CN103310223A - Vehicle loss assessment system based on image recognition and method thereof - Google Patents
Vehicle loss assessment system based on image recognition and method thereof Download PDFInfo
- Publication number
- CN103310223A CN103310223A CN2013100807162A CN201310080716A CN103310223A CN 103310223 A CN103310223 A CN 103310223A CN 2013100807162 A CN2013100807162 A CN 2013100807162A CN 201310080716 A CN201310080716 A CN 201310080716A CN 103310223 A CN103310223 A CN 103310223A
- Authority
- CN
- China
- Prior art keywords
- svm classifier
- classifier device
- circuit
- image
- typical sample
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a vehicle loss assessment system based on image recognition and a method thereof. The system comprises image acquiring equipment and a background processing unit, wherein the background processing unit comprises an analog-digital converter, a digital signal processor and an image recognition module; the image recognition module comprises an SVM (Support Vector Machine) classifier training module, an SVM classifier recognition module and a database; each typical sample is input into the SVM classifier training module respectively; the SVM classifier training module is used for outputting an SVM classifier model; an image sample to be judged output by the digital signal processor is input to the SVM classifier recognition module; and the SVM classifier recognition module is used for loading a trained SVM classifier model to obtain and output a vehicle loss assessment result. Due to the adoption of the system, vehicle loss assessment can be realized remotely, the workload and cost of vehicle loss assessment can be lowered greatly for an insurance company, and the working efficiency is increased effectively; the loss assessment system and method are simple, are easy to operate, are high in intelligence degree, and have low requirements on operators; and the loss assessment result is scientific, accurate, reliable and objective.
Description
Technical field
The present invention relates to a kind of vehicle loss assessment system based on image recognition and method.
Background technology
The car damage identification teacher is according to the automobile construction principle, specialization inspection, test and exploration means by science, system are carried out analysis-by-synthesis to car crass and the scene of the accident, use vehicle assessment of loss data and mantenance data the vehicle collision reparation to be carried out the professional and technical personnel of the assessment of loss price of science, system.In the present vehicle insurance setting loss Claims Resolution field of insurance company, most of insurance companies all adopt artificial setting loss mode, go to the scene of the accident or Auto repair shop by setting loss teacher of insurance company, and vehicle carries out setting loss to being in danger.
This traditional artificial setting loss mode exists the problem of the following aspects:
(1) must to on-the-spot to the vehicle inspection of being in danger, test, for setting loss Shi Eryan, workload is larger, work efficiency is low;
(2) position that has an accident is random, may be in far-out area, distance insurance company setting loss center, and setting loss teacher is difficult in time to rush towards the scene of the accident, can't the support vehicles setting loss ageing.
In order to address the above problem, some insurance companies in the scene of the accident or Auto repair shop carry out photo acquisition, then take back or the long-range setting loss center that is sent to, again by setting loss teacher according to take a picture and carry out artificial setting loss.Replace the on-the-spot setting loss mode of traditional setting loss teacher, can improve to a certain extent its work efficiency, and guaranteed the ageing of car damage identification.Yet the damage identification method after the improvement still depends on setting loss's teacher artificial setting loss, still has following problem:
1) requires setting loss teacher to grasp comprehensive vocational skills, setting loss's teacher professional ability is had relatively high expectations;
2) setting loss result is drawn by setting loss Shi Jianding fully, has larger subjectivity and one-sidedness, setting loss result's deviation easily occurs, can not react objective, exactly the vehicle damaged condition.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, a kind of Traditional Man setting loss mode of replacing is provided, only need common staff to press the setting loss start button and can finish the robotization setting loss, intelligent degree is high, can significantly reduce workload, increase work efficiency, and need not setting loss teacher and rush towards the scene, the effective guarantee car damage identification is ageing, and setting loss is science, accurate, reliable, objective vehicle loss assessment system and method based on image recognition as a result.
The objective of the invention is to be achieved through the following technical solutions: a kind of vehicle loss assessment system based on image recognition, it comprise for collection vehicle treat the image capture device of setting loss image of component information and be used for to the image file that image capture device gathers process, the background processing unit of identification, setting loss, image capture device carries out data communication by transmission network and background processing unit;
Described background processing unit comprises analog to digital converter, digital signal processor and picture recognition module, and the input end of analog to digital converter connects image capture device, and the output terminal of analog to digital converter is connected with picture recognition module by digital signal processor;
Described picture recognition module comprises for the svm classifier device training module that typical sample is carried out features training, for the svm classifier device identification module that image pattern to be discriminated is identified with for the database of storing typical sample; Described typical sample comprises that slight damage typical sample, moderate are damaged typical sample and severe is damaged typical sample, and each typical sample is inputted respectively svm classifier device training module, svm classifier device training module output svm classifier device model; The image pattern to be discriminated of digital signal processor output inputs to svm classifier device identification module, and svm classifier device identification module loads and trained the svm classifier device model of finishing, and obtains and export the car damage identification result.
Further, svm classifier device training module comprises data pre-process circuit, characteristic extracting circuit, proper vector normalization circuit and svm classifier device drill circuit, the input end of data pre-process circuit connects the typical sample signal, the output terminal of data pre-process circuit links to each other with an input end of svm classifier device drill circuit with the proper vector normalization circuit by characteristic extracting circuit successively, and another input end of svm classifier device drill circuit is inputted the corresponding car damage identification result of this typical sample signal.
Further, svm classifier device identification module comprises the data pre-process circuit, characteristic extracting circuit, proper vector normalization circuit and svm classifier device identification circuit, the input end of data pre-process circuit connects sample signal to be discriminated, the output terminal of data pre-process circuit links to each other with the input end of proper vector normalization circuit with svm classifier device identification circuit by characteristic extracting circuit successively, be loaded with in the svm classifier device identification circuit and train the svm classifier device of finishing, the proper vector of proper vector normalization circuit output inputs in the svm classifier device finishes identification, and the svm classifier device is exported the car damage identification result of sample to be discriminated.
A kind of car damage identification method based on image recognition, it may further comprise the steps:
S1: the image capture device collection vehicle is treated the image information of setting loss parts;
S2: image file inputs to analog to digital converter and carries out analog to digital conversion, is converted to enter digital signal processor after the digital signal and process, and transfers to picture recognition module and carry out car damage identification after digital signal processing;
The step that described picture recognition module is carried out car damage identification may further comprise the steps:
The training of S201:SVM sorter, it comprises following substep:
S2011: respectively slight damage typical sample, moderate damage typical sample and the severe damage typical sample that is pre-stored in the database carried out the data pre-service;
S2012: feature extraction, composition characteristic vector;
S2013: normalization proper vector;
S2014: confirm the car damage identification result that this typical sample is corresponding;
S2015: with proper vector and this car damage identification result respectively as the input and output of svm classifier device drill circuit, training svm classifier device;
S2016: obtain svm classifier device model and storage;
The identification of S202:SVM sorter, it comprises following substep:
S2021: the image pattern signal to be discriminated to digital signal processor output carries out the data pre-service;
S2022: feature extraction, composition characteristic vector;
S2023: normalization proper vector;
S2024: load and trained the svm classifier device of finishing;
S2025: proper vector inputed in the svm classifier device identify;
S2026: the output according to the svm classifier device obtains the corresponding car damage identification result of this image pattern to be discriminated.
The invention has the beneficial effects as follows:
(1) no longer need to the scene of the accident for the setting loss of vehicle or maintenance depot to the vehicle inspection of being in danger, test, and the photo that only need gather the front end damaged vehicle gets final product long-range realization car damage identification, can significantly reduce workload and cost that insurance company carries out car damage identification, the Effective Raise work efficiency;
(2) need not setting loss teacher and rush towards the scene of the accident, only need to gather the front end photo, again by communication network be transferred to that the Background control center is processed, identification and setting loss can finish the vehicle remote setting loss, even accident occurs in apart from far-out area, insurance company setting loss center, but also effective guarantee car damage identification ageing;
(3) loss assessment system and method are simple, easy to operate, and intelligent degree is high, to operating personnel require lowly, the layman can finish relevant setting loss operation;
(4) setting loss result is by default normative reference decision, and not take artificial will as transfer, setting loss is science, accurate, reliable, objective as a result;
(5) the support vector machines method is adopted in the identification of image file, has further improved recognition accuracy, helps further to improve setting loss result's accuracy and reliability.
Description of drawings
Fig. 1 is vehicle loss assessment system structural representation block diagram of the present invention;
Fig. 2 is the structural representation block diagram of svm classifier device training module;
Fig. 3 is the structural representation block diagram of svm classifier device identification module;
Fig. 4 is car damage identification method process flow diagram of the present invention.
Embodiment
Below in conjunction with accompanying drawing technical scheme of the present invention is described in further detail, but protection scope of the present invention is not limited to the following stated.
As shown in Figure 1, a kind of vehicle loss assessment system based on image recognition, it comprise for collection vehicle treat the image capture device of setting loss image of component information and be used for to the image file that image capture device gathers process, the background processing unit of identification, setting loss, image capture device carries out data communication by transmission network and background processing unit;
Described background processing unit comprises analog to digital converter, digital signal processor and picture recognition module, and the input end of analog to digital converter connects image capture device, and the output terminal of analog to digital converter is connected with picture recognition module by digital signal processor;
Described picture recognition module comprises for the svm classifier device training module that typical sample is carried out features training, for the svm classifier device identification module that image pattern to be discriminated is identified with for the database of storing typical sample; Described typical sample comprises that slight damage typical sample, moderate are damaged typical sample and severe is damaged typical sample, and each typical sample is inputted respectively svm classifier device training module, svm classifier device training module output svm classifier device model; The image pattern to be discriminated of digital signal processor output inputs to svm classifier device identification module, and svm classifier device identification module loads and trained the svm classifier device model of finishing, and obtains and export the car damage identification result.
As shown in Figure 2, svm classifier device training module comprises data pre-process circuit, characteristic extracting circuit, proper vector normalization circuit and svm classifier device drill circuit, the input end of data pre-process circuit connects the typical sample signal, the output terminal of data pre-process circuit links to each other with an input end of svm classifier device drill circuit with the proper vector normalization circuit by characteristic extracting circuit successively, and another input end of svm classifier device drill circuit is inputted the corresponding car damage identification result of this typical sample signal.
As shown in Figure 3, svm classifier device identification module comprises the data pre-process circuit, characteristic extracting circuit, proper vector normalization circuit and svm classifier device identification circuit, the input end of data pre-process circuit connects sample signal to be discriminated, the output terminal of data pre-process circuit links to each other with the input end of proper vector normalization circuit with svm classifier device identification circuit by characteristic extracting circuit successively, be loaded with in the svm classifier device identification circuit and train the svm classifier device of finishing, the proper vector of proper vector normalization circuit output inputs in the svm classifier device finishes identification, and the svm classifier device is exported the car damage identification result of sample to be discriminated.
As shown in Figure 4, a kind of car damage identification method based on image recognition, it may further comprise the steps:
S1: the image capture device collection vehicle is treated the image information of setting loss parts;
S2: image file inputs to analog to digital converter and carries out analog to digital conversion, is converted to enter digital signal processor after the digital signal and process, and transfers to picture recognition module and carry out car damage identification after digital signal processing;
The step that described picture recognition module is carried out car damage identification may further comprise the steps:
S201: as shown in Figure 2, the training of svm classifier device, it comprises following substep:
S2011: respectively slight damage typical sample, moderate damage typical sample and the severe damage typical sample that is pre-stored in the database carried out the data pre-service;
S2012: feature extraction, composition characteristic vector;
S2013: normalization proper vector;
S2014: confirm the car damage identification result that this typical sample is corresponding;
S2015: with proper vector and this car damage identification result respectively as the input and output of svm classifier device drill circuit, training svm classifier device;
S2016: obtain svm classifier device model and storage;
S202: as shown in Figure 3, the identification of svm classifier device, it comprises following substep:
S2021: the image pattern signal to be discriminated to digital signal processor output carries out the data pre-service;
S2022: feature extraction, composition characteristic vector;
S2023: normalization proper vector;
S2024: load and trained the svm classifier device of finishing;
S2025: proper vector inputed in the svm classifier device identify;
S2026: the output according to the svm classifier device obtains the corresponding car damage identification result of this image pattern to be discriminated.
Claims (4)
1. vehicle loss assessment system based on image recognition, it is characterized in that: it comprise for collection vehicle treat the image capture device of setting loss image of component information and be used for to the image file that image capture device gathers process, the background processing unit of identification, setting loss, image capture device carries out data communication by transmission network and background processing unit;
Described background processing unit comprises analog to digital converter, digital signal processor and picture recognition module, and the input end of analog to digital converter connects image capture device, and the output terminal of analog to digital converter is connected with picture recognition module by digital signal processor;
Described picture recognition module comprises for the svm classifier device training module that typical sample is carried out features training, for the svm classifier device identification module that image pattern to be discriminated is identified with for the database of storing typical sample; Described typical sample comprises that slight damage typical sample, moderate are damaged typical sample and severe is damaged typical sample, and each typical sample is inputted respectively svm classifier device training module, svm classifier device training module output svm classifier device model; The image pattern to be discriminated of digital signal processor output inputs to svm classifier device identification module, and svm classifier device identification module loads and trained the svm classifier device model of finishing, and obtains and export the car damage identification result.
2. a kind of vehicle loss assessment system based on image recognition according to claim 1, it is characterized in that: described svm classifier device training module comprises the data pre-process circuit, characteristic extracting circuit, proper vector normalization circuit and svm classifier device drill circuit, the input end of data pre-process circuit connects the typical sample signal, the output terminal of data pre-process circuit links to each other with an input end of svm classifier device drill circuit with the proper vector normalization circuit by characteristic extracting circuit successively, and another input end of svm classifier device drill circuit is inputted the corresponding car damage identification result of this typical sample signal.
3. a kind of vehicle loss assessment system based on image recognition according to claim 1, it is characterized in that: described svm classifier device identification module comprises the data pre-process circuit, characteristic extracting circuit, proper vector normalization circuit and svm classifier device identification circuit, the input end of data pre-process circuit connects sample signal to be discriminated, the output terminal of data pre-process circuit links to each other with the input end of proper vector normalization circuit with svm classifier device identification circuit by characteristic extracting circuit successively, be loaded with in the svm classifier device identification circuit and train the svm classifier device of finishing, the proper vector of proper vector normalization circuit output inputs in the svm classifier device finishes identification, and the svm classifier device is exported the car damage identification result of sample to be discriminated.
4. car damage identification method based on image recognition, it is characterized in that: it may further comprise the steps:
S1: the image capture device collection vehicle is treated the image information of setting loss parts;
S2: image file inputs to analog to digital converter and carries out analog to digital conversion, is converted to enter digital signal processor after the digital signal and process, and transfers to picture recognition module and carry out car damage identification after digital signal processing;
The step that described picture recognition module is carried out car damage identification may further comprise the steps:
The training of S201:SVM sorter, it comprises following substep:
S2011: respectively slight damage typical sample, moderate damage typical sample and the severe damage typical sample that is pre-stored in the database carried out the data pre-service;
S2012: feature extraction, composition characteristic vector;
S2013: normalization proper vector;
S2014: confirm the car damage identification result that this typical sample is corresponding;
S2015: with proper vector and this car damage identification result respectively as the input and output of svm classifier device drill circuit, training svm classifier device;
S2016: obtain svm classifier device model and storage;
The identification of S202:SVM sorter, it comprises following substep:
S2021: the image pattern signal to be discriminated to digital signal processor output carries out the data pre-service;
S2022: feature extraction, composition characteristic vector;
S2023: normalization proper vector;
S2024: load and trained the svm classifier device of finishing;
S2025: proper vector inputed in the svm classifier device identify;
S2026: the output according to the svm classifier device obtains the corresponding car damage identification result of this image pattern to be discriminated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013100807162A CN103310223A (en) | 2013-03-13 | 2013-03-13 | Vehicle loss assessment system based on image recognition and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013100807162A CN103310223A (en) | 2013-03-13 | 2013-03-13 | Vehicle loss assessment system based on image recognition and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103310223A true CN103310223A (en) | 2013-09-18 |
Family
ID=49135417
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013100807162A Pending CN103310223A (en) | 2013-03-13 | 2013-03-13 | Vehicle loss assessment system based on image recognition and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103310223A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104932359A (en) * | 2015-05-29 | 2015-09-23 | 大连楼兰科技股份有限公司 | Vehicle remote unattended loss assessment system based on CAE technology and loss assessment method thereof |
| CN105678622A (en) * | 2016-01-07 | 2016-06-15 | 平安科技（深圳）有限公司 | Analysis method and system for vehicle insurance claim-settlement photos |
| CN105976449A (en) * | 2016-05-27 | 2016-09-28 | 大连楼兰科技股份有限公司 | Remote automatic damage assessment and collision detection method and system for vehicle |
| CN106055891A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | Remote damage-assessment system and method established based on artificial intelligence Softmax regression method for different types of vehicles |
| CN106055776A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | Regional and remote damage-assessment system and method established based on artificial-intelligence supervised learning linear regression method for different types of vehicles |
| CN106055778A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | Remote damage-assessment system and method established based on artificial intelligence for different types of vehicles |
| CN106056147A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | System and method for establishing target division remote damage assessment of different vehicle types based artificial intelligence radial basis function neural network method |
| CN106067033A (en) * | 2016-05-27 | 2016-11-02 | 大连楼兰科技股份有限公司 | Vehicle remote setting loss mathematical model method of testing based on branch's formula and system |
| CN106066907A (en) * | 2016-05-27 | 2016-11-02 | 大连楼兰科技股份有限公司 | The setting loss grading method judged based on many parts multi-model |
| CN106600422A (en) * | 2016-11-24 | 2017-04-26 | 中国平安财产保险股份有限公司 | Car insurance intelligent loss assessment method and system |
| CN106780048A (en) * | 2016-11-28 | 2017-05-31 | 中国平安财产保险股份有限公司 | A kind of self-service Claims Resolution method of intelligent vehicle insurance, self-service Claims Resolution apparatus and system |
| CN107092922A (en) * | 2017-03-13 | 2017-08-25 | 平安科技（深圳）有限公司 | Car damages recognition methods and server |
| CN107358596A (en) * | 2017-04-11 | 2017-11-17 | 阿里巴巴集团控股有限公司 | A kind of car damage identification method based on image, device, electronic equipment and system |
| CN107403424A (en) * | 2017-04-11 | 2017-11-28 | 阿里巴巴集团控股有限公司 | A kind of car damage identification method based on image, device and electronic equipment |
| CN107748893A (en) * | 2017-09-29 | 2018-03-02 | 阿里巴巴集团控股有限公司 | Lift the method, apparatus and server of car damage identification image recognition result |
| CN108885700A (en) * | 2015-10-02 | 2018-11-23 | 川科德博有限公司 | Data set semi-automatic labelling |
| CN109146694A (en) * | 2018-07-13 | 2019-01-04 | 平安科技（深圳）有限公司 | Electronic device, the preferential rank of user's vehicle insurance determine method and storage medium |
| CN109272504A (en) * | 2018-10-17 | 2019-01-25 | 广汽丰田汽车有限公司 | The detection of vehicle bumps defect, retroactive method, apparatus and system |
| CN109919785A (en) * | 2019-02-22 | 2019-06-21 | 德联易控科技(北京)有限公司 | Assessment processing method, apparatus, equipment and the storage medium of car damage identification |
| WO2019144416A1 (en) * | 2018-01-29 | 2019-08-01 | 深圳前海达闼云端智能科技有限公司 | Information processing method and system, cloud processing device and computer program product |
| WO2019174306A1 (en) * | 2018-03-16 | 2019-09-19 | 阿里巴巴集团控股有限公司 | Item damage assessment method and device |
| US10817956B2 (en) | 2017-04-11 | 2020-10-27 | Alibaba Group Holding Limited | Image-based vehicle damage determining method and apparatus, and electronic device |
| US11544914B2 (en) | 2021-02-18 | 2023-01-03 | Inait Sa | Annotation of 3D models with signs of use visible in 2D images |
| US11971953B2 (en) | 2021-02-02 | 2024-04-30 | Inait Sa | Machine annotation of photographic images |
| US11983836B2 (en) | 2021-02-18 | 2024-05-14 | Inait Sa | Annotation of 3D models with signs of use visible in 2D images |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040044453A1 (en) * | 2002-08-29 | 2004-03-04 | International Business Machines Corporation | Continuously monitoring and correcting operational conditions in automobiles from a remote location through wireless transmissions |
| CN1658559A (en) * | 2005-02-22 | 2005-08-24 | 刘波 | Remote real-time monitoring vehide loss deviding system based on internet and its monitoring method |
| CN101242379A (en) * | 2008-03-18 | 2008-08-13 | 北京中车检信息技术有限公司 | Car damage identification method based on mobile communication terminal or network terminal |
| US8364505B1 (en) * | 2004-02-02 | 2013-01-29 | Allstate Insurance Company | Systems and methods for early identification of a total loss vehicle |
| CN102928435A (en) * | 2012-10-15 | 2013-02-13 | 南京航空航天大学 | Aircraft skin damage identification method and device based on image and ultrasound information fusion |
-
2013
- 2013-03-13 CN CN2013100807162A patent/CN103310223A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040044453A1 (en) * | 2002-08-29 | 2004-03-04 | International Business Machines Corporation | Continuously monitoring and correcting operational conditions in automobiles from a remote location through wireless transmissions |
| US8364505B1 (en) * | 2004-02-02 | 2013-01-29 | Allstate Insurance Company | Systems and methods for early identification of a total loss vehicle |
| CN1658559A (en) * | 2005-02-22 | 2005-08-24 | 刘波 | Remote real-time monitoring vehide loss deviding system based on internet and its monitoring method |
| CN101242379A (en) * | 2008-03-18 | 2008-08-13 | 北京中车检信息技术有限公司 | Car damage identification method based on mobile communication terminal or network terminal |
| CN102928435A (en) * | 2012-10-15 | 2013-02-13 | 南京航空航天大学 | Aircraft skin damage identification method and device based on image and ultrasound information fusion |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104932359A (en) * | 2015-05-29 | 2015-09-23 | 大连楼兰科技股份有限公司 | Vehicle remote unattended loss assessment system based on CAE technology and loss assessment method thereof |
| CN108885700A (en) * | 2015-10-02 | 2018-11-23 | 川科德博有限公司 | Data set semi-automatic labelling |
| CN105678622A (en) * | 2016-01-07 | 2016-06-15 | 平安科技（深圳）有限公司 | Analysis method and system for vehicle insurance claim-settlement photos |
| CN106066907A (en) * | 2016-05-27 | 2016-11-02 | 大连楼兰科技股份有限公司 | The setting loss grading method judged based on many parts multi-model |
| CN106066907B (en) * | 2016-05-27 | 2020-04-14 | 大连楼兰科技股份有限公司 | Loss assessment grading method based on multi-part multi-model judgment |
| CN106056147A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | System and method for establishing target division remote damage assessment of different vehicle types based artificial intelligence radial basis function neural network method |
| CN106067033A (en) * | 2016-05-27 | 2016-11-02 | 大连楼兰科技股份有限公司 | Vehicle remote setting loss mathematical model method of testing based on branch's formula and system |
| CN106055891A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | Remote damage-assessment system and method established based on artificial intelligence Softmax regression method for different types of vehicles |
| CN106055776A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | Regional and remote damage-assessment system and method established based on artificial-intelligence supervised learning linear regression method for different types of vehicles |
| CN106055778A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | Remote damage-assessment system and method established based on artificial intelligence for different types of vehicles |
| CN105976449A (en) * | 2016-05-27 | 2016-09-28 | 大连楼兰科技股份有限公司 | Remote automatic damage assessment and collision detection method and system for vehicle |
| CN106600422A (en) * | 2016-11-24 | 2017-04-26 | 中国平安财产保险股份有限公司 | Car insurance intelligent loss assessment method and system |
| CN106780048A (en) * | 2016-11-28 | 2017-05-31 | 中国平安财产保险股份有限公司 | A kind of self-service Claims Resolution method of intelligent vehicle insurance, self-service Claims Resolution apparatus and system |
| CN107092922B (en) * | 2017-03-13 | 2018-08-31 | 平安科技（深圳）有限公司 | Vehicle damages recognition methods and server |
| CN107092922A (en) * | 2017-03-13 | 2017-08-25 | 平安科技（深圳）有限公司 | Car damages recognition methods and server |
| CN107403424B (en) * | 2017-04-11 | 2020-09-18 | 阿里巴巴集团控股有限公司 | Vehicle loss assessment method and device based on image and electronic equipment |
| US10789786B2 (en) | 2017-04-11 | 2020-09-29 | Alibaba Group Holding Limited | Picture-based vehicle loss assessment |
| CN107403424A (en) * | 2017-04-11 | 2017-11-28 | 阿里巴巴集团控股有限公司 | A kind of car damage identification method based on image, device and electronic equipment |
| US11049334B2 (en) | 2017-04-11 | 2021-06-29 | Advanced New Technologies Co., Ltd. | Picture-based vehicle loss assessment |
| CN107358596A (en) * | 2017-04-11 | 2017-11-17 | 阿里巴巴集团控股有限公司 | A kind of car damage identification method based on image, device, electronic equipment and system |
| US10817956B2 (en) | 2017-04-11 | 2020-10-27 | Alibaba Group Holding Limited | Image-based vehicle damage determining method and apparatus, and electronic device |
| US10713865B2 (en) | 2017-09-29 | 2020-07-14 | Alibaba Group Holding Limited | Method and apparatus for improving vehicle loss assessment image identification result, and server |
| CN107748893A (en) * | 2017-09-29 | 2018-03-02 | 阿里巴巴集团控股有限公司 | Lift the method, apparatus and server of car damage identification image recognition result |
| WO2019144416A1 (en) * | 2018-01-29 | 2019-08-01 | 深圳前海达闼云端智能科技有限公司 | Information processing method and system, cloud processing device and computer program product |
| TWI683260B (en) * | 2018-03-16 | 2020-01-21 | 香港商阿里巴巴集團服務有限公司 | Method and device for determining damage to items |
| WO2019174306A1 (en) * | 2018-03-16 | 2019-09-19 | 阿里巴巴集团控股有限公司 | Item damage assessment method and device |
| US11300522B2 (en) | 2018-03-16 | 2022-04-12 | Advanced New Technologies Co., Ltd. | Article damage evaluation |
| CN109146694A (en) * | 2018-07-13 | 2019-01-04 | 平安科技（深圳）有限公司 | Electronic device, the preferential rank of user's vehicle insurance determine method and storage medium |
| CN109146694B (en) * | 2018-07-13 | 2024-02-02 | 平安科技（深圳）有限公司 | Electronic device, user vehicle insurance preference level determining method and storage medium |
| CN109272504A (en) * | 2018-10-17 | 2019-01-25 | 广汽丰田汽车有限公司 | The detection of vehicle bumps defect, retroactive method, apparatus and system |
| CN109919785A (en) * | 2019-02-22 | 2019-06-21 | 德联易控科技(北京)有限公司 | Assessment processing method, apparatus, equipment and the storage medium of car damage identification |
| US11971953B2 (en) | 2021-02-02 | 2024-04-30 | Inait Sa | Machine annotation of photographic images |
| US11983836B2 (en) | 2021-02-18 | 2024-05-14 | Inait Sa | Annotation of 3D models with signs of use visible in 2D images |
| US11544914B2 (en) | 2021-02-18 | 2023-01-03 | Inait Sa | Annotation of 3D models with signs of use visible in 2D images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103310223A (en) | Vehicle loss assessment system based on image recognition and method thereof | |
| CN110084281B (en) | Image generation method, neural network compression method, related device and equipment | |
| CN101097605B (en) | Vehicle personal identification system of ETC electric no-parking charge | |
| CN106021548A (en) | Remote damage assessment method and system based on distributed artificial intelligent image recognition | |
| CN104992270A (en) | Power transmission and transformation equipment state maintenance aid decision making system and method | |
| CN107092922A (en) | Car damages recognition methods and server | |
| CN106600422A (en) | Car insurance intelligent loss assessment method and system | |
| CN104794768A (en) | Attendance checking system and attendance checking method capable of regularly and automatically running attendance checking calculation | |
| CN111126481A (en) | Training method and device of neural network model | |
| CN110647951A (en) | Wireless radio frequency equipment identity recognition method and system based on machine learning algorithm | |
| CN105631445A (en) | Character recognition method and system for license plate with Chinese characters | |
| DE102021115299A1 (en) | METHOD AND DEVICE FOR CONTINUOUS FEW-SHOT LEARNING WITHOUT FORGETTING | |
| CN103761515A (en) | Human face feature extracting method and device based on LBP | |
| CN111382808A (en) | Vehicle detection processing method and device | |
| AG | Development of portable automatic number plate recognition (ANPR) system on Raspberry Pi | |
| CN111444986A (en) | Building drawing component classification method and device, electronic equipment and storage medium | |
| CN106205199A (en) | A kind of car plate fault-tolerance processing system | |
| CN111970400A (en) | Crank call identification method and device | |
| Sulehria et al. | Vehicle number plate recognition using mathematical morphology and neural networks | |
| CN109325409A (en) | Passing vehicle deck verifying bench | |
| CN109858573B (en) | Method for preventing lifting of collecting card based on neural network | |
| CN113255941B (en) | Bridge construction waste treatment method and device | |
| CN114227717A (en) | Intelligent inspection method, device, equipment and storage medium based on inspection robot | |
| CN107729885A (en) | A kind of face Enhancement Method based on the study of multiple residual error | |
| CN117132990A (en) | Railway carriage information identification method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130918 |