CN108010269A - A kind of driving based on car networking is divert one's attention monitoring, early warning system and method - Google Patents

A kind of driving based on car networking is divert one's attention monitoring, early warning system and method Download PDF

Info

Publication number
CN108010269A
CN108010269A CN201711492277.0A CN201711492277A CN108010269A CN 108010269 A CN108010269 A CN 108010269A CN 201711492277 A CN201711492277 A CN 201711492277A CN 108010269 A CN108010269 A CN 108010269A
Authority
CN
China
Prior art keywords
lt
gt
mo
mi
attention
Prior art date
Application number
CN201711492277.0A
Other languages
Chinese (zh)
Inventor
郭唐仪
潘姝
王若愚
葛徐婷
吕亦江
朱云霞
伊特格勒
孙豪
郝浪
郭进
Original Assignee
南京理工大学
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 南京理工大学 filed Critical 南京理工大学
Priority to CN201711492277.0A priority Critical patent/CN108010269A/en
Publication of CN108010269A publication Critical patent/CN108010269A/en

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal operating condition and not elsewhere provided for
    • G08B21/02Alarms for ensuring the safety of persons

Abstract

The present invention proposes a kind of driving based on car networking and diverts one's attention monitoring, early warning system and method, and divert one's attention monitoring, early warning system of the driving based on car networking specifically includes:Intelligent vehicle mounted terminal, for vehicle position information where gathering driver information, driver;Cloud system processing platform, for judging driver in the risk for diverting one's attention to drive according to foregoing drivers information and being issued warning signal in response to the risk to the vehicle and its nearby vehicle;The Vehicular intelligent car-mounted terminal and its nearby vehicle intelligent vehicle mounted terminal make early warning in response to the pre-warning signal.Cloud system platform of the present invention determines driver when diverting one's attention, and to target vehicle is divert one's attention and its nearby vehicle sends warning information, intelligent vehicle mounted terminal receives warning information and simultaneously plays warning information, so as to driver's early warning, can effectively improve the traffic safety of road entirety.

Description

A kind of driving based on car networking is divert one's attention monitoring, early warning system and method

Technical field

The present invention relates to wisdom traffic field, particularly a kind of driving based on car networking divert one's attention monitoring, early warning system and Method.

Background technology

Driving is divert one's attention be main people because one of, and the main reason for initiation road traffic accident.China's system in 2014 Accident accounts for 47.2% caused by driving behavior of diverting one's attention in the simple traffic accident of meter.Driving diverts one's attention to considerably increase accident wind Danger, not only endangers its life property safety, but also other road users are caused with huge potential danger.Therefore, such as What in real time, effectively detection driver state of diverting one's attention be solves the problems, such as a difficult point diverting one's attention of driving, it is and this car driver is different It is also a big key point that normal status information is timely, accurately passes to other car owners.

The application for car networking technology essentially consists in traffic information, state of motion of vehicle, vehicle path planning etc. at present Information exchange in terms of car, road, environment, and ignore driver's critical role shared in people-Che-road-environmental system.

Current driving detection method of diverting one's attention is mainly based upon driver's physiological reaction feature, driver's operation behavior, car Driving trace.The driving shape of driver can intuitively be reflected by driving human physiological characteristics using electrocardio, myoelectricity, skin conductivity rate etc. State, but these are all to lean on human body sensor, continuity and reliability are low.Utilize driver's operation behavior and vehicle traveling rail Mark can reflect the state of driver indirectly.The data acquisition of both approaches is relatively simple, but testing result is driven The geometric properties such as people's experience, type of vehicle, road geometrical condition influence, and the accuracy for state-detection of diverting one's attention to driver is not high.

The content of the invention

The present invention propose a kind of driving based on car networking divert one's attention monitoring, early warning system, solve the prior art to drive People divert one's attention state-detection accuracy it is not high the problem of.

Realize that technical solution of the invention is:A kind of driving based on car networking divert one's attention monitoring, early warning system, bag Include:

Intelligent vehicle mounted terminal, for vehicle position information where gathering driver information, driver;

Cloud system processing platform, for judging that driver is in the risk for diverting one's attention to drive and sound according to foregoing drivers information It should be issued warning signal in the risk to the vehicle and its nearby vehicle;

The Vehicular intelligent car-mounted terminal and its nearby vehicle intelligent vehicle mounted terminal make early warning in response to the pre-warning signal.

The invention also provides a kind of driving based on car networking divert one's attention monitoring, method for early warning, concretely comprise the following steps:

Step 1, intelligent vehicle mounted terminal collection driver eye movement behavioral data;

Step 2, cloud system platform judge that driver is in the risk for diverting one's attention to drive according to driver eye movement behavioral data, and Issued warning signal in response to the risk to the vehicle and its nearby vehicle;

Step 3, intelligent vehicle mounted terminal in response to the pre-warning signal in step 2 make early warning.

Compared with prior art, the present invention its remarkable advantage is:

(1) present invention is gathered driving human eye by intelligent vehicle mounted terminal non-contact modular and moves behavioural information in real time, to driving People is noiseless, and data reliability is high, highly practical;

(2) present invention, can automatic identification by the detection model of diverting one's attention of cloud system platform without manually inputting any data Driver's state;

(3) when cloud system platform of the present invention determines driver and diverts one's attention, to diverting one's attention target vehicle and its nearby vehicle is sent Warning information, intelligent vehicle mounted terminal receive warning information and play warning information, so as to driver's early warning, effectively improve road Overall traffic safety.

Further detailed description is done to the present invention below in conjunction with the accompanying drawings.

Brief description of the drawings

Fig. 1 be one embodiment of the invention provide drivings based on car networking divert one's attention monitor, the exemplary diagram of early warning system.

Fig. 2 be one embodiment of the invention provide drivings based on car networking divert one's attention monitor, the frame diagram of early warning system.

Fig. 3 be one embodiment of the invention provide drivings based on car networking divert one's attention monitor, the flow chart of method for early warning.

Embodiment

A kind of driving based on car networking divert one's attention monitoring, early warning system, including:

Intelligent vehicle mounted terminal, for vehicle position information where gathering driver information, driver;

In further embodiment, intelligent vehicle mounted terminal includes GPS device, data acquisition module, controller, data storage Module and safe early warning module, the GPS device, data acquisition module, data memory module, safe early warning module with control Device connection processed.

The eye that data acquisition module obtains driver in real time moves behavioral data, and controller passes the data by communication module Cloud system processing platform is given, while the GPS information of the vehicle is also passed to cloud system processing platform by controller.It is intelligent vehicle-carried The pre-warning signal that the data memory module storage cloud system processing platform of terminal is sent, the data memory module for target vehicle of diverting one's attention After receiving pre-warning signal, the safe early warning module of this car is triggered at once, and controller control safe early warning module carries out early warning;Together When, the vehicle on periphery is also by the safe early warning mould of the pre-warning signal, then nearby vehicle that receive cloud system processing platform and send Block, which will also be triggered, carries out early warning.In other embodiments, data acquisition module moves behavioral value equipment using contactless eye, Such as the faceLAB eye trackers of Seeing Machines companies of Australia research and development.

In further embodiment, the driver information of collection is specially that eye moves behavioral data, including:Driven in time T People's blinkpunkt falls the times N in each regionn, n=1,2,3,4, left window, front window, right window, in-car region are represented respectively;Ith is noted Apparent time blinkpunkt angle ωi;Ith watches behavior start time attentivelyFinish time

Cloud system processing platform, for judging that driver is in the risk for diverting one's attention to drive and sound according to foregoing drivers information It should be issued warning signal in the risk to the vehicle and its nearby vehicle, specially send voice reminder signal to the vehicle, to The vehicle-surroundings vehicle sends voice reminder signal and the vehicle location signal.

In further embodiment, cloud system processing platform judges that driver is according to foregoing drivers information and diverts one's attention to drive The specific method for the risk sailed is:

Step 1, cloud system processing platform establish normal driving and driving is divert one's attention database;

Step 2, the characteristic parameter of diverting one's attention in calculating time T, are specially:

Watch duration D attentively1

Sight leaves front window zone time accounting D2

Saccade velocity average D3

Wherein, NnRepresent in time T that driver's blinkpunkt falls number in each region, n=1,2,3,4, represent respectively left Window, front window, right window, in-car region;Blinkpunkt angle ω when ith is watched attentivelyi;Ith watches behavior start time attentivelyAt the end of CarveN represents fixation times.

Step 3, basis watch duration attentively and carry out diverting one's attention to drive just judgement:

If there is watching duration D attentively1More than 1.6s, then it is judged as that driver is in the risk for diverting one's attention to drive;If watch attentively Length then carries out step 4 not less than 1.6s;

Step 4, judge risk of the driver in driving of diverting one's attention according to driving model of diverting one's attention again, when the output knot of model Fruit is+1, represents normal driving state, and when the output result of model is -1, expression diverts one's attention to drive;Wherein, divert one's attention driving model For:

In formula, x={ D2,D3, xaFor kernel function center;L represents sample size;B represents biasing;ai=0.2, yi=-1;σ For function widths parameter, 0.41 is taken in this model.

The Vehicular intelligent car-mounted terminal and its nearby vehicle intelligent vehicle mounted terminal make early warning in response to the pre-warning signal.

With reference to embodiment, the present invention will be further described.

Embodiment 1

A kind of driving based on car networking divert one's attention monitoring, method for early warning, concretely comprise the following steps:

Step 1, intelligent vehicle mounted terminal collection driver eye movement behavioral data;

Step 2, cloud system platform judge that driver is in the risk for diverting one's attention to drive according to driver eye movement behavioral data, and Issued warning signal in response to the risk to the vehicle and its nearby vehicle, cloud system platform is according to driver eye movement behavioral data Judge that the specific method that driver is in the risk for diverting one's attention to drive is:

Step 2.1, cloud system processing platform establish normal driving and driving is divert one's attention database;

Step 2.2, the characteristic parameter of diverting one's attention in calculating time T, are specially:

Watch duration D attentively1

Sight leaves front window zone time accounting D2

Saccade velocity average D3

Step 2.3, basis watch duration attentively and carry out diverting one's attention to drive just judgement:

If there is watching duration D attentively1More than 1.6s, then it is judged as that driver is in the risk for diverting one's attention to drive;If watch attentively Length then carries out step 2.4 not less than 1.6s;

Step 2.4, judge risk of the driver in driving of diverting one's attention according to driving model of diverting one's attention again, when the output of model As a result it is+1, represents normal driving state, when the output result of model is -1, expression diverts one's attention to drive;Wherein, divert one's attention driving model For:

In formula, x={ D2,D3, xaFor kernel function center;σ is function widths parameter;L represents sample size;B represents inclined Put;ai=0.2, yi=-1.

Wherein, to the vehicle and its nearby vehicle issue warning signal including:Voice reminder signal is sent to the vehicle;To The vehicle-surroundings vehicle sends voice reminder signal and the vehicle location signal.

Step 3, intelligent vehicle mounted terminal in response to the pre-warning signal in step 2 make early warning.

Claims (9)

  1. Monitoring, early warning system 1. a kind of driving based on car networking is divert one's attention, it is characterised in that including:
    Intelligent vehicle mounted terminal, for vehicle position information where gathering driver information, driver;
    Cloud system processing platform, for according to foregoing drivers information judge driver be in divert one's attention drive risk and in response to The risk is issued warning signal to the vehicle and its nearby vehicle;
    The Vehicular intelligent car-mounted terminal and its nearby vehicle intelligent vehicle mounted terminal make early warning in response to the pre-warning signal.
  2. Monitoring, early warning system 2. the driving according to claim 1 based on car networking is divert one's attention, it is characterised in that the intelligence Energy car-mounted terminal includes GPS device, data acquisition module, controller, data memory module and safe early warning module, described GPS device, data acquisition module, data memory module, safe early warning module are connected with controller.
  3. Monitoring, early warning system 3. the driving according to claim 1 based on car networking is divert one's attention, it is characterised in that described to drive The person's of sailing information is specially that eye moves behavioral data, including:Driver's blinkpunkt falls the times N in each region in time Tn, n=1,2, 3,4, left window, front window, right window, in-car region are represented respectively;Blinkpunkt angle ω when ith is watched attentivelyi;Ith is watched behavior attentively and is opened Begin the momentFinish time
  4. Monitoring, early warning system 4. the driving according to claim 1 based on car networking is divert one's attention, it is characterised in that described to be somebody's turn to do It is specially that voice is broadcast that Vehicular intelligent car-mounted terminal and its nearby vehicle intelligent vehicle mounted terminal make early warning in response to the pre-warning signal Report early warning.
  5. Monitoring, early warning system 5. the driving according to claim 1 based on car networking is divert one's attention, it is characterised in that cloud system Processing platform judges that the specific method that driver is in the risk for diverting one's attention to drive is according to foregoing drivers information:
    Step 1, cloud system processing platform establish normal driving and driving is divert one's attention database;
    Step 2, the characteristic parameter of diverting one's attention in calculating time T, are specially:
    Watch duration D attentively1
    Sight leaves front window zone time accounting D2
    Saccade velocity average D3
    Wherein, NnRepresent in time T that driver's blinkpunkt falls number in each region, n=1,2,3,4, left window, preceding is represented respectively Window, right window, in-car region;Blinkpunkt angle ω when ith is watched attentivelyi;Ith watches behavior start time attentivelyFinish timeN Represent fixation times;
    Step 3, basis watch duration attentively and carry out diverting one's attention to drive preliminary judgement:
    If there is watching duration D attentively1More than 1.6s, then it is judged as that driver is in the risk for diverting one's attention to drive;If watch duration attentively not surpass 1.6s is crossed, then carries out step 4;
    Step 4, judge risk of the driver in driving of diverting one's attention according to driving model of diverting one's attention again, when the output result of model is + 1, represent normal driving state, when the output result of model is -1, expression diverts one's attention to drive;Wherein, driving model of diverting one's attention is:
    <mrow> <mi>y</mi> <mo>=</mo> <mi>f</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>)</mo> </mrow> <mo>=</mo> <mi>sgn</mi> <mrow> <mo>(</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>l</mi> </munderover> <msub> <mi>a</mi> <mi>i</mi> </msub> <msub> <mi>y</mi> <mi>i</mi> </msub> <mo>&amp;CenterDot;</mo> <msup> <mi>e</mi> <mfrac> <mrow> <mo>-</mo> <mo>|</mo> <mo>|</mo> <mi>x</mi> <mo>-</mo> <msub> <mi>x</mi> <mi>a</mi> </msub> <mo>|</mo> <msup> <mo>|</mo> <mn>2</mn> </msup> </mrow> <msup> <mrow> <mo>(</mo> <mn>2</mn> <mi>&amp;sigma;</mi> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mfrac> </msup> <mo>+</mo> <mi>b</mi> <mo>)</mo> </mrow> </mrow>
    In formula, x={ D2,D3, xaFor kernel function center;σ is function widths parameter;L represents sample size;B represents biasing;ai= 0.2、yi=-1.
  6. Monitoring, early warning system 6. the driving according to claim 1 based on car networking is divert one's attention, it is characterised in that cloud system Processing platform includes in response to the pre-warning signal that the risk is sent to the vehicle and its nearby vehicle:
    Voice reminder signal is sent to the vehicle;
    Voice reminder signal and the vehicle location signal are sent to the vehicle-surroundings vehicle.
  7. Monitoring, method for early warning 7. a kind of driving based on car networking is divert one's attention, it is characterised in that concretely comprise the following steps:
    Step 1, intelligent vehicle mounted terminal collection driver eye movement behavioral data;
    Step 2, cloud system platform judge that driver is in the risk for diverting one's attention to drive according to driver eye movement behavioral data, and respond Issued warning signal in the risk to the vehicle and its nearby vehicle;
    Step 3, intelligent vehicle mounted terminal make early warning in response to the pre-warning signal in step 2.
  8. Monitoring, method for early warning 8. the driving according to claim 7 based on car networking is divert one's attention, it is characterised in that cloud system Platform judges that driver is in concretely comprising the following steps for the risk for driving of diverting one's attention according to driver eye movement behavioral data:
    Step 2.1, the characteristic parameter of diverting one's attention in calculating time T, are specially:
    Watch duration D attentively1
    Sight leaves front window zone time accounting D2
    Saccade velocity average D3
    Wherein, NnRepresent in time T that driver's blinkpunkt falls number in each region, n=1,2,3,4, left window, preceding is represented respectively Window, right window, in-car region;Blinkpunkt angle ω when ith is watched attentivelyi;Ith watches behavior start time attentivelyFinish timeN Represent fixation times;
    Step 2.2, basis watch duration attentively and carry out diverting one's attention to drive preliminary judgement:
    If there is watching duration D attentively1More than 1.6s, then it is judged as that driver is in the risk for diverting one's attention to drive;If watch duration attentively not surpass 1.6s is crossed, then carries out step 2.3;
    Step 2.3, judge risk of the driver in driving of diverting one's attention according to driving model of diverting one's attention again, when the output result of model is + 1, represent normal driving state, when the output result of model is -1, expression diverts one's attention to drive;Wherein, driving model of diverting one's attention is:
    <mrow> <mi>y</mi> <mo>=</mo> <mi>f</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>)</mo> </mrow> <mo>=</mo> <mi>sgn</mi> <mrow> <mo>(</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>l</mi> </munderover> <msub> <mi>a</mi> <mi>i</mi> </msub> <msub> <mi>y</mi> <mi>i</mi> </msub> <mo>&amp;CenterDot;</mo> <msup> <mi>e</mi> <mfrac> <mrow> <mo>-</mo> <mo>|</mo> <mo>|</mo> <mi>x</mi> <mo>-</mo> <msub> <mi>x</mi> <mi>a</mi> </msub> <mo>|</mo> <msup> <mo>|</mo> <mn>2</mn> </msup> </mrow> <msup> <mrow> <mo>(</mo> <mn>2</mn> <mi>&amp;sigma;</mi> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mfrac> </msup> <mo>+</mo> <mi>b</mi> <mo>)</mo> </mrow> </mrow>
    In formula, x={ D2,D3, xaFor kernel function center;σ is function widths parameter;L represents sample size;B represents biasing;ai= 0.2、yi=-1.
  9. Monitoring, method for early warning 9. the driving according to claim 7 based on car networking is divert one's attention, it is characterised in that to the car And its nearby vehicle issue warning signal including:Voice reminder signal is sent to the vehicle;Sent to the vehicle-surroundings vehicle Voice reminder signal and the vehicle location signal.
CN201711492277.0A 2017-12-30 2017-12-30 A kind of driving based on car networking is divert one's attention monitoring, early warning system and method CN108010269A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711492277.0A CN108010269A (en) 2017-12-30 2017-12-30 A kind of driving based on car networking is divert one's attention monitoring, early warning system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711492277.0A CN108010269A (en) 2017-12-30 2017-12-30 A kind of driving based on car networking is divert one's attention monitoring, early warning system and method

Publications (1)

Publication Number Publication Date
CN108010269A true CN108010269A (en) 2018-05-08

Family

ID=62049203

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711492277.0A CN108010269A (en) 2017-12-30 2017-12-30 A kind of driving based on car networking is divert one's attention monitoring, early warning system and method

Country Status (1)

Country Link
CN (1) CN108010269A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104966382A (en) * 2015-05-21 2015-10-07 浙江吉利汽车研究院有限公司 Driver physiological status monitoring and responding system and method
CN105139584A (en) * 2015-09-30 2015-12-09 宇龙计算机通信科技(深圳)有限公司 Fatigue driving processing method and apparatus
CN107126223A (en) * 2017-06-16 2017-09-05 武汉理工大学 Time of driver's reaction measuring system and method under the conditions of real vehicle

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104966382A (en) * 2015-05-21 2015-10-07 浙江吉利汽车研究院有限公司 Driver physiological status monitoring and responding system and method
CN105139584A (en) * 2015-09-30 2015-12-09 宇龙计算机通信科技(深圳)有限公司 Fatigue driving processing method and apparatus
CN107126223A (en) * 2017-06-16 2017-09-05 武汉理工大学 Time of driver's reaction measuring system and method under the conditions of real vehicle

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李胜江: "驾驶人视觉注意力分散检测方法研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 *

Similar Documents

Publication Publication Date Title
US8653986B2 (en) Traffic information system
US10445954B2 (en) Drive event capturing based on geolocation
US8996234B1 (en) Driver performance determination based on geolocation
US20070032929A1 (en) System and method for recording physical response
EP2335234B1 (en) Method for avoiding collisions
US9147353B1 (en) Driving analysis using vehicle-to-vehicle communication
US9994218B2 (en) Method for smartphone-based accident detection
JP5120249B2 (en) Monitoring device and monitoring method, control device and control method, and program
CN101727741B (en) Safe driving evaluation system and safe driving evaluation program
EP2892020A1 (en) Continuous identity monitoring for classifying driving data for driving performance analysis
CN102975721A (en) System and method for improving a performance estimation of an operator of a vehicle
CN102509418A (en) Fatigue driving estimation and early-warning method and device of multi-sensor information fusion
CN103832282A (en) Automobile intelligent speed limiting system and automobile speed limiting method
KR101405679B1 (en) An abnormal driving state detact and warning system which based on location-based service
CN102069800B (en) Vehicle running control method and control device
CN104386063A (en) Driving assistance system based on artificial intelligence
CN103700160A (en) Motor vehicle onboard terminal based on microsensor and driving behavior judgment method
CN102044170B (en) Vehicle driving support control apparatus
CN102991504B (en) Method for determining and prewarning lane change safety of drivers
JP5263312B2 (en) Traffic jam judging device and vehicle control device
CN202870934U (en) Driving recording device
CN102314596B (en) For providing the computer based system and method for driving assistance information
CN105741556B (en) The method for pushing and supplying system of traffic information
CN103770733A (en) Method and device for detecting safety driving states of driver
CN102310771B (en) Motor vehicle safety control method and system based on driver face identification

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination