CN106228754A - A kind of hands based on binocular vision detection equipment - Google Patents

A kind of hands based on binocular vision detection equipment Download PDF

Info

Publication number
CN106228754A
CN106228754A CN201610648586.1A CN201610648586A CN106228754A CN 106228754 A CN106228754 A CN 106228754A CN 201610648586 A CN201610648586 A CN 201610648586A CN 106228754 A CN106228754 A CN 106228754A
Authority
CN
China
Prior art keywords
hands
driving behavior
photographic head
camera
dangerous driving
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.)
Granted
Application number
CN201610648586.1A
Other languages
Chinese (zh)
Other versions
CN106228754B (en
Inventor
王宗跃
郑翠玲
蔡国榕
吴云东
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.)
Jimei University
Original Assignee
Jimei University
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 Jimei University filed Critical Jimei University
Priority to CN201610648586.1A priority Critical patent/CN106228754B/en
Publication of CN106228754A publication Critical patent/CN106228754A/en
Application granted granted Critical
Publication of CN106228754B publication Critical patent/CN106228754B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02Alarms for ensuring the safety of persons
    • G08B21/06Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60QARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
    • B60Q9/00Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/18Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/181Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources

Abstract

The invention discloses a kind of hands based on binocular vision detection equipment, including the first photographic head, second camera, arithmetic unit and local alarm device, wherein, arithmetic unit Real-time Collection the first photographic head and the video image of second camera, carry out dangerous driving behavior comprehensively to analyze, and when finding dangerous driving behavior, perform local actuation of an alarm by local alarm device;Data recording equipment storage arithmetic unit collection is from the first photographic head and the real time video image of second camera, as the conclusive evidence of dangerous driving behavior, thus reach accurately analyze and record various dangerous driving behavior, real-time prompting driver and surrounding vehicles and automatically perform the purpose of safety measure.The present invention eliminates the uncertainty in video image identification and fuzzy factors;When finding dangerous driving behavior, driver safety can be reminded to drive, remind surrounding vehicles to dodge and can automatically perform reduction of speed traveling in time, force the safety measures such as parking, and retain driving recording.

Description

A kind of hands based on binocular vision detection equipment
Technical field
The present invention relates to safe driving technology, the one especially relating to be applied in safe driving technology is based on binocular vision The hands detection equipment felt.
Background technology
For current safe driving, driver in drunk driving, fatigue driving, make a phone call, in the case of insobriety Driving is fraught with risks, and is susceptible to vehicle accident.At present, anti-fatigue-driving technology based on human facial expression recognition has fuzzy Property, uncertainty, such as patent 201310209728, and can not accurately analyze make a phone call, drunk driving etc. changes phase with facial expression The dangerous driving behavior that closing property is weak;Safe driving based on steering wheel pressure transducer is set up, such as patent 201410397767, then Driver's both hands attitudes vibration cannot be detected, thus miss and the driving of long-time fixed pose, doubtful doze behavior are divided Analysis alarm.
Summary of the invention
In order to solve above-mentioned technical problem, the present invention provides a kind of hands based on binocular vision to detect equipment, including first Photographic head, second camera, arithmetic unit and local alarm device, wherein, arithmetic unit Real-time Collection the first photographic head and the The video image of two photographic head, carries out dangerous driving behavior and comprehensively analyzes, and when finding dangerous driving behavior, is reported by this locality Alarm device performs local actuation of an alarm;Data recording equipment storage arithmetic unit collection is from the first photographic head and second camera Real time video image, as the conclusive evidence of dangerous driving behavior, thus reaches accurately to analyze and record various dangerous driving row For, real-time prompting driver and surrounding vehicles the purpose automatically performing safety measure.
To this end, technical scheme provided by the present invention is, a kind of hands based on binocular vision detection equipment, take the photograph including first As head, second camera, arithmetic unit and local alarm device, it is characterised in that: arithmetic unit Real-time Collection the first photographic head With the video image of second camera, carry out dangerous driving behavior and comprehensively analyze, and when finding dangerous driving behavior, by this Ground alarm device performs local actuation of an alarm, and wherein, the step that dangerous driving behavior is analyzed is as follows:
A) image common-denominator target extracts, and to the first photographic head and the real time video image of second camera, extracts therein respectively Steering wheel and both hands target, and the relative position of calculated direction dish and both hands target, angle and distance data;
B) two-hand positions relation calculates, in conjunction with relative with both hands target with the steering wheel of second camera from the first photographic head Position, angle and distance data, perform data correction and fusion, obtains both hands and believes with position relative to the exact posture of steering wheel Breath;
C) driving behavior data analysis, according to the both hands exact posture calculated and positional information, analyzes drunk driving therein, fatigue Drive, make a phone call, the dangerous driving behavior such as insobriety.
Further improvement of the present invention is, described local actuation of an alarm includes the sound and light alarm outside Che Nei and car, reduction of speed Travel and force to stop.
Further improvement of the present invention is, hands detection equipment also includes data recording equipment, and it is used for storing computing dress Put collection from the first photographic head and the real time video image of second camera.
Further improvement of the present invention is, hands detection equipment also includes data remote transmitting device, is analyzed by arithmetic unit The dangerous driving behavior data gone out, and data recording equipment storage vedio data be sent in remote data management The heart.
What the present invention can reach has the technical effect that Real-time Collection the first photographic head of the present invention and the video of second camera Image, and calculate through the extraction of image common-denominator target, two-hand positions relation, perform data correction and fusion, obtain both hands relative In exact posture and the positional information of steering wheel, eliminate the uncertainty in video image identification and fuzzy factors, improve Analyze and the accuracy of hazardous act warning.
The present invention, when finding dangerous driving behavior, performs local actuation of an alarm by local alarm device, can remind and drive The person's of sailing safe driving, prompting surrounding vehicles are dodged and can automatically be performed reduction of speed in time and travel, force the safety measures such as parking;Data Recording equipment real-time storage by arithmetic unit collection from the first photographic head and the real time video image of second camera, as danger The conclusive evidence of driving behavior.
Accompanying drawing explanation
Fig. 1 is the structural representation of a kind of hands based on binocular vision detection device,
Fig. 2 is the flow chart that dangerous driving behavior is analyzed.
Detailed description of the invention
In order to deepen the understanding of the present invention, the present invention is further described with embodiment below in conjunction with the accompanying drawings, this enforcement Example is only used for explaining the present invention, does not constitute protection scope of the present invention and limits.
For current safe driving, driver in drunk driving, fatigue driving, make a phone call, in the case of insobriety Driving is fraught with risks, and is susceptible to vehicle accident.At present, anti-fatigue-driving technology based on human facial expression recognition has fuzzy Property, uncertainty, such as patent 201310209728, and can not accurately analyze make a phone call, drunk driving etc. changes phase with facial expression The dangerous driving behavior that closing property is weak;Safe driving based on steering wheel pressure transducer is set up, such as patent 201410397767, then Driver's both hands attitudes vibration cannot be detected, thus miss and the driving of long-time fixed pose, doubtful doze behavior are divided Analysis alarm.
In order to solve above-mentioned technical problem, the present invention provides a kind of hands based on binocular vision to detect equipment, including first Photographic head, second camera, arithmetic unit and local alarm device, wherein, arithmetic unit Real-time Collection the first photographic head and the The video image of two photographic head, carries out dangerous driving behavior and comprehensively analyzes, and when finding dangerous driving behavior, is reported by this locality Alarm device performs local actuation of an alarm;Data recording equipment storage arithmetic unit collection is from the first photographic head and second camera Real time video image, as the conclusive evidence of dangerous driving behavior, thus reaches accurately to analyze and record various dangerous driving row For, real-time prompting driver and surrounding vehicles the purpose automatically performing safety measure.
To this end, provide a kind of hands based on binocular vision to detect equipment, as it is shown in figure 1, include the first photographic head 1, second Regarding of photographic head 2, arithmetic unit 3 and local alarm device 4, arithmetic unit Real-time Collection the first photographic head 1 and second camera 2 Frequently image, carries out dangerous driving behavior and comprehensively analyzes, and when finding dangerous driving behavior, performs basis by local alarm device Ground actuation of an alarm, wherein, dangerous driving behavior analysis is as in figure 2 it is shown, its step is as follows:
A) image common-denominator target extracts, and such as the S1 of Fig. 2, to the first photographic head 1 and the real time video image of second camera 2, divides Take steering wheel therein and both hands target indescribably, and the relative position of calculated direction dish and both hands target, angle and distance data;
The premise of this step is the relative position relation of known photographic head and steering wheel, owing to photographic head is fixedly mounted on steering wheel Front, this relative position relation can described hands detection equipment install time be determined;
The Objective extraction characteristics of image of steering wheel is its shape and color, and the Objective extraction characteristics of image of both hands and arm Being its shape, profile and motion feature, this motion feature can solve according to image dynamic change characterization;
According to single photographic head, both hands and the steering wheel position relationship on horizontal plane can only be drawn, including the phase of the two To position, angle and distance data, but cannot definitely learn that both hands are whether in steering wheel plane.
B) two-hand positions relation calculates, such as the S2 of Fig. 2, in conjunction with from the first photographic head 1 and the direction of second camera 2 The relative position of dish and both hands target, angle and distance data, perform data correction and fusion, obtain both hands relative to steering wheel Exact posture and positional information;
This step can calculate both hands and the vertical height of steering wheel plane and horizontal range, and the real-time attitude of arm, as In conjunction with the most dynamically analyzing, then can analyze driver and keep the duration of certain vehicle driving posture.According to above-mentioned information, can be Next step driving behavior analysis provides abundant and sufficiently exact attitude and positional information.
C) driving behavior data analysis, such as the S3 of Fig. 2, according to the both hands exact posture calculated and positional information, analyzes Drunk driving therein, fatigue driving, make a phone call, the dangerous driving behavior such as insobriety.
Both hands are relative to the attitude of steering wheel and positional information, including both hands and the vertical height of steering wheel plane, level Distance and the real-time attitude of arm, corresponding to drunk driving, fatigue driving, make a phone call, the different dangerous driving such as insobriety Behavior, such as: drunk driving there will be significantly abnormal arm action, makes a phone call, there will be one hand and hold up steering wheel, fatigue driving meeting Occur keeping fixing vehicle driving posture for a long time.
Local actuation of an alarm includes that the sound and light alarm outside Che Nei and car, reduction of speed travel and force to stop.Acousto-optic report in car Alert prompting driver safety is driven, and car outer sound and light alarm prompting surrounding vehicles is dodged in time.When extremely hazardous driving row occurs For time, reduction of speed travel even force parking can avoid security incident in time.
A kind of hands based on binocular vision detection equipment also includes data recording equipment 5, and it is used for storing arithmetic unit 3 and adopts Collection is from the first photographic head 1 and the real time video image of second camera 2, and this is as the conclusive evidence of dangerous driving behavior.
A kind of hands based on binocular vision detection equipment also includes data remote transmitting device 6, arithmetic unit 3 analysis is drawn Dangerous driving behavior data, and data recording equipment 5 storage vedio data be sent to remote data management center.
What the present invention can reach has the technical effect that
Real-time Collection the first photographic head of the present invention and the video image of second camera, and through image common-denominator target extract, double Hand position relation calculates, and performs data correction and fusion, obtains both hands relative to the exact posture of steering wheel and positional information, picks Except the uncertainty in video image identification and fuzzy factors, improve and analyze and the accuracy of hazardous act warning;This Bright when finding dangerous driving behavior, perform local actuation of an alarm by local alarm device, driver safety can be reminded to drive, Remind surrounding vehicles to dodge and can automatically perform reduction of speed in time to travel, force the safety measures such as parking;Data recording equipment is real-time Store by arithmetic unit collection from the first photographic head and the real time video image of second camera, as dangerous driving behavior really Cut evidence.
What embodiments of the invention were announced is preferred embodiment, but is not limited thereto, the ordinary skill people of this area Member, easily according to above-described embodiment, understands the spirit of the present invention, and makes different amplifications and change, but as long as without departing from this The spirit of invention, the most within the scope of the present invention.

Claims (4)

1. hands based on a binocular vision detection equipment, including the first photographic head, second camera, arithmetic unit and local report Alarm device, it is characterised in that: arithmetic unit Real-time Collection the first photographic head and the video image of second camera, carry out danger and drive Sail behavior integration analysis, and when finding dangerous driving behavior, by the local local actuation of an alarm of alarm device execution, wherein, The step that dangerous driving behavior is analyzed is as follows:
Image common-denominator target extracts, and to the first photographic head and the real time video image of second camera, extracts side therein respectively To dish and both hands target, and the relative position of calculated direction dish and both hands target, angle and distance data;
Two-hand positions relation calculates, in conjunction with from the steering wheel of the first photographic head and second camera and the phase para-position of both hands target Put, angle and distance data, perform data correction and fusion, obtain both hands and believe with position relative to the exact posture of steering wheel Breath;
Driving behavior data analysis, according to the both hands attitude calculated and positional information, analyze drunk driving therein, fatigue driving, Make a phone call, the dangerous driving behavior of insobriety.
A kind of hands based on binocular vision the most according to claim 1 detection equipment, it is characterised in that described local warning Action includes that the sound and light alarm outside Che Nei and car, reduction of speed travel and force to stop.
A kind of hands based on binocular vision the most according to claim 1 detection equipment, it is characterised in that hands detection equipment is also Including data recording equipment, data recording equipment is for storing arithmetic unit collection from the first photographic head and the reality of second camera Time video image.
A kind of hands based on binocular vision the most according to claim 1 detection equipment, it is characterised in that hands detection equipment is also Including data remote transmitting device, its dangerous driving behavior data that arithmetic unit analysis is drawn, and data recording equipment storage Vedio data be sent to remote data management center.
CN201610648586.1A 2016-08-10 2016-08-10 A kind of hand detection device based on binocular vision Expired - Fee Related CN106228754B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610648586.1A CN106228754B (en) 2016-08-10 2016-08-10 A kind of hand detection device based on binocular vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610648586.1A CN106228754B (en) 2016-08-10 2016-08-10 A kind of hand detection device based on binocular vision

Publications (2)

Publication Number Publication Date
CN106228754A true CN106228754A (en) 2016-12-14
CN106228754B CN106228754B (en) 2019-01-08

Family

ID=57547140

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610648586.1A Expired - Fee Related CN106228754B (en) 2016-08-10 2016-08-10 A kind of hand detection device based on binocular vision

Country Status (1)

Country Link
CN (1) CN106228754B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107403554A (en) * 2017-09-01 2017-11-28 北京壹卡行科技有限公司 Binocular integrated driving person's behavioural analysis apparatus and method for
CN107948620A (en) * 2017-12-28 2018-04-20 智车优行科技(北京)有限公司 Binocular camera adjustment method based on advanced drive assist system
CN111444763A (en) * 2020-02-24 2020-07-24 珠海格力电器股份有限公司 Security control method and device, storage medium and air conditioner
CN112329555A (en) * 2020-10-20 2021-02-05 易显智能科技有限责任公司 Intelligent mixed sensing system for hand action gesture of driver

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6034722A (en) * 1997-11-03 2000-03-07 Trimble Navigation Limited Remote control and viewing for a total station
CN101119481A (en) * 2007-08-27 2008-02-06 刘文萍 Remote alarm video monitoring system and method
CN101739843A (en) * 2009-12-04 2010-06-16 河海大学常州校区 Device and method for real-time three-dimensionally sensing safe driving of vehicle having mixed multi-visual information
CN103029750A (en) * 2012-12-11 2013-04-10 昆山研达电脑科技有限公司 System and method for automatically reminding driver of postures of steering wheel operation
CN105404862A (en) * 2015-11-13 2016-03-16 山东大学 Hand tracking based safe driving detection method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6034722A (en) * 1997-11-03 2000-03-07 Trimble Navigation Limited Remote control and viewing for a total station
CN101119481A (en) * 2007-08-27 2008-02-06 刘文萍 Remote alarm video monitoring system and method
CN101739843A (en) * 2009-12-04 2010-06-16 河海大学常州校区 Device and method for real-time three-dimensionally sensing safe driving of vehicle having mixