CN106021548A - Remote damage assessment method and system based on distributed artificial intelligent image recognition - Google Patents

Remote damage assessment method and system based on distributed artificial intelligent image recognition Download PDF

Info

Publication number
CN106021548A
CN106021548A CN201610365742.3A CN201610365742A CN106021548A CN 106021548 A CN106021548 A CN 106021548A CN 201610365742 A CN201610365742 A CN 201610365742A CN 106021548 A CN106021548 A CN 106021548A
Authority
CN
China
Prior art keywords
image
setting loss
accident
vehicle
car
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
Application number
CN201610365742.3A
Other languages
Chinese (zh)
Inventor
田雨农
张虹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dalian Roiland Technology Co Ltd
Original Assignee
Dalian Roiland Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Dalian Roiland Technology Co Ltd filed Critical Dalian Roiland Technology Co Ltd
Priority to CN201610365742.3A priority Critical patent/CN106021548A/en
Publication of CN106021548A publication Critical patent/CN106021548A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43—Querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/61—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/71—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • 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

Abstract

The invention discloses a remote damage assessment method and system based on distributed artificial intelligent image recognition. The method comprises the steps that an image collecting device collects external part images of a traffic accident vehicle and sends the external part images to a cloud platform; a vehicle-mounted sensor device acquires collision data information and uploads the collision data information to the cloud platform; an image processing module carries out preprocessing on the collected external part images of the traffic accident vehicle and stores the image preprocessing results into a vehicle damage assessment database; an image feature extraction module extracts features of the external part images according to the image preprocessing results, image matching is carried out on the obtained preprocessing external part image feature information of the traffic accident vehicle and an image base in the vehicle damage assessment database, and an external part damage assessment result of the traffic accident vehicle is obtained through a vehicle external part damage assessment model. By means of the method, on one hand, traffic accident vehicle external part damage assessment can be quickly carried out; on the other hand, by means of image and collision information step-by-step type damage assessment, the damage assessment faults can be reduced, and the precision and efficiency of settlement of claims can be improved.

Description

Long-range damage identification method based on distributed artificial intelligence image recognition and system
Technical field
The invention belongs to long-range setting loss field, specifically know based on distributed artificial intelligence image Other long-range damage identification method and system.
Background technology
After colliding due to vehicle, vehicle self can produce various deformation and damage, but only leans on Setting loss person carries out accident vehicle setting loss by rule of thumb, there is a lot of subjectivitys and the machine of associating insurance fraud Rate.Additionally, tradition setting loss is disassembled in order to the accuracy of accident vehicle setting loss needs to carry out vehicle, This also adds additional the expense of settlement of insurance claim.In the face of current insurance market keen competition shape Formula, in order to improve further insurance Claims Resolution service ability, by the long-range loss assessment system of vehicle insurance this One brand-new modernized service method strengthens Claims Resolution flow management and control；Optimize Claims Resolution flow process, improve reason Pay for efficiency, effectively integrate Claims Resolution resource.At present, market has based on determining that car accident is taken pictures Damage system, but there is forgery and shoot the problems such as unclear in image.
Summary of the invention
The present invention is directed to the problems referred to above that prior art exists, invented a kind of based on distributed people The long-range damage identification method of work intelligent image identification and system, on the one hand solve setting loss person and carry out determining The subjectivity damaged and the probability reducing associating insurance fraud；On the other hand disassembling of accident vehicle can be avoided Expense, thus be greatly promoted and protecting satisfaction and the standardization of accident insurance Claims Resolution of client.
On the one hand, the invention provides long-range setting loss based on distributed artificial intelligence image recognition Method, including:
S1: image capture device carry out accident vehicle appearance member image acquisition and be sent in cloud put down Platform；
S2: obtain crash data information by onboard sensor equipment, and set by onboard sensor For being uploaded to cloud platform；
S3: image processing module carries out pretreatment for the appearance member image of accident vehicle collection, And the result of Image semantic classification is stored in car damage identification data base；Image characteristics extraction module Result for Image semantic classification carries out the feature extraction of appearance member image；
S4: to obtained pretreatment accident vehicle appearance member image feature information and car damage identification number Carry out images match according to the image library in storehouse, thus obtain thing by vehicle appearance part setting loss model Therefore the appearance member setting loss result of vehicle；
S5: obtained accident vehicle by car accident type decision model by appearance member setting loss result Collision accident type；The car load setting loss of accident vehicle is obtained again by car load accident setting loss model Result；
S6: obtained the settlement of insurance claim side of car load according to car load setting loss result by setting loss single module Case；The settlement of insurance claim scheme of accident vehicle is sent to user by network.
Concrete, crash data information in step S2, including 3-axis acceleration, three shaft angle speed The data such as degree, audio frequency, video.
Concrete, step S3 carries out pretreatment to appearance member image, including gray proces, Image lattice figure extracts, anamorphose bitmap extracts, pattern colour difference is joined.
Concrete, feature extraction to appearance member image in step S3, including the deformation of image The distribution of scope, gradation of image and co-occurrence matrix, anamorphose ratio, color of image value side figure, figure The aggregated vector of picture, the autoregression texture model of image, image wavelet transform.
Concrete, car damage identification data base in step S3, particularly as follows:
The first step, after obtaining the appearance member view data of accident vehicle, obtained appearance member figure As data are stored in car damage identification data base as appearance member original image storehouse；
Second step, for the accident sample obtained by true accident and collision simulation analysis, By automatic setting loss module obtain based on setting loss such as vehicle, accessory appearance setting loss, accident patterns Result is stored in car damage identification data base as setting loss total data storehouse.
3rd step, by the Image semantic classification result data obtained by image processing module, is stored in car As appearance member pre-processed results data base in setting loss data base；
4th step, by the image characteristics extraction result data obtained by image characteristics extraction module, It is stored in car damage identification data base as appearance member image feature base；
5th step, obtains 3-axis acceleration, three axis angular rates, audio frequency, vedio data, It is stored in car damage identification data base as original collision information data base；
6th step, to 3-axis acceleration, three axis angular rate data by colliding its signal Information retrieval also carries out Filtering Processing, and the result after process is stored in conduct in car damage identification data base Secondary collision information database；After voice data is carried out denoising, Filtering Processing, result is stored in car As secondary audio database in setting loss data base；Video image is carried out gradation of image etc. pre- As secondary video data base during after process, result is stored in car damage identification data base；
7th step, is carried out for different types of data from the secondary data storehouse of car damage identification data base Feature extraction is stored in car damage identification data base as collision information property data base；
8th step, according to the setting loss data of collision simulation accident reproduction set up based on vehicle, based on Position, maintenance program based on part, and be stored in car damage identification data base as vehicle maintenance Storehouse.
More specifically, setting loss total data storehouse includes three below divided data storehouse:
1) set up damage rank according to vehicle according to different outward appearance parts and be stored in car damage identification number Rank storehouse is damaged as appearance member according in storehouse；
2) set up accidents classification rule and type according to the data of collision simulation accident reproduction, and deposit Enter in car damage identification data base as accident pattern storehouse；
3) it is stored in car damage identification data base according to accident of setting up with the mapping relations damaging rank to make For car load setting loss storehouse.
On the other hand, present invention also offers a kind of based on distributed artificial intelligence image recognition Remotely loss assessment system, including:
Image capture device, carry out accident vehicle appearance member image acquisition and be sent in cloud put down Platform；
Onboard sensor equipment, it is thus achieved that crash data information, and uploaded by onboard sensor equipment To cloud platform；
Image processing module, the appearance member image for accident vehicle collection carries out pretreatment, and The result of Image semantic classification is stored in car damage identification data base；
Image characteristics extraction module, carries out the spy of appearance member image for the result of Image semantic classification Levy extraction；
Appearance member setting loss object module, to obtained pretreatment accident vehicle appearance member characteristics of image Information carries out images match with the image library in car damage identification data base, thus passes through vehicle appearance Part setting loss model obtains the appearance member setting loss result of accident vehicle；
Car load setting loss result, is obtained by car accident type decision model by appearance member setting loss result Collision accident type to accident vehicle；Accident vehicle is obtained again by car load accident setting loss model Car load setting loss result；
Setting loss single module, is sent to user by the settlement of insurance claim scheme of accident vehicle by network.
Automatically setting loss module, a large amount of according to obtained by true accident and collision accident simulation analysis Data sample, carries out data classification, data prediction, in conjunction with setting loss expertise and automatically determines Damage method, it is achieved the automatic setting loss of accident vehicle；
Car damage identification data base, stores various data.
Further, vehicle appearance part setting loss model, is image recognition side based on artificial intelligence Method and gradation of image matching process, use Si ft Feature Correspondence Algorithm, template matching algorithm, Information integration image recognition algorithm, sets up relevant picture recognition module, is encapsulated as in the middle of platform One of part.
Further, car accident type decision model, is to use decision tree, random forest people Work intellectual learning method and the method for normalizing of correlation rule, set up relevant car accident type Determination module, is encapsulated as one of platform middleware.
Further, SVM, BP neutral net artificial intelligence's learning method and incidence number are used According to method for normalizing, and set up relevant car load accident setting loss module, be encapsulated as platform middleware One of.
Due to the fact that the above technical method of employing, it is possible to obtain following technique effect: this Bright can be quickly carried out accident appearance member setting loss, after occurring especially for low speed collision accident, Major part Claims Resolution occurs mainly in vehicle appearance part, so remotely setting loss is first precisely fixed by appearance member Damage can improve Claims Resolution precision and the efficiency of long-range setting loss；Can quickly judge accident pattern and accident Responsibility, accelerates Claims Resolution efficiency, and can carry out Claims Resolution reference in conjunction with conventional Claims Resolution event；This The bright overall setting loss result that can also provide accident vehicle and provide the Claims Resolution of the other side's accident vehicle Scope.
On the one hand the application solves setting loss person and carries out the subjectivity of setting loss and reduce associating insurance fraud Probability；On the other hand can avoid the expense of disassembling of accident vehicle, thus be greatly promoted and protecting visitor The satisfaction at family and the standardization of accident insurance Claims Resolution.
Accompanying drawing explanation
For clearer explanation embodiments of the invention or the technical scheme of prior art, below Introduce the accompanying drawing used required in embodiment or description of the prior art is done one simply, aobvious And easy insight, the accompanying drawing in describing below is only some embodiments of the present invention, for ability From the point of view of the those of ordinary skill of territory, on the premise of not paying creative work, it is also possible to according to this A little accompanying drawings obtain other accompanying drawing.
Fig. 1 is long-range loss assessment system based on distributed artificial intelligence image recognition structural representation Figure.
Fig. 2 is long-range setting loss flowage structure based on distributed artificial intelligence image recognition signal Figure.
Detailed description of the invention
For making the purpose of embodiments of the invention, technical scheme and advantage clearer, knot below Close the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out the completeest Whole description:
Embodiment 1
Long-range damage identification method based on distributed artificial intelligence image recognition, including:
S1: image capture device, described image capture device can be mobile phone or picture pick-up device, Carry out the appearance member image acquisition of accident vehicle and be sent in cloud platform by mobile phone A PP；
S2: obtain crash data information, described crash data by vehicle-mounted OBD sensor device Information includes the data such as 3-axis acceleration, three axis angular rates, audio frequency, video, and by vehicle-mounted OBD sensor device is uploaded to cloud platform；
S3: image processing module carries out pretreatment for the appearance member image of accident vehicle collection, Described appearance member image carries out pretreatment and includes that gray proces, image lattice figure extract, image becomes The pre-processing image data such as bitmap extracts, pattern colour difference is joined；And by the knot of Image semantic classification Fruit is stored in car damage identification data base；Image characteristics extraction module is for the knot of Image semantic classification Fruit carries out the feature extraction of appearance member image, described feature extraction include image deformation range, Gradation of image distribution and co-occurrence matrix, anamorphose ratio, color of image value side figure, image poly- The characteristics of image such as resultant vector, the autoregression texture model of image, image wavelet transform；
S4: to obtained pretreatment accident vehicle appearance member image feature information and car damage identification number Carry out images match according to the image library in storehouse, thus obtain thing by vehicle appearance part setting loss model Therefore the appearance member setting loss result of vehicle；
S5: obtained accident vehicle by car accident type decision model by appearance member setting loss result Collision accident type；The car load setting loss of accident vehicle is obtained again by car load accident setting loss model Result；
S6: obtained the settlement of insurance claim side of car load according to car load setting loss result by setting loss single module Case；The settlement of insurance claim scheme of accident vehicle is sent to user's by network by final insurance company Mobile phone insurance APP software.
On the other hand, present invention also offers a kind of based on distributed artificial intelligence image recognition Remotely loss assessment system, including:
Image capture device, carry out accident vehicle appearance member image acquisition and be sent in cloud put down Platform；
Vehicle-mounted OBD sensor device, it is thus achieved that crash data information, described crash data information bag Include the data such as 3-axis acceleration, three axis angular rates, audio frequency, video, and sensed by vehicle-mounted OBD Device equipment is uploaded to cloud platform；
Image processing module, the appearance member image for accident vehicle collection carries out pretreatment, and The result of Image semantic classification is stored in car damage identification data base；
Image characteristics extraction module, carries out the spy of appearance member image for the result of Image semantic classification Levy extraction；Described feature extraction includes the distribution of the deformation range of image, gradation of image and symbiosis square Battle array, anamorphose ratio, color of image value side figure, the aggregated vector of image, the autoregression of image The characteristics of image such as texture model, image wavelet transform；
Appearance member setting loss object module, to obtained pretreatment accident vehicle appearance member characteristics of image Information carries out images match with the image library in car damage identification data base, thus passes through vehicle appearance Part setting loss model obtains the appearance member setting loss result of accident vehicle；
Car load setting loss result, is obtained by car accident type decision model by appearance member setting loss result Collision accident type to accident vehicle；Accident vehicle is obtained again by car load accident setting loss model Car load setting loss result；
Setting loss single module, obtains the settlement of insurance claim scheme of car load；Final insurance company is by accident vehicle Settlement of insurance claim scheme by network be sent to user mobile phone insurance APP software.
Automatically setting loss module, a large amount of according to obtained by true accident and collision accident simulation analysis Data sample, carries out data classification, data prediction, in conjunction with setting loss expertise and automatically determines Damage method, as curvilinear motion etc. realized thing in energy variation, the deformation of vehicle part, material Therefore the automatic setting loss of vehicle；
Car damage identification data base, stores various data.
Embodiment 2
The technical scheme the most identical with embodiment 1, more specifically, wherein car damage identification Data base, particularly as follows:
The first step, after obtaining the appearance member view data of accident vehicle, is on the one hand adopted by image Collection equipment, such as mobile phone or picture pick-up device, on the other hand passes through collision simulation analysis, by institute The appearance member view data obtained is stored in car damage identification data base as appearance member original image Storehouse；
Second step, for the accident sample obtained by true accident and collision simulation analysis, By automatic setting loss module obtain based on setting loss such as vehicle, accessory appearance setting loss, accident patterns Result is stored in car damage identification data base as setting loss total data storehouse.
3rd step, by the Image semantic classification result data obtained by image processing module, is stored in car As appearance member pre-processed results data base in setting loss data base；
4th step, by the image characteristics extraction result data obtained by image characteristics extraction module, It is stored in car damage identification data base as appearance member image feature base；
5th step, obtains 3-axis acceleration, three axis angular rates, audio frequency, vedio data, On the one hand by vehicle OBD sensor device, on the other hand by collision simulation analysis, The data obtained is stored in car damage identification data base as original collision information data base；
6th step, to 3-axis acceleration, three axis angular rate data by colliding its signal Information retrieval also carries out Filtering Processing, and the result after process is stored in conduct in car damage identification data base Secondary collision information database；After voice data is carried out denoising, Filtering Processing, result is stored in car As secondary audio database in setting loss data base；Video image, such as collision simulation are produced The part injury picture for collision accident animation and accident vehicle, carry out the pre-places such as gradation of image As secondary video data base during after reason, result is stored in car damage identification data base；
7th step, is carried out for different types of data from the secondary data storehouse of car damage identification data base Feature extraction is stored in car damage identification data base as collision information property data base；
8th step, according to the setting loss data of collision simulation accident reproduction set up based on vehicle, based on Position, maintenance program based on part, and be stored in car damage identification data base as vehicle maintenance Storehouse.
Embodiment 3
The technical scheme the most identical with embodiment 1, more specifically, wherein setting loss sum According to storehouse, particularly as follows:
1) set up damage rank according to vehicle according to different outward appearance parts and be stored in car damage identification number Rank storehouse is damaged as appearance member according in storehouse；
2) set up accidents classification rule and type according to the data of collision simulation accident reproduction, and deposit Enter in car damage identification data base as accident pattern storehouse；
3) it is stored in car damage identification data base according to accident of setting up with the mapping relations damaging rank to make For car load setting loss storehouse.
Embodiment 4
In order to be quickly carried out accident appearance member setting loss, occur especially for low speed collision accident After, major part Claims Resolution occurs mainly in vehicle appearance part, therefore provides vehicle appearance part setting loss mould Type, is image-recognizing method based on artificial intelligence and gradation of image matching process, uses Si ft Feature Correspondence Algorithm, template matching algorithm, information integration image recognition algorithm etc., set up relevant Picture recognition module, be encapsulated as one of platform middleware.
In order to quickly judge accident pattern and accident responsibility, efficiency of settling a claim can be accelerated, therefore provide Car accident type decision model, is to use the artificial intellectual learning side such as decision tree, random forest Method and the method for normalizing of correlation rule, set up relevant car accident type decision module, envelope Dress is one of platform middleware.
On the one hand realizing providing the overall setting loss result of accident vehicle, it is right that another aspect realization is given The Claims Resolution scope of side's accident vehicle.Therefore provide car load accident setting loss model, use SVM, BP The artificial intellectual learning method such as neutral net and associated data method for normalizing, and set up relevant Car load accident setting loss module, is encapsulated as one of platform middleware.
Embodiment 5
Supplementing as embodiment 1-4, sets up settlement of insurance claim system based on WEB in this embodiment System network environment infrastructure；APP towards vehicle insurance user；In the application of insurance company Between part, various resources in encapsulation network environment, and provide interface to integrated platform, it is fixed to use Damage the form encapsulation setting loss application middleware of Web service, by each list of setting loss workflow composing Only functional realiey and service；Setting loss job stream of network realize based on setting loss Web service Information sharing is integrated with application, on final setting loss integrated platform, provides in a transparent manner Setting loss services, and comprises Claims Resolution scheme and maintenance analysis service, and allows insurance company to move with the insured State is registered, is nullified and manage respective resource and service, it is achieved setting loss procedure, standardization.
The above, the only present invention preferably detailed description of the invention, but the protection model of the present invention Enclosing and be not limited thereto, any those familiar with the art is in the skill of present disclosure In the range of art, according to technical scheme and inventive concept equivalent in addition thereof or change Become, all should contain within protection scope of the present invention.

Claims (10)

1. long-range damage identification method based on distributed artificial intelligence image recognition, it is characterised in that bag Include:
S1: image capture device carry out accident vehicle appearance member image acquisition and be sent in cloud put down Platform；
S2: obtain crash data information by onboard sensor equipment, and set by onboard sensor For being uploaded to cloud platform；
S3: image processing module carries out pretreatment for the appearance member image of accident vehicle collection, And the result of Image semantic classification is stored in car damage identification data base；Image characteristics extraction module Result for Image semantic classification carries out the feature extraction of appearance member image；
S4: to obtained pretreatment accident vehicle appearance member image feature information and car damage identification number Carry out images match according to the image library in storehouse, thus obtain thing by vehicle appearance part setting loss model Therefore the appearance member setting loss result of vehicle；
S5: obtained accident vehicle by car accident type decision model by appearance member setting loss result Collision accident type；The car load setting loss of accident vehicle is obtained again by car load accident setting loss model Result；
S6: obtained the settlement of insurance claim side of car load according to car load setting loss result by setting loss single module Case；The settlement of insurance claim scheme of accident vehicle is sent to user by network the most at last.
Long-range setting loss based on distributed artificial intelligence image recognition the most according to claim 1 Method, it is characterised in that crash data information in step S2, including 3-axis acceleration, three The data such as axis angular rate, audio frequency, video.
Long-range setting loss based on distributed artificial intelligence image recognition the most according to claim 1 Method, it is characterised in that in step S3, appearance member image is carried out pretreatment, including gray scale Process, image lattice figure extracts, anamorphose bitmap extracts, pattern colour difference is joined.
Long-range setting loss based on distributed artificial intelligence image recognition the most according to claim 1 Method, it is characterised in that feature extraction to appearance member image in step S3, including image Deformation range, gradation of image distribution and co-occurrence matrix, anamorphose ratio, color of image value side Figure, the aggregated vector of image, the autoregression texture model of image, image wavelet transform.
Long-range setting loss based on distributed artificial intelligence image recognition the most according to claim 1 Method, it is characterised in that car damage identification data base in step S3, particularly as follows:
The first step, after obtaining the appearance member view data of accident vehicle, obtained appearance member figure As data are stored in car damage identification data base as appearance member original image storehouse；
Second step, for the accident sample obtained by true accident and collision simulation analysis, By automatic setting loss module obtain based on setting loss such as vehicle, accessory appearance setting loss, accident patterns Result is stored in car damage identification data base as setting loss total data storehouse.
3rd step, by the Image semantic classification result data obtained by image processing module, is stored in car As appearance member pre-processed results data base in setting loss data base；
4th step, by the image characteristics extraction result data obtained by image characteristics extraction module, It is stored in car damage identification data base as appearance member image feature base；
5th step, obtains 3-axis acceleration, three axis angular rates, audio frequency, vedio data, It is stored in car damage identification data base as original collision information data base；
6th step, to 3-axis acceleration, three axis angular rate data by colliding its signal Information retrieval also carries out Filtering Processing, and the result after process is stored in conduct in car damage identification data base Secondary collision information database；After voice data is carried out denoising, Filtering Processing, result is stored in car As secondary audio database in setting loss data base；Video image is carried out gradation of image etc. pre- As secondary video data base during after process, result is stored in car damage identification data base；
7th step, is carried out for different types of data from the secondary data storehouse of car damage identification data base Feature extraction is stored in car damage identification data base as collision information property data base；
8th step, according to the setting loss data of collision simulation accident reproduction set up based on vehicle, based on Position, maintenance program based on part, and be stored in car damage identification data base as vehicle maintenance Storehouse.
Long-range setting loss based on distributed artificial intelligence image recognition the most according to claim 5 Method, it is characterised in that setting loss total data storehouse includes three below divided data storehouse:
1) set up damage rank according to vehicle according to different outward appearance parts and be stored in car damage identification number Rank storehouse is damaged as appearance member according in storehouse；
2) set up accidents classification rule and type according to the data of collision simulation accident reproduction, and deposit Enter in car damage identification data base as accident pattern storehouse；
3) it is stored in car damage identification data base according to accident of setting up with the mapping relations damaging rank to make For car load setting loss storehouse.
7. long-range loss assessment system based on distributed artificial intelligence image recognition, it is characterised in that bag Include:
Image capture device, carry out accident vehicle appearance member image acquisition and be sent in cloud put down Platform；
Onboard sensor equipment, it is thus achieved that crash data information, and uploaded by onboard sensor equipment To cloud platform；
Image processing module, the appearance member image for accident vehicle collection carries out pretreatment, and The result of Image semantic classification is stored in car damage identification data base；
Image characteristics extraction module, carries out the spy of appearance member image for the result of Image semantic classification Levy extraction；
Appearance member setting loss object module, to obtained pretreatment accident vehicle appearance member characteristics of image Information carries out images match with the image library in car damage identification data base, thus passes through vehicle appearance Part setting loss model obtains the appearance member setting loss result of accident vehicle；
Car load setting loss result, is obtained by car accident type decision model by appearance member setting loss result Collision accident type to accident vehicle；Accident vehicle is obtained again by car load accident setting loss model Car load setting loss result；
Setting loss single module, is sent to user by the settlement of insurance claim scheme of accident vehicle by network.
Automatically setting loss module, a large amount of according to obtained by true accident and collision accident simulation analysis Data sample, carries out data classification, data prediction, in conjunction with setting loss expertise and automatically determines Damage method, it is achieved the automatic setting loss of accident vehicle；
Car damage identification data base, stores various data.
Long-range setting loss based on distributed artificial intelligence image recognition the most according to claim 7 System, it is characterised in that including: vehicle appearance part setting loss model, based on artificial intelligence Image-recognizing method and gradation of image matching process, use Sift Feature Correspondence Algorithm, template Matching algorithm, information integration image recognition algorithm, set up relevant picture recognition module, encapsulation For one of platform middleware.
Long-range setting loss based on distributed artificial intelligence image recognition the most according to claim 7 System, it is characterised in that car accident type decision model, is to use decision tree, the most gloomy Woods artificial intelligence's learning method and the method for normalizing of correlation rule, set up relevant car accident Type decision module, is encapsulated as one of platform middleware.
Long-range setting loss based on distributed artificial intelligence image recognition the most according to claim 7 System, it is characterised in that use SVM, BP neutral net artificial intelligence's learning method and association Data normalization method, and set up relevant car load accident setting loss module, it is encapsulated as in the middle of platform One of part.
CN201610365742.3A 2016-05-27 2016-05-27 Remote damage assessment method and system based on distributed artificial intelligent image recognition Pending CN106021548A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610365742.3A CN106021548A (en) 2016-05-27 2016-05-27 Remote damage assessment method and system based on distributed artificial intelligent image recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610365742.3A CN106021548A (en) 2016-05-27 2016-05-27 Remote damage assessment method and system based on distributed artificial intelligent image recognition

Publications (1)

Publication Number Publication Date
CN106021548A true CN106021548A (en) 2016-10-12

Family

ID=57092335

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610365742.3A Pending CN106021548A (en) 2016-05-27 2016-05-27 Remote damage assessment method and system based on distributed artificial intelligent image recognition

Country Status (1)

Country Link
CN (1) CN106021548A (en)

Cited By (41)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN106599093A (en) * 2016-11-25 2017-04-26 中国平安财产保险股份有限公司 Car insurance intelligent loss assessment platform-based database calling 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
CN106803205A (en) * 2016-12-27 2017-06-06 北京量子保科技有限公司 A kind of system and method for insuring from kinetonucleus compensation
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
CN107392218A (en) * 2017-04-11 2017-11-24 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
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
CN107862614A (en) * 2017-11-08 2018-03-30 广东翼卡车联网服务有限公司 A kind of method, storage device and car-mounted terminal for preventing vehicle insurance insurance fraud
CN107886436A (en) * 2017-11-08 2018-04-06 广东翼卡车联网服务有限公司 Method, storage medium and the car-mounted terminal that a kind of car insurance is settled a claim automatically
CN108257066A (en) * 2018-01-30 2018-07-06 重庆穗丰汽车救援有限公司 A kind of vehicular rescue service system
CN108269397A (en) * 2017-12-27 2018-07-10 深圳市元征软件开发有限公司 The processing method and mobile unit of a kind of highway traffic data
CN108282536A (en) * 2018-01-30 2018-07-13 重庆穗丰汽车救援有限公司 A kind of shared rescue system of vehicle
CN108323209A (en) * 2018-01-29 2018-07-24 深圳前海达闼云端智能科技有限公司 Information processing method, system, cloud processing device and computer program product
CN108389392A (en) * 2018-04-04 2018-08-10 广东容祺智能科技有限公司 A kind of traffic accident responsibility identification system based on machine learning
CN108600390A (en) * 2018-05-15 2018-09-28 北京首汽智行科技有限公司 A kind of shared car damage identification and Claims Resolution method and device based on region chain
CN108596047A (en) * 2018-03-30 2018-09-28 上海与德通讯技术有限公司 Vehicle damages recognition methods, intelligent terminal and computer readable storage medium
CN108769624A (en) * 2018-07-09 2018-11-06 北京精友世纪软件技术有限公司 It is a kind of intelligence vehicle insurance mobile video survey system
CN108961082A (en) * 2018-07-06 2018-12-07 北京精友世纪软件技术有限公司 A kind of vehicle insurance loss assessment system and method based on AI image recognition
CN109064341A (en) * 2018-07-06 2018-12-21 阿里巴巴集团控股有限公司 A kind of self-aided terminal, self-auxiliary device and electronic equipment
CN109215027A (en) * 2018-10-11 2019-01-15 平安科技（深圳）有限公司 A kind of car damage identification method neural network based, server and medium
CN109443301A (en) * 2018-09-25 2019-03-08 平安科技（深圳）有限公司 A kind of car damage identification method, computer readable storage medium and server
CN109677324A (en) * 2019-01-25 2019-04-26 南京北斗城际在线信息股份有限公司北京分公司 Parked vehicle collision alarm method based on NB-IoT technology
CN109948811A (en) * 2019-01-31 2019-06-28 德联易控科技(北京)有限公司 Processing method, device and the electronic equipment of car damage identification
CN110020734A (en) * 2019-04-24 2019-07-16 武汉华创欣网科技有限公司 A kind of mobile damage identification method of the vehicle remote based on big data
WO2019148732A1 (en) * 2018-02-01 2019-08-08 平安科技（深圳）有限公司 Vehicle liability cognizance method, terminal, and computer-readable storage medium
WO2019184899A1 (en) * 2018-03-26 2019-10-03 苏州山水树儿信息技术有限公司 Vehicle collision damage assessment method and system based on historical cases
CN110363670A (en) * 2018-03-26 2019-10-22 苏州山水树儿信息技术有限公司 Vehicle collision damage identification method and system based on history case
CN110389570A (en) * 2018-04-19 2019-10-29 株洲中车时代电气股份有限公司 A kind of locomotive traction system trouble-shooter and method
CN110598880A (en) * 2019-09-12 2019-12-20 神华铁路货车运输有限责任公司沧州机车车辆维修分公司 Vehicle maintenance process control method
CN110647853A (en) * 2019-09-27 2020-01-03 支付宝(杭州)信息技术有限公司 Computer-implemented vehicle damage assessment method and device
CN111339168A (en) * 2020-03-06 2020-06-26 德联易控科技(北京)有限公司 Data processing method, device, system, storage medium and processor
CN111806458A (en) * 2020-06-22 2020-10-23 中国平安财产保险股份有限公司 Unmanned vehicle reporting method and device, unmanned vehicle and storage medium
CN111914692A (en) * 2017-04-28 2020-11-10 创新先进技术有限公司 Vehicle loss assessment image acquisition method and device
CN112269978A (en) * 2020-10-22 2021-01-26 支付宝(杭州)信息技术有限公司 Image acquisition method and device
CN112446513A (en) * 2020-12-15 2021-03-05 恒大恒驰新能源汽车研究院(上海)有限公司 Vehicle part detection method and device and computer readable storage medium
CN112948962A (en) * 2021-01-29 2021-06-11 东风商用车有限公司 Method and device for quickly building vehicle appearance
CN113177536A (en) * 2021-06-28 2021-07-27 四川九通智路科技有限公司 Vehicle collision detection method and device based on deep residual shrinkage network
CN113538193A (en) * 2021-06-30 2021-10-22 东莞市绿灯网络科技有限公司 Traffic accident handling method and system based on artificial intelligence and computer vision
CN113902045A (en) * 2021-12-09 2022-01-07 成都车晓科技有限公司 Vehicle insurance field rapid damage assessment method based on image recognition
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

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN104268783A (en) * 2014-05-30 2015-01-07 翱特信息系统（中国）有限公司 Vehicle loss assessment method and device and terminal device
CN105096198A (en) * 2015-09-02 2015-11-25 郁佳敏 Automobile insurance accident remote network survey instrument and remote reporting and surveying method thereof
CN105182535A (en) * 2015-09-28 2015-12-23 大连楼兰科技股份有限公司 Method of using intelligent glasses for vehicle maintenance
US20160012539A1 (en) * 2014-07-10 2016-01-14 Audatex North America, Inc. Mobile total loss vehicle evaluation system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN104268783A (en) * 2014-05-30 2015-01-07 翱特信息系统（中国）有限公司 Vehicle loss assessment method and device and terminal device
US20160012539A1 (en) * 2014-07-10 2016-01-14 Audatex North America, Inc. Mobile total loss vehicle evaluation system
CN105096198A (en) * 2015-09-02 2015-11-25 郁佳敏 Automobile insurance accident remote network survey instrument and remote reporting and surveying method thereof
CN105182535A (en) * 2015-09-28 2015-12-23 大连楼兰科技股份有限公司 Method of using intelligent glasses for vehicle maintenance

Cited By (60)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN106599093A (en) * 2016-11-25 2017-04-26 中国平安财产保险股份有限公司 Car insurance intelligent loss assessment platform-based database calling 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
CN106803205A (en) * 2016-12-27 2017-06-06 北京量子保科技有限公司 A kind of system and method for insuring from kinetonucleus compensation
CN107392218B (en) * 2017-04-11 2020-08-04 创新先进技术有限公司 Vehicle loss assessment method and device based on image and electronic equipment
CN112435215A (en) * 2017-04-11 2021-03-02 创新先进技术有限公司 Vehicle loss assessment method based on image, mobile terminal and server
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
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
CN112435215B (en) * 2017-04-11 2024-02-13 创新先进技术有限公司 Image-based vehicle damage assessment method, mobile terminal and server
US10817956B2 (en) 2017-04-11 2020-10-27 Alibaba Group Holding Limited Image-based vehicle damage determining method and apparatus, and electronic device
CN107392218A (en) * 2017-04-11 2017-11-24 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
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
CN111914692A (en) * 2017-04-28 2020-11-10 创新先进技术有限公司 Vehicle loss assessment image acquisition method and device
CN111914692B (en) * 2017-04-28 2023-07-14 创新先进技术有限公司 Method and device for acquiring damage assessment image of vehicle
CN107886436A (en) * 2017-11-08 2018-04-06 广东翼卡车联网服务有限公司 Method, storage medium and the car-mounted terminal that a kind of car insurance is settled a claim automatically
CN107862614A (en) * 2017-11-08 2018-03-30 广东翼卡车联网服务有限公司 A kind of method, storage device and car-mounted terminal for preventing vehicle insurance insurance fraud
CN108269397A (en) * 2017-12-27 2018-07-10 深圳市元征软件开发有限公司 The processing method and mobile unit of a kind of highway traffic data
CN108323209A (en) * 2018-01-29 2018-07-24 深圳前海达闼云端智能科技有限公司 Information processing method, system, cloud processing device and computer program product
CN108323209B (en) * 2018-01-29 2023-10-31 达闼机器人股份有限公司 Information processing method, system, cloud processing device and computer storage medium
CN108282536A (en) * 2018-01-30 2018-07-13 重庆穗丰汽车救援有限公司 A kind of shared rescue system of vehicle
CN108257066A (en) * 2018-01-30 2018-07-06 重庆穗丰汽车救援有限公司 A kind of vehicular rescue service system
WO2019148732A1 (en) * 2018-02-01 2019-08-08 平安科技（深圳）有限公司 Vehicle liability cognizance method, terminal, and computer-readable storage medium
WO2019184899A1 (en) * 2018-03-26 2019-10-03 苏州山水树儿信息技术有限公司 Vehicle collision damage assessment method and system based on historical cases
CN110363670A (en) * 2018-03-26 2019-10-22 苏州山水树儿信息技术有限公司 Vehicle collision damage identification method and system based on history case
CN111886619A (en) * 2018-03-26 2020-11-03 苏州山水树儿信息技术有限公司 Vehicle collision damage assessment method and system based on historical case
CN108596047A (en) * 2018-03-30 2018-09-28 上海与德通讯技术有限公司 Vehicle damages recognition methods, intelligent terminal and computer readable storage medium
CN108389392A (en) * 2018-04-04 2018-08-10 广东容祺智能科技有限公司 A kind of traffic accident responsibility identification system based on machine learning
CN110389570A (en) * 2018-04-19 2019-10-29 株洲中车时代电气股份有限公司 A kind of locomotive traction system trouble-shooter and method
CN108600390A (en) * 2018-05-15 2018-09-28 北京首汽智行科技有限公司 A kind of shared car damage identification and Claims Resolution method and device based on region chain
CN109064341A (en) * 2018-07-06 2018-12-21 阿里巴巴集团控股有限公司 A kind of self-aided terminal, self-auxiliary device and electronic equipment
CN108961082A (en) * 2018-07-06 2018-12-07 北京精友世纪软件技术有限公司 A kind of vehicle insurance loss assessment system and method based on AI image recognition
CN108769624A (en) * 2018-07-09 2018-11-06 北京精友世纪软件技术有限公司 It is a kind of intelligence vehicle insurance mobile video survey system
CN108769624B (en) * 2018-07-09 2020-09-22 北京精友世纪软件技术有限公司 Intelligent automobile insurance mobile video surveying system
CN109443301B (en) * 2018-09-25 2021-09-10 平安科技（深圳）有限公司 Vehicle loss assessment method, computer readable storage medium and server
CN109443301A (en) * 2018-09-25 2019-03-08 平安科技（深圳）有限公司 A kind of car damage identification method, computer readable storage medium and server
CN109215027A (en) * 2018-10-11 2019-01-15 平安科技（深圳）有限公司 A kind of car damage identification method neural network based, server and medium
CN109677324B (en) * 2019-01-25 2021-01-29 柳笛科技(北京)有限公司 Parking vehicle collision alarm method based on NB-IoT technology
CN109677324A (en) * 2019-01-25 2019-04-26 南京北斗城际在线信息股份有限公司北京分公司 Parked vehicle collision alarm method based on NB-IoT technology
CN109948811A (en) * 2019-01-31 2019-06-28 德联易控科技(北京)有限公司 Processing method, device and the electronic equipment of car damage identification
CN110020734A (en) * 2019-04-24 2019-07-16 武汉华创欣网科技有限公司 A kind of mobile damage identification method of the vehicle remote based on big data
CN110598880B (en) * 2019-09-12 2022-04-19 神华铁路货车运输有限责任公司沧州机车车辆维修分公司 Vehicle maintenance process control method
CN110598880A (en) * 2019-09-12 2019-12-20 神华铁路货车运输有限责任公司沧州机车车辆维修分公司 Vehicle maintenance process control method
CN110647853A (en) * 2019-09-27 2020-01-03 支付宝(杭州)信息技术有限公司 Computer-implemented vehicle damage assessment method and device
CN111339168B (en) * 2020-03-06 2023-08-22 德联易控科技(北京)有限公司 Data processing method, device, system, storage medium and processor
CN111339168A (en) * 2020-03-06 2020-06-26 德联易控科技(北京)有限公司 Data processing method, device, system, storage medium and processor
CN111806458A (en) * 2020-06-22 2020-10-23 中国平安财产保险股份有限公司 Unmanned vehicle reporting method and device, unmanned vehicle and storage medium
CN111806458B (en) * 2020-06-22 2022-04-22 中国平安财产保险股份有限公司 Unmanned vehicle reporting method and device, unmanned vehicle and storage medium
CN112269978B (en) * 2020-10-22 2022-11-15 蚂蚁胜信(上海)信息技术有限公司 Image acquisition method and device
CN112269978A (en) * 2020-10-22 2021-01-26 支付宝(杭州)信息技术有限公司 Image acquisition method and device
CN112446513A (en) * 2020-12-15 2021-03-05 恒大恒驰新能源汽车研究院(上海)有限公司 Vehicle part detection method and device and computer readable storage medium
CN112948962B (en) * 2021-01-29 2023-09-01 东风商用车有限公司 Quick vehicle appearance construction method and device
CN112948962A (en) * 2021-01-29 2021-06-11 东风商用车有限公司 Method and device for quickly building vehicle appearance
US11971953B2 (en) 2021-02-02 2024-04-30 Inait Sa Machine annotation of photographic images
US11544914B2 (en) 2021-02-18 2023-01-03 Inait Sa Annotation of 3D models with signs of use visible in 2D images
CN113177536A (en) * 2021-06-28 2021-07-27 四川九通智路科技有限公司 Vehicle collision detection method and device based on deep residual shrinkage network
CN113538193A (en) * 2021-06-30 2021-10-22 东莞市绿灯网络科技有限公司 Traffic accident handling method and system based on artificial intelligence and computer vision
CN113902045B (en) * 2021-12-09 2022-04-01 成都车晓科技有限公司 Vehicle insurance field rapid damage assessment method based on image recognition
CN113902045A (en) * 2021-12-09 2022-01-07 成都车晓科技有限公司 Vehicle insurance field rapid damage assessment method based on image recognition

Similar Documents

Publication Publication Date Title
CN106021548A (en) Remote damage assessment method and system based on distributed artificial intelligent image recognition
CN111784685B (en) Power transmission line defect image identification method based on cloud edge cooperative detection
CN108596277B (en) Vehicle identity recognition method and device and storage medium
CN106778684A (en) deep neural network training method and face identification method
CN104166841B (en) The quick detection recognition methods of pedestrian or vehicle is specified in a kind of video surveillance network
CN108717524B (en) Gesture recognition system based on double-camera mobile phone and artificial intelligence system
CN103218831A (en) Video moving target classification and identification method based on outline constraint
CN106815560B (en) Face recognition method applied to self-adaptive driving seat
CN107194371B (en) User concentration degree identification method and system based on hierarchical convolutional neural network
CN103020992B (en) A kind of video image conspicuousness detection method based on motion color-associations
CN106022929A (en) Collision accident loss estimating method and system based on expert system
CN106599925A (en) Plant leaf identification system and method based on deep learning
CN109359666A (en) A kind of model recognizing method and processing terminal based on multiple features fusion neural network
CN109672863A (en) A kind of construction personnel's safety equipment intelligent monitoring method based on image recognition
CN108615226A (en) A kind of image defogging method fighting network based on production
CN106250838A (en) vehicle identification method and system
CN109935080A (en) The monitoring system and method that a kind of vehicle flowrate on traffic route calculates in real time
CN105915853A (en) Remote unmanned loss assessment method and remote unmanned loss assessment system based on infrared sensing
CN109063789A (en) The classification method of shaft tower and power line, device and system
CN110427821A (en) A kind of method for detecting human face and system based on lightweight convolutional neural networks
CN111382808A (en) Vehicle detection processing method and device
CN102819747B (en) Method for automatically classifying forestry service images
CN109583349A (en) A kind of method and system for being identified in color of the true environment to target vehicle
CN104143091A (en) Single-sample face recognition method based on improved mLBP
CN106056451A (en) Vehicle OBD sensor-based remote unmanned loss assessment system

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: 20161012