不作一一赘述。
本说明书一个或多个实施例提供的一种提升车辆定损图像识别结果的方法、装置及服务器，可以通过图像的识别算法得到初步的受损部件的信息后，结合车辆的配件列表得到所述初步受损部件的在配件列表中更加精确的车辆配件编号。对定损图像通过算法识别后结合配件列表输出更加准确的配件编号，可以有效提升图像识别结果的准确性，提高图像识别精度。本说明书提供的实施方案，可以结合细化到单个个体车辆的配件数据信息输出车辆的受损配件的配件识别编号，输出结果更加精准，极大的利于配件定位/采购，降低了整体定损图像识别算法的识别成本和学习周期，大大提高了车辆定损图像识别处理的效率和准确性。
尽管本说明书实施例内容中提到通过CNN网络的算法识别初步受损部件、配件列表的分级划分、受损图像的再次识别处理、利用配件识别编号查询配件价格等之类的图像识别、获取、交互、计算、判断等描述，但是，本说明书实施例并不局限于必须是符合行业通信标准、标准图像数据处理协议、网络模型、计算机处理和数据库规则或本说明书实施例所描述的情况。某些行业标准或者使用自定义方式或实施例描述的实施基础上略加修改后的实施方案也可以实现上述实施例相同、等同或相近、或变形后可预料的实施效果。应用这些修改或变形后的数据获取、存储、判断、处理方式等获取的实施例，仍然可以属于本说明书的可选实施方案范围之内。
在20世纪90年代，对于一个技术的改进可以很明显地区分是硬件上的改进(例如，对二极管、晶体管、开关等电路结构的改进)还是软件上的改进(对于方法流程的改进)。然而，随着技术的发展，当今的很多方法流程的改进已经可以视为硬件电路结构的直接改进。设计人员几乎都通过将改进的方法流程编程到硬件电路中来得到相应的硬件电路结构。因此，不能说一个方法流程的改进就不能用硬件实体模块来实现。例如，可编程逻辑器件(Programmable Logic Device,PLD)(例如现场可编程门阵列(Field Programmable Gate Array，FPGA)) 就是这样一种集成电路，其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字系统“集成”在一片PLD上，而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且，如今，取代手工地制作集成电路芯片，这种编程也多半改用“逻辑编译器(logic compiler)”软件来实现，它与程序开发撰写时所用的软件编译器相类似，而要编译之前的原始代码也得用特定的编程语言来撰写，此称之为硬件描述语言(Hardware Description Language，HDL)，而HDL也并非仅有一种，而是有许多种，如ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java HardwareDescription Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等，目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)与Verilog。本领域技术人员也应该清楚，只需要将方法流程用上述几种硬件描述语言稍作逻辑编程并编程到集成电路中，就可以很容易得到实现该逻辑方法流程的硬件电路。
控制器可以按任何适当的方式实现，例如，控制器可以采取例如微处理器或处理器以及存储可由该(微)处理器执行的计算机可读程序代码(例如软件或固件)的计算机可读介质、逻辑门、开关、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑控制器和嵌入微控制器的形式，控制器的例子包括但不限于以下微控制器：ARC 625D、Atmel AT91SAM、Microchip PIC18F26K20以及Silicone Labs C8051F320，存储器控制器还可以被实现为存储器的控制逻辑的一部分。本领域技术人员也知道，除了以纯计算机可读程序代码方式实现控制器以外，完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件，而对其内包括的用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至，可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、车载人机交互设备、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
虽然本说明书实施例提供了如实施例或流程图所述的方法操作步骤，但基于常规或者无创造性的手段可以包括更多或者更少的操作步骤。实施例中列举的步骤顺序仅仅为众多步骤执行顺序中的一种方式，不代表唯一的执行顺序。在实际中的装置或终端产品执行时，可以按照实施例或者附图所示的方法顺序执行或者并行执行(例如并行处理器或者多线程处理的环境，甚至为分布式数据处理环境)。术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、产品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、产品或者设备所固有的要素。在没有更多限制的情况下，并不排除在包括所述要素的过程、方法、产品或者设备中还存在另外的相同或等同要素。
为了描述的方便，描述以上装置时以功能分为各种模块分别描述。当然，在实施本说明书实施例时可以把各模块的功能在同一个或多个软件和/或硬件中实现，也可以将实现同一功能的模块由多个子模块或子单元的组合实现等。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
本领域技术人员也知道，除了以纯计算机可读程序代码方式实现控制器以外，完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因 此这种控制器可以被认为是一种硬件部件，而对其内部包括的用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至，可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机 存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
本领域技术人员应明白，本说明书的实施例可提供为方法、系统或计算机程序产品。因此，本说明书实施例可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本说明书实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本说明书实施例可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本说明书实施例，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。在本说明书的描述中，参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本说明书实施例的至少一个实施例或示例中。在本说明书中，对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且，描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外，在不相互矛盾的情况下，本领域的技术人员可以将本说明书中描述的不同实施例 或示例以及不同实施例或示例的特征进行结合和组合。
以上所述仅为本说明书实施例的实施例而已，并不用于限制本说明书实施例。对于本领域技术人员来说，本说明书实施例可以有各种更改和变化。凡在本说明书实施例的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本说明书实施例的权利要求范围之内。
Claims (12)
- 一种提升车辆定损图像识别结果的方法，所述方法包括：获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；获取所述车辆的配件列表，所述配件列表中包括车辆配件数据对应的配件识别编号；将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；输出匹配到的所述车辆配件的配件识别编号。
- 如权利要求1所述的一种提升车辆定损图像识别结果的方法，所述获取所述车辆的配件列表包括：利用所述车辆的车辆识别码查询获取的所述车辆的配件列表数据信息。
- 如权利要求1所述的一种提升车辆定损图像识别结果的方法，所述将所述初步受损部件在所述配件列表中进行匹配确定所述初步受损部件对应在所述配件列表中的车辆配件，包括：查询所述配件列表中是否有确定所述初步受损部件特征属性的车辆配件，若有，则将查询到的车辆配件作为与所述初步受损部件对应的车辆配件。
- 如权利要求1所述的一种提升车辆定损图像识别结果的方法，所述将所述初步受损部件在所述配件列表中进行匹配确定所述初步受损部件对应在所述配件列表中的车辆配件，包括：若在所述配件列表中存在至少两个所述初步受损部件的子级配件分类时，则对所述初步受损部件所对应的定损图像再次进行识别处理，直至在所述子级配件分类中确定出所述初步受损部件对应的唯一车辆配件，或达到定损图像的识别处理次数上限。
- 如权利要求1、3、4中任意一项所述的一种提升车辆定损图像识别结果的方法，所述方法还包括：若在所述配件列表中未匹配到所述初步受损部件对应的车辆配件，则在所述配件列表中查找与所述初步受损部件有配件包含关系的车辆配件，并以查找到的车辆配件作为所述初步受损部件对应在所述配件列表中的车辆配件。
- 一种提升车辆定损图像识别结果的装置，所述装置包括：算法处理模块，用于获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；配件列表处理模块，用于获取所述车辆的配件列表，将所述配件列表中的车辆配件数据转换为相应的配件识别编号；匹配模块，用于将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；识别结果输出模块，用于输出匹配到的所述车辆配件的配件识别编号。
- 如权利要求6所述的一种提升车辆定损图像识别结果的装置，所述配件列表处理模块中获取的配件列表包括：利用所述车辆的车辆识别码查询获取的所述车辆的配件列表数据信息。
- 如权利要求6所述的一种提升车辆定损图像识别结果的装置，所述匹配模块包括：特征配件模块，用于查询所述配件列表中是否有确定所述初步受损部件特征属性的车辆配件，若有，则将查询到的车辆配件作为与所述初步受损部件对应的车辆配件。
- 如权利要求6所述的一种提升车辆定损图像识别结果的装置，所述匹配模块包括：重识别模块，用于若在所述配件列表中存在至少两个所述初步受损部件的子级配件分类时，则对所述初步受损部件所对应的定损图像再次进行识别处理，直至在所述子级配件分类中确定出所述初步受损部件对应的唯一车辆配件，或达到定损图像的识别处理次数上限。
- 如权利要求6、8、9中任意一项所述的一种提升车辆定损图像识别结果的装置，所述装置还包括：关系配件匹配模块，用于在所述配件列表中未匹配到所述初步受损部件对应的车辆配件时，在所述配件列表中查找与所述初步受损部件有配件包含关系的车辆配件，并以查找到的车辆配件作为所述初步受损部件对应在所述配件列表中的车辆配件。
- 一种提升车辆定损图像识别结果的装置，包括处理器以及用于存储处理器可执行指令的存储器，所述处理器执行所述指令时实现：获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；获取所述车辆的配件列表，将所述配件列表中的车辆配件数据转换为相应的配件识别编号；将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；输出匹配到的所述车辆配件的配件识别编号。
- 一种服务器，包括至少一个处理器和存储处理器可执行指令的存储器，所述处理器执行所述指令时实现：获取车辆的初步受损部件，所述初步受损部件包括利用预设的图像识别算法对定损图像进行识别处理得到车辆的受损部件；获取所述车辆的配件列表，将所述配件列表中的车辆配件数据转换为相应的配件识别编号；将所述初步受损部件在所述配件列表中进行匹配，确定所述初步受损部件对应在所述配件列表中的车辆配件；输出匹配到的所述车辆配件的配件识别编号。
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP18861228.7A EP3617949A4 (en) | 2017-09-29 | 2018-09-26 | METHOD AND DEVICE FOR IMPROVING THE RESULT OF IDENTIFICATION OF A VEHICLE LOSS ASSESSMENT IMAGE AND SERVER |
| SG11201911631XA SG11201911631XA (en) | 2017-09-29 | 2018-09-26 | Method and apparatus for improving vehicle loss assessment image identification result, and server |
| US16/714,722 US10713865B2 (en) | 2017-09-29 | 2019-12-14 | Method and apparatus for improving vehicle loss assessment image identification result, and server |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710911173.2 | 2017-09-29 | ||
| CN201710911173.2A CN107748893A (zh) | 2017-09-29 | 2017-09-29 | 提升车辆定损图像识别结果的方法、装置及服务器 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US16/714,722 Continuation US10713865B2 (en) | 2017-09-29 | 2019-12-14 | Method and apparatus for improving vehicle loss assessment image identification result, and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019062743A1 true WO2019062743A1 (zh) | 2019-04-04 |
Family
ID=61254641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/107526 WO2019062743A1 (zh) | 2017-09-29 | 2018-09-26 | 提升车辆定损图像识别结果的方法、装置及服务器 |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US10713865B2 (zh) |
| EP (1) | EP3617949A4 (zh) |
| CN (1) | CN107748893A (zh) |
| SG (1) | SG11201911631XA (zh) |
| TW (1) | TWI676938B (zh) |
| WO (1) | WO2019062743A1 (zh) |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107748893A (zh) * | 2017-09-29 | 2018-03-02 | 阿里巴巴集团控股有限公司 | 提升车辆定损图像识别结果的方法、装置及服务器 |
| CN110634120B (zh) * | 2018-06-05 | 2022-06-03 | 杭州海康威视数字技术股份有限公司 | 一种车辆损伤判别方法及装置 |
| CN108876640A (zh) * | 2018-07-07 | 2018-11-23 | 北京精友世纪软件技术有限公司 | 一种基于人工智能的图像识别及维修方案估算的定损系统 |
| CN109242006A (zh) * | 2018-08-23 | 2019-01-18 | 阿里巴巴集团控股有限公司 | 基于车型分类的识别车辆损伤的方法及装置 |
| CN110570316A (zh) * | 2018-08-31 | 2019-12-13 | 阿里巴巴集团控股有限公司 | 训练损伤识别模型的方法及装置 |
| CN110569700B (zh) * | 2018-09-26 | 2020-11-03 | 创新先进技术有限公司 | 优化损伤识别结果的方法及装置 |
| CN110335238A (zh) * | 2019-05-08 | 2019-10-15 | 吉林大学 | 一种深度学习的汽车漆膜缺陷识别系统构建方法 |
| CN115668250A (zh) * | 2020-01-03 | 2023-01-31 | 易识有限公司 | 确定对损坏车辆的喷漆要求的方法 |
| US10970835B1 (en) * | 2020-01-13 | 2021-04-06 | Capital One Services, Llc | Visualization of damage on images |
| CN112132130B (zh) * | 2020-09-22 | 2022-10-04 | 福州大学 | 一种面向全场景的实时性车牌检测方法及系统 |
| US11769120B2 (en) * | 2020-10-14 | 2023-09-26 | Mitchell International, Inc. | Systems and methods for improving user experience during damage appraisal |
| CN112365008B (zh) * | 2020-10-27 | 2023-01-10 | 南阳理工学院 | 基于大数据的汽车配件选定方法及装置 |
| US20220148050A1 (en) * | 2020-11-11 | 2022-05-12 | Cdk Global, Llc | Systems and methods for using machine learning for vehicle damage detection and repair cost estimation |
| CN112836831B (zh) * | 2020-12-30 | 2022-04-12 | 邦邦汽车销售服务(北京)有限公司 | 汽车维修关联配件的数据处理方法和装置 |
| CN112749816A (zh) * | 2021-04-06 | 2021-05-04 | 上海臻势汽车科技有限公司 | 一种车辆定损选件的方法及系统 |
| US11803535B2 (en) | 2021-05-24 | 2023-10-31 | Cdk Global, Llc | Systems, methods, and apparatuses for simultaneously running parallel databases |
| CN113553985A (zh) * | 2021-08-02 | 2021-10-26 | 中再云图技术有限公司 | 一种基于人工智能高空烟雾检测识别方法，存储装置及服务器 |
| US11983145B2 (en) | 2022-08-31 | 2024-05-14 | Cdk Global, Llc | Method and system of modifying information on file |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268783A (zh) * | 2014-05-30 | 2015-01-07 | 翱特信息系统（中国）有限公司 | 车辆定损估价的方法、装置和终端设备 |
| US20150063627A1 (en) * | 2013-08-29 | 2015-03-05 | The Boeing Company | Methods and apparatus to identify components from images of the components |
| US20150112842A1 (en) * | 2013-10-21 | 2015-04-23 | Insurance Auto Auctions, Inc. | Parts exchange method and apparatus |
| CN106709808A (zh) * | 2016-11-22 | 2017-05-24 | 中国平安财产保险股份有限公司 | 基于车险智能定损平台的唯一配件自动过滤方法及系统 |
| CN106776681A (zh) * | 2016-11-04 | 2017-05-31 | 中国平安财产保险股份有限公司 | 一种车险配件数据库中配件数据的维护方法和系统 |
| CN107122484A (zh) * | 2017-05-08 | 2017-09-01 | 明觉科技（北京）有限公司 | 零件信息查询方法及系统 |
| CN107748893A (zh) * | 2017-09-29 | 2018-03-02 | 阿里巴巴集团控股有限公司 | 提升车辆定损图像识别结果的方法、装置及服务器 |
Family Cites Families (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7596242B2 (en) | 1995-06-07 | 2009-09-29 | Automotive Technologies International, Inc. | Image processing for vehicular applications |
| US5839112A (en) | 1994-12-28 | 1998-11-17 | Automatic Data Processing | Method and apparatus for displaying and selecting vehicle parts |
| WO1999040529A1 (en) | 1998-02-04 | 1999-08-12 | Biodynamic Research Corp. | System and method for acquiring and quantifying vehicular damage information |
| EP0982673A3 (en) * | 1998-08-21 | 2002-10-02 | Tsubasa System Co. Ltd. | Vehicle repair cost estimating system |
| US7797271B1 (en) * | 2001-06-18 | 2010-09-14 | Versata Development Group, Inc. | Custom browse hierarchies for subsets of items in a primary hierarchy |
| US20040019534A1 (en) * | 2002-07-26 | 2004-01-29 | Kevin Callahan | Methods and apparatus for purchasing a replacement part for a product |
| US7676062B2 (en) | 2002-09-03 | 2010-03-09 | Automotive Technologies International Inc. | Image processing for vehicular applications applying image comparisons |
| IT1337796B1 (it) | 2004-05-11 | 2007-02-20 | Fausto Siri | Procedimento per il riconoscimento, l'analisi e la valutazione delle deformazioni in particolare in automezzi |
| US7889931B2 (en) | 2004-10-22 | 2011-02-15 | Gb Investments, Inc. | Systems and methods for automated vehicle image acquisition, analysis, and reporting |
| US20060132291A1 (en) | 2004-11-17 | 2006-06-22 | Dourney Charles Jr | Automated vehicle check-in inspection method and system with digital image archiving |
| US20090138290A1 (en) | 2006-09-26 | 2009-05-28 | Holden Johnny L | Insurance adjustment through digital imaging system and method |
| US8694429B1 (en) * | 2008-01-15 | 2014-04-08 | Sciquest, Inc. | Identifying and resolving discrepancies between purchase documents and invoices |
| US20130297353A1 (en) | 2008-01-18 | 2013-11-07 | Mitek Systems | Systems and methods for filing insurance claims using mobile imaging |
| CA2721708C (en) | 2008-04-17 | 2018-01-09 | The Travelers Indemnity Company | A method of and system for determining and processing object structure condition information |
| CN102132300B (zh) | 2008-06-03 | 2018-02-02 | 扎斯特部件在线有限公司 | 在线列出物品的系统和方法 |
| US20140309913A1 (en) | 2013-04-15 | 2014-10-16 | Flextronics Ap, Llc | Relay and Exchange Protocol in an Automated Zone-Based Vehicular Traffic Control Environment |
| US10387960B2 (en) * | 2012-05-24 | 2019-08-20 | State Farm Mutual Automobile Insurance Company | System and method for real-time accident documentation and claim submission |
| US8712893B1 (en) | 2012-08-16 | 2014-04-29 | Allstate Insurance Company | Enhanced claims damage estimation using aggregate display |
| US8510196B1 (en) | 2012-08-16 | 2013-08-13 | Allstate Insurance Company | Feedback loop in mobile damage assessment and claims processing |
| US20140257627A1 (en) * | 2013-03-11 | 2014-09-11 | Ford Global Technologies, Llc | Potential chassis damage identification and notification system |
| CN103310223A (zh) * | 2013-03-13 | 2013-09-18 | 四川天翼网络服务有限公司 | 一种基于图像识别的车辆定损系统及方法 |
| US20140316825A1 (en) * | 2013-04-18 | 2014-10-23 | Audatex North America, Inc. | Image based damage recognition and repair cost estimation |
| DE102013211502A1 (de) * | 2013-06-19 | 2014-12-24 | Robert Bosch Gmbh | Identifikationsvorrichtung |
| TWM481428U (zh) * | 2013-12-31 | 2014-07-01 | Zhong-Xun Cai | 車輛故障評估系統 |
| US10380696B1 (en) * | 2014-03-18 | 2019-08-13 | Ccc Information Services Inc. | Image processing system for vehicle damage |
| US10089396B2 (en) * | 2014-07-30 | 2018-10-02 | NthGen Software Inc. | System and method of a dynamic interface for capturing vehicle data |
| US10387827B2 (en) * | 2014-08-28 | 2019-08-20 | Kenneth Ian Poncher | Intelligent part numbering system and method |
| US9466158B2 (en) * | 2014-12-03 | 2016-10-11 | General Motors Llc | Interactive access to vehicle information |
| CN104392005A (zh) * | 2014-12-18 | 2015-03-04 | 北京精友世纪软件技术有限公司 | 一种汽车快速定损方法 |
| US9972215B2 (en) * | 2015-08-18 | 2018-05-15 | Lincoln Global, Inc. | Augmented reality interface for weld sequencing |
| CN105608428A (zh) * | 2015-12-18 | 2016-05-25 | 周桂英 | 修理厂智能识别汽车外观伤损的方法 |
| CN105931007A (zh) * | 2016-01-13 | 2016-09-07 | 平安科技（深圳）有限公司 | 定损审核方法、服务器及终端 |
| TWM522886U (zh) * | 2016-02-24 | 2016-06-01 | Yulon Motor Co Ltd | 車輛檢修輔助系統 |
| CN106296118A (zh) * | 2016-08-03 | 2017-01-04 | 深圳市永兴元科技有限公司 | 基于图像识别的车辆定损方法及装置 |
| US10762513B2 (en) * | 2016-12-05 | 2020-09-01 | Sap Se | Data analytics system using insight providers |
| US11087292B2 (en) * | 2017-09-01 | 2021-08-10 | Allstate Insurance Company | Analyzing images and videos of damaged vehicles to determine damaged vehicle parts and vehicle asymmetries |
-
2017
- 2017-09-29 CN CN201710911173.2A patent/CN107748893A/zh active Pending
-
2018
- 2018-05-30 TW TW107118448A patent/TWI676938B/zh active
- 2018-09-26 SG SG11201911631XA patent/SG11201911631XA/en unknown
- 2018-09-26 WO PCT/CN2018/107526 patent/WO2019062743A1/zh unknown
- 2018-09-26 EP EP18861228.7A patent/EP3617949A4/en active Pending
-
2019
- 2019-12-14 US US16/714,722 patent/US10713865B2/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150063627A1 (en) * | 2013-08-29 | 2015-03-05 | The Boeing Company | Methods and apparatus to identify components from images of the components |
| US20150112842A1 (en) * | 2013-10-21 | 2015-04-23 | Insurance Auto Auctions, Inc. | Parts exchange method and apparatus |
| CN104268783A (zh) * | 2014-05-30 | 2015-01-07 | 翱特信息系统（中国）有限公司 | 车辆定损估价的方法、装置和终端设备 |
| CN106776681A (zh) * | 2016-11-04 | 2017-05-31 | 中国平安财产保险股份有限公司 | 一种车险配件数据库中配件数据的维护方法和系统 |
| CN106709808A (zh) * | 2016-11-22 | 2017-05-24 | 中国平安财产保险股份有限公司 | 基于车险智能定损平台的唯一配件自动过滤方法及系统 |
| CN107122484A (zh) * | 2017-05-08 | 2017-09-01 | 明觉科技（北京）有限公司 | 零件信息查询方法及系统 |
| CN107748893A (zh) * | 2017-09-29 | 2018-03-02 | 阿里巴巴集团控股有限公司 | 提升车辆定损图像识别结果的方法、装置及服务器 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP3617949A4 * |
Also Published As
| Publication number | Publication date |
|---|---|
| SG11201911631XA (en) | 2020-01-30 |
| CN107748893A (zh) | 2018-03-02 |
| TW201915829A (zh) | 2019-04-16 |
| EP3617949A4 (en) | 2020-06-17 |
| EP3617949A1 (en) | 2020-03-04 |
| US20200118365A1 (en) | 2020-04-16 |
| US10713865B2 (en) | 2020-07-14 |
| TWI676938B (zh) | 2019-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019062743A1 (zh) | 提升车辆定损图像识别结果的方法、装置及服务器 | |
| WO2019062742A1 (zh) | 提升车辆定损图像识别结果的方法、装置及服务器 | |
| TWI684922B (zh) | 基於圖像的車輛定損方法、裝置、電子設備及系統 | |
| WO2019214313A1 (zh) | 一种车辆定损的交互处理方法、装置、处理设备及客户端 | |
| CN108108767B (zh) | 一种谷物识别方法、装置和计算机存储介质 | |
| TWI686759B (zh) | 車險定損資料的處理方法、裝置和處理設備 | |
| US20150235142A1 (en) | System and method for identification of multimedia content elements | |
| TW201839704A (zh) | 基於圖像的車輛定損方法、裝置及電子設備 | |
| Souani et al. | Efficient algorithm for automatic road sign recognition and its hardware implementation | |
| TW201909171A (zh) | 會話資訊處理方法、裝置、電子設備 | |
| Hurney et al. | Review of pedestrian detection techniques in automotive far‐infrared video | |
| US11270149B2 (en) | Image recognition method and system based on deep learning | |
| JP6945639B2 (ja) | 画像処理方法及び装置 | |
| US20140217901A1 (en) | Spatial intensity distribution controlled flash | |
| CN107861750B (zh) | 一种标签管理方法、标签管理装置及智能终端 | |
| TW202030684A (zh) | 理賠業務的處理方法及裝置 | |
| EP3715834B1 (en) | Grain identification method and device, and computer storage medium | |
| CN104598937A (zh) | 文字信息的识别方法和装置 | |
| CN111950469A (zh) | 一种道路标识检测方法、系统、设备和介质 | |
| CN114550220B (zh) | 行人重识别模型的训练方法及行人重识别方法 | |
| CN114898749B (zh) | 一种汽车电子手册交互方法、装置及车辆 | |
| CN111885804B (zh) | 一种机箱灯光无线遥控方法、装置及可储存介质 | |
| CN113805698B (zh) | 一种执行指令确定方法、装置、设备及存储介质 | |
| CN112380369B (zh) | 图像检索模型的训练方法、装置、设备和存储介质 | |
| CN108388859B (zh) | 物体检测方法、网络训练方法、装置和计算机存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18861228 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2018861228 Country of ref document: EP Effective date: 20191129 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |