CN105976449A - Remote automatic damage assessment and collision detection method and system for vehicle - Google Patents
Remote automatic damage assessment and collision detection method and system for vehicle Download PDFInfo
- Publication number
- CN105976449A CN105976449A CN201610365730.0A CN201610365730A CN105976449A CN 105976449 A CN105976449 A CN 105976449A CN 201610365730 A CN201610365730 A CN 201610365730A CN 105976449 A CN105976449 A CN 105976449A
- Authority
- CN
- China
- Prior art keywords
- collision
- data
- vehicle
- detection
- setting loss
- 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
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
Abstract
The invention provides a remote automatic damage assessment and collision detection method and system for a vehicle. The method includes the steps of establishment of a collision detection module, training of the collision detection module, preliminary collision detection, collision signal acquisition and secondary collision detection and judgment. The method and system are designed targeted to variability of multiple factors in the determining process of a damage-level judgment model, time and place of vehicle collision can be automatically judged at the second level, therefore the insurance fraud phenomena of forged accidents in the vehicle claim process are reduced, and meanwhile timeliness of settlement of insurance claims is improved.
Description
Technical field
The invention belongs to vehicle remote automatic setting loss field, the specifically automatic setting loss of vehicle remote
Collision checking method and system.
Background technology
Vehicle low-speed motion, including low speed links traveling, vehicle parking etc..Low-speed motion process
In collision accident be the class that in vehicle accident, proportion is maximum.Collision rift, insurance company is resonable
The artificial setting loss mode subjectivity used during compensation is strong, often results in Claims Resolution dispute.Additionally,
Tradition setting loss is disassembled in order to the accuracy of accident vehicle setting loss needs to carry out vehicle, and this most additionally increases
Add the expense of settlement of insurance claim.Remote auto loss assessment system, on the one hand solves setting loss person and carries out
The subjectivity of setting loss and the probability of minimizing associating insurance fraud;On the other hand tearing open of accident vehicle can be avoided
Solution expense, thus be greatly promoted and protecting satisfaction and the standardization of accident insurance Claims Resolution of client.
Remote auto setting loss technology, by the multi-signal in collection vehicle driving process, such as speed, adds
Speed, angular velocity, sound etc., use signal processing and the machine learning techniques letter to collecting
Number carry out intelligent processing method, to realize whether automatic decision collision occurs and collision rift vehicle
Damage situation.Wherein collision detection one of most important link during being this setting loss, foundation is touched
Hit process model and the signal characteristic by detection collision process judges whether collision is it
In one of key technology.
Summary of the invention
The present invention proposes a kind of vehicle remote automatic setting loss collision checking method and system, is pin
The polytropy of factors during determining in impairment scale judgment models is designed, this
Application can reach second level and automatically judge time and the place of vehicle collision, thus reduces vehicle reason
The insurance fraud phenomenon of the forgery accident during compensation, improves the ageing of settlement of insurance claim simultaneously.
On the one hand, the invention provides vehicle remote automatic setting loss collision checking method, including:
Set up the step of collision detection model, the step of training collision detection model, collision primary detection
Step, collision alarm gather step, collision secondary detection judge step.
Concrete, by analyzing when different operating mode, speed, angle, vehicles, touch
When hitting generation, vehicle produces the different characteristic of signal, sets up the collision being described collision process
Detection model.
Concrete, train collision detection model, by collision detection model is carried out simulation calculation,
Determine the signal characteristic that collision detection judges, with the machine learning algorithm such as SVM, random forest be
Core, is utilized emulation data and measured data as learning data, is set up by study and automatically sentence
The parameter model of disconnected collision, is then stored in cloud platform using this parameter model as the knowledge of computer
Knowledge base.
Concrete, collision primary detection is to set collision multiple domain by actual measurement and emulation crash data
Value judges, to occurring or the detection of the doubtful signal that collides and extraction.
Concrete, after collision primary detection, collision alarm collection is sensed by vehicle-mounted OBD
Device equipment occur or doubtful crash time, intercept certain time length monitoring signal,
Automatically data are uploaded to cloud platform.
More specifically, the step that collision secondary detection judges is specifically, upload to the number of cloud platform
According to, after filtering, after feature extraction and the pretreatment such as eigentransformation, standardization, input SVM
Collision detection model carries out computing, show whether vehicle occurs the conclusion of real collision.
On the other hand, present invention also offers a kind of vehicle remote automatic setting loss collision detection system
System, including:
Collision detection model, utilizes the data acquisition information of onboard sensor equipment, with speed,
The time domain of the signal such as acceleration, angular velocity and frequency domain character as characterising parameter, and the joining day,
Collision process, as auxiliary parameter, is carried out by the environmental information that place, audio frequency, image etc. are correlated with
Comprehensive description;
Collision detection training pattern, the ginseng to the different machines learning method such as SVM, random forest
Number optimizing and empirical data analysis;
The primary detection model of collision, is collided many thresholdings sentenced by actual measurement and emulation crash data setting
Fixed, carry out occurring or the detection of the doubtful signal that collides and extraction;
Collision detection model database, by emulation crash data, measured data and relevant pre-place
Reason data set up collision detection model database according to different machines learning method;
Onboard sensor equipment, carries out transmission and the collection of data, it is thus achieved that when doubtful accident occurs
Vehicle 3-axis acceleration, three axis angular rates, speed, the time, place, voice data,
View data;
The pretreatment module of collision alarm data: by filtering techniques such as FIR, CHE, extracts
The true waveform of signal, and select effectively to collide Expressive Features;
Collision secondary detection model, will emulate data and actual experience data combines, in big data
Realize automatic decision collision on the basis of study the most truly to occur;
Car damage identification data base, is to carry out lot of accident Sample Establishing based on emulation to obtain, according to
The accident reproduction data of collision simulation combine setting loss expert and automatic setting loss module is carried out based on often
The accident setting loss of one vehicle, thus the accident for each vehicle has only to carry out OBD data
Analyze and i.e. may know that the damage of vehicle and the setting loss of car load;
Long-range unmanned Collision Detection knowledge base: solidify the phase of long-range unmanned Collision Detection
Close knowledge and achievement.
Further, doubtful accident occur the 3-axis acceleration of moment vehicle, three axis angular rates,
Speed, time, place, voice data, view data, on the one hand can be by cloud platform
Collision Detection finally determines whether truly to there occurs collision;On the other hand collected is true
Real crash data can improve setting loss model further as the training sample of long-range setting loss model
Training precision.
Further, cloud platforms based on big data and artificial intelligence's learning method, set up vehicle
Collision detection data base/knowledge base.
More specifically, the various Resource Encapsulations in vehicle crash data storehouse accident and emulation formed
And virtualization, collision detection training pattern, pretreatment module, model database/knowledge base etc.,
It is various concrete application services by being packaged into collision detection application module, forms conformance with standard and connect
The functional module of mouth.
Due to the fact that the above technical method of employing, it is possible to obtain following technique effect: this
Bright can reach second level by vehicle remote automatic setting loss collision detection model with technology and automatically sentence
Determine time and the place of vehicle collision, thus reduce deceiving of the forgery accident during vehicle Claims Resolution
Protect phenomenon, improve the ageing of settlement of insurance claim simultaneously;Collision detection precision is high.
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 vehicle remote automatic setting loss collision detecting system structural representation.
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
The invention provides vehicle remote automatic setting loss collision checking method, including:
S1: set up the step of collision detection model, by analyzing at different operating mode, speed, angles
When degree, vehicle, when collision occurs, vehicle produces the different characteristic of signal, and foundation crashes
The collision detection model that the process of hitting is described.
S2: the step of training collision detection model, by carrying out emulation meter to collision detection model
Calculate, determine the signal characteristic that collision detection judges, with SVM (support vector machine), the most gloomy
The machine learning algorithms such as woods are core, utilize emulation data and measured data as learning data,
The parameter model of automatic decision collision is set up, then using this parameter model as calculating by study
The knowledge of machine is stored in cloud platform knowledge base.
S3: the step of collision primary detection, is to set collision by actual measurement and emulation crash data
Many thresholdings judge, to occurring or the detection of the doubtful signal that collides and extraction.
The step that S4: collision alarm gathers, after collision primary detection, collision alarm collection
By vehicle-mounted OBD sensor device occur or doubtful crash time, intercept certain
The monitoring signal of duration, such as 5s, 8s, 10s, uploads data automatically to cloud platform.
S5: the step that collision secondary detection judges, uploads to the data of cloud platform, after filtering,
After feature extraction and the pretreatment such as eigentransformation, standardization, in input SVM collision detection model
Carry out computing, show whether vehicle occurs the conclusion of real collision.This result can be as entering one
Step judges the basis signal of vehicle damage grade, for starting the judgement of impairment scale.
Embodiment 2
Present invention also offers a kind of vehicle remote automatic setting loss collision detecting system, including:
Collision detection model, utilizes the data acquisition information of onboard sensor equipment, with speed,
The time domain of the signal such as acceleration, angular velocity and frequency domain character as characterising parameter, and the joining day,
Collision process, as auxiliary parameter, is carried out by the environmental information that place, audio frequency, image etc. are correlated with
Comprehensive description;
Collision detection training pattern, machines different to SVM (support vector machine), random forest etc.
The parameter optimization of device learning method and empirical data analysis;
The primary detection model of collision, is collided many thresholdings sentenced by actual measurement and emulation crash data setting
Fixed, carry out occurring or the detection of the doubtful signal that collides and extraction;
Collision detection model database, by emulation crash data, measured data and relevant pre-place
Reason data set up collision detection model database according to different machines learning method;
Onboard sensor equipment, carries out transmission and the collection of data, it is thus achieved that when doubtful accident occurs
Vehicle 3-axis acceleration, three axis angular rates, speed, the time, place, voice data,
View data;
The pretreatment module of collision alarm data: by filtering techniques such as FIR, CHE, extracts
The true waveform of signal, and select effectively to collide Expressive Features;
Collision secondary detection model, artificial based on SVM (support vector machine), random forest etc.
Intelligent algorithm, will emulate data and actual experience data combines, on the basis of big data learn
Realize automatic decision collision the most truly to occur;
Car damage identification data base, is to carry out lot of accident Sample Establishing based on emulation to obtain, because
Have only to carry out OBD data analysis for the accident of each vehicle and i.e. may know that the damage of vehicle
Injure the setting loss of car load;
The knowledge base of long-range unmanned Collision Detection: long-range unmanned Collision Detection knowledge
Storehouse: solidify relevant knowledge and the achievement of long-range unmanned Collision Detection.
Doubtful accident occur the 3-axis acceleration of moment vehicle, three axis angular rates, speed, the time,
Place, voice data, view data, on the one hand can be by the Collision Detection of cloud platform
Finally determine whether truly to there occurs collision;On the other hand the real collision data collected can
The training precision of setting loss model is improved further using the training sample as long-range setting loss model.
Cloud platforms based on big data and artificial intelligence's learning method, set up vehicle collision detection number
According to storehouse/knowledge base.Technology base has been established in application for association areas such as the unmanned setting loss of vehicle remote
Plinth.The Test database of vehicle collision simultaneously/knowledge base also safely provides for vehicle is unmanned
Referential data information.
The various Resource Encapsulations in the vehicle crash data storehouse that accident and emulation are formed and virtualization,
Collision detection training pattern, pretreatment module, model database/knowledge base etc., will be packaged into
Collision detection application module is various concrete application services, forms the function of conformance with standard interface
Change module.
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. vehicle remote automatic setting loss collision checking method, it is characterised in that including: set up collision
The step of detection model, the step of training collision detection model, the step of collision primary detection,
The step that the step of collision alarm collection, collision secondary detection judge.
Vehicle remote the most according to claim 1 automatic setting loss collision checking method, its feature
Being, by analyzing when different operating mode, speed, angle, vehicles, collision occurs
Time vehicle produce the different characteristic of signal, set up collision detection mould that collision process is described
Type.
Vehicle remote the most according to claim 1 automatic setting loss collision checking method, its feature
It is, trains collision detection model, by collision detection model is carried out simulation calculation, determine
The signal characteristic that collision detection judges, with the machine learning algorithm such as SVM, random forest as core,
Utilize emulation data and measured data as learning data, set up automatic decision by study and collide
Parameter model, then this parameter model is stored in cloud platform knowledge as the knowledge of computer
Storehouse.
Vehicle remote the most according to claim 1 automatic setting loss collision checking method, its feature
Being, the primary detection of collision is to set the many thresholdings of collision by actual measurement and emulation crash data to sentence
Fixed, to occurring or the detection of the doubtful signal that collides and extraction.
Vehicle remote the most according to claim 1 automatic setting loss collision checking method, its feature
Being, after collision primary detection, collision alarm collection is by vehicle-mounted OBD sensor device
Occur or doubtful crash time, intercept the monitoring signal of certain time length, automatically on
Pass data to cloud platform.
Vehicle remote the most according to claim 1 automatic setting loss collision checking method, its feature
Being, the step that collision secondary detection judges, specifically, upload to the data of cloud platform, is passed through
After filtering, feature extraction and the pretreatment such as eigentransformation, standardization, input SVM collision detection
Model carries out computing, show whether vehicle occurs the conclusion of real collision.
7. a vehicle remote automatic setting loss collision detecting system, it is characterised in that including:
Collision detection model, utilizes the data acquisition information of onboard sensor equipment, with speed,
The time domain of the signal such as acceleration, angular velocity and frequency domain character as characterising parameter, and the joining day,
Collision process, as auxiliary parameter, is carried out by the environmental information that place, audio frequency, image etc. are correlated with
Comprehensive description;
Collision detection training pattern, to the optimizing of the different machines learnings method such as SVM parameter and
Empirical data is analyzed;
The primary detection model of collision, is collided many thresholdings sentenced by actual measurement and emulation crash data setting
Fixed, carry out occurring or the detection of the doubtful signal that collides and extraction;
Collision detection model database, by emulation crash data, measured data and relevant pre-place
Reason data set up collision detection model database according to different machines learning method;
Onboard sensor equipment, carries out transmission and the collection of data, it is thus achieved that when doubtful accident occurs
Vehicle 3-axis acceleration, three axis angular rates, speed, the time, place, voice data,
View data;
The pretreatment module of collision alarm data: by filtering techniques such as FIR, CHE, extracts
The true waveform of signal, and select effectively to collide Expressive Features;
Collision secondary detection model, will emulate data and actual experience data combines, in big data
Realize automatic decision collision on the basis of study the most truly to occur;
Car damage identification data base, is to carry out lot of accident Sample Establishing based on emulation to obtain, for
The accident of each vehicle have only to carry out OBD data analysis i.e. may know that vehicle damage and
The setting loss of car load.
Vehicle remote the most according to claim 7 automatic setting loss collision detecting system, its feature
Be, doubtful accident occur the 3-axis acceleration of moment vehicle, three axis angular rates, speed, time
Between, place, voice data, view data, on the one hand by the Collision Detection of cloud platform
Finally determine whether truly to there occurs collision;On the other hand collected data are improved remote further
Journey setting loss model.
Vehicle remote the most according to claim 7 automatic setting loss collision detecting system, its feature
It is, cloud platforms based on big data and artificial intelligence's learning method, sets up vehicle collision detection
Data base and knowledge base.
Vehicle remote the most according to claim 7 automatic setting loss collision detecting system, its feature
It is, the various Resource Encapsulations in vehicle crash data storehouse that accident and emulation are formed and virtual
Change, collision detection training pattern, pretreatment module, model database and knowledge base etc., will envelope
Dressing up collision detection application module is various concrete application services, forms conformance with standard interface
Functional module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610365730.0A CN105976449A (en) | 2016-05-27 | 2016-05-27 | Remote automatic damage assessment and collision detection method and system for vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610365730.0A CN105976449A (en) | 2016-05-27 | 2016-05-27 | Remote automatic damage assessment and collision detection method and system for vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105976449A true CN105976449A (en) | 2016-09-28 |
Family
ID=56956843
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610365730.0A Pending CN105976449A (en) | 2016-05-27 | 2016-05-27 | Remote automatic damage assessment and collision detection method and system for vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105976449A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106887054A (en) * | 2017-01-17 | 2017-06-23 | 福建天泉教育科技有限公司 | A kind of method and system of the doubtful accident condition of marked vehicle |
CN106920171A (en) * | 2017-01-23 | 2017-07-04 | 深圳优动信息科技有限公司 | The method and device that car accident is settled a claim online |
CN106979863A (en) * | 2017-03-17 | 2017-07-25 | 上海瞬动科技有限公司合肥分公司 | A kind of unmanned plane IMU collision checking methods and device |
CN107284387A (en) * | 2017-06-13 | 2017-10-24 | 得道车联网络科技(上海)有限公司 | A kind of car crass detection method based on Active Learning |
CN107895410A (en) * | 2017-11-08 | 2018-04-10 | 广东翼卡车联网服务有限公司 | A kind of car accident report process method, storage device and car-mounted terminal |
CN108737785A (en) * | 2018-05-21 | 2018-11-02 | 北京奇伦天佑创业投资有限公司 | Indoor tumble automatic checkout system based on TOF 3D video cameras |
CN109342765A (en) * | 2018-10-12 | 2019-02-15 | 成都四方伟业软件股份有限公司 | Vehicle collision detection method and device |
CN109559403A (en) * | 2018-11-30 | 2019-04-02 | 阿里巴巴集团控股有限公司 | A kind of car damage identification method, device and system for losing data based on vehicle part |
CN109670085A (en) * | 2018-12-17 | 2019-04-23 | 成都路行通信息技术有限公司 | A kind of method of discrimination of vehicle collision accident grade |
CN109741483A (en) * | 2018-12-11 | 2019-05-10 | 成都路行通信息技术有限公司 | A kind of car crass detection method based on car networking platform |
CN112308723A (en) * | 2019-07-31 | 2021-02-02 | 北京钛方科技有限责任公司 | Vehicle detection method and system |
CN113542393A (en) * | 2021-07-12 | 2021-10-22 | 交互未来(北京)科技有限公司 | Data transmission method and device |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103310223A (en) * | 2013-03-13 | 2013-09-18 | 四川天翼网络服务有限公司 | Vehicle loss assessment system based on image recognition and method thereof |
CN104021601A (en) * | 2014-05-30 | 2014-09-03 | 爱培科科技开发(深圳)有限公司 | Car collision detection method and device based on three-shaft acceleration sensor |
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 |
WO2015118325A1 (en) * | 2014-02-04 | 2015-08-13 | Sudak Menachem | Monitoring system and method |
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 |
CN105184896A (en) * | 2015-10-08 | 2015-12-23 | 珠海市杰理科技有限公司 | Collision detection device, event data recorder comprising same as well as collision detection processing method |
CN205017458U (en) * | 2015-08-21 | 2016-02-03 | 山东协通通信技术有限公司 | Long -range setting loss system of surveying of vehicle |
CN105512358A (en) * | 2015-11-24 | 2016-04-20 | 大连楼兰科技股份有限公司 | Loss assessment method of vehicle collision accidents based on CAE simulation technology |
-
2016
- 2016-05-27 CN CN201610365730.0A patent/CN105976449A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103310223A (en) * | 2013-03-13 | 2013-09-18 | 四川天翼网络服务有限公司 | Vehicle loss assessment system based on image recognition and method thereof |
WO2015118325A1 (en) * | 2014-02-04 | 2015-08-13 | Sudak Menachem | Monitoring system and method |
CN104021601A (en) * | 2014-05-30 | 2014-09-03 | 爱培科科技开发(深圳)有限公司 | Car collision detection method and device based on three-shaft acceleration sensor |
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 |
CN205017458U (en) * | 2015-08-21 | 2016-02-03 | 山东协通通信技术有限公司 | Long -range setting loss system of surveying of vehicle |
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 |
CN105184896A (en) * | 2015-10-08 | 2015-12-23 | 珠海市杰理科技有限公司 | Collision detection device, event data recorder comprising same as well as collision detection processing method |
CN105512358A (en) * | 2015-11-24 | 2016-04-20 | 大连楼兰科技股份有限公司 | Loss assessment method of vehicle collision accidents based on CAE simulation technology |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106887054A (en) * | 2017-01-17 | 2017-06-23 | 福建天泉教育科技有限公司 | A kind of method and system of the doubtful accident condition of marked vehicle |
CN106920171A (en) * | 2017-01-23 | 2017-07-04 | 深圳优动信息科技有限公司 | The method and device that car accident is settled a claim online |
CN106979863A (en) * | 2017-03-17 | 2017-07-25 | 上海瞬动科技有限公司合肥分公司 | A kind of unmanned plane IMU collision checking methods and device |
CN107284387A (en) * | 2017-06-13 | 2017-10-24 | 得道车联网络科技(上海)有限公司 | A kind of car crass detection method based on Active Learning |
CN107895410A (en) * | 2017-11-08 | 2018-04-10 | 广东翼卡车联网服务有限公司 | A kind of car accident report process method, storage device and car-mounted terminal |
CN108737785B (en) * | 2018-05-21 | 2020-07-03 | 北京奇伦天佑创业投资有限公司 | Indoor automatic detection system that tumbles based on TOF 3D camera |
CN108737785A (en) * | 2018-05-21 | 2018-11-02 | 北京奇伦天佑创业投资有限公司 | Indoor tumble automatic checkout system based on TOF 3D video cameras |
CN109342765A (en) * | 2018-10-12 | 2019-02-15 | 成都四方伟业软件股份有限公司 | Vehicle collision detection method and device |
CN109342765B (en) * | 2018-10-12 | 2020-11-10 | 成都四方伟业软件股份有限公司 | Vehicle collision detection method and device |
CN109559403A (en) * | 2018-11-30 | 2019-04-02 | 阿里巴巴集团控股有限公司 | A kind of car damage identification method, device and system for losing data based on vehicle part |
CN109741483A (en) * | 2018-12-11 | 2019-05-10 | 成都路行通信息技术有限公司 | A kind of car crass detection method based on car networking platform |
CN109670085A (en) * | 2018-12-17 | 2019-04-23 | 成都路行通信息技术有限公司 | A kind of method of discrimination of vehicle collision accident grade |
CN112308723A (en) * | 2019-07-31 | 2021-02-02 | 北京钛方科技有限责任公司 | Vehicle detection method and system |
CN113542393A (en) * | 2021-07-12 | 2021-10-22 | 交互未来(北京)科技有限公司 | Data transmission method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105976449A (en) | Remote automatic damage assessment and collision detection method and system for vehicle | |
EP3533681B1 (en) | Method for detecting safety of driving behavior, apparatus and storage medium | |
CN105620480B (en) | Intelligent vehicle independence lane-change opportunity decision-making technique | |
CN106274483A (en) | The Vehicular automatic driving switching device differentiated based on driving behavior of diverting one's attention and method | |
CN105590466A (en) | Monitoring system and monitoring method for dangerous operation behaviors of driver on cloud platform | |
CN104802737A (en) | Mobile phone based vehicle abnormality driving behavior detection method | |
CN105976074A (en) | Vehicle health parameter generation and presentation method and device | |
CN106066907B (en) | Loss assessment grading method based on multi-part multi-model judgment | |
CN110143202A (en) | A kind of dangerous driving identification and method for early warning and system | |
CN106022929A (en) | Collision accident loss estimating method and system based on expert system | |
CN108877213A (en) | The recognition methods and system of traffic accident | |
CN103471865A (en) | Train suspension system failure isolation method based on LDA method | |
CN106203437B (en) | Individual driving behavior recognition methods and device | |
CN106056451A (en) | Vehicle OBD sensor-based remote unmanned loss assessment system | |
CN109886724A (en) | A kind of resident trip track recognizing method of robustness | |
CN106557939A (en) | A kind of motor vehicle detecting system and method | |
CN115782905A (en) | Automatic driving vehicle driving safety degree quantification system | |
CN106055776A (en) | Regional and remote damage-assessment system and method established based on artificial-intelligence supervised learning linear regression method for different types of vehicles | |
Ambros et al. | Proactive assessment of road curve safety using floating car data: An exploratory study | |
CN110264741A (en) | Road conditions detection method, device, equipment and medium based on motion sensor | |
CN109910876A (en) | A kind of AEBS main control method | |
CN110377982A (en) | The test method and system of automatic Pilot performance, electronic equipment, storage medium | |
CN114818326A (en) | Verification method and device for urban rail transit electronic map | |
CN110956072B (en) | Driving skill training method based on big data analysis | |
CN112580736A (en) | Drunk driving vehicle identification method based on SVM algorithm |
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 |
Application publication date: 20160928 |
|
RJ01 | Rejection of invention patent application after publication |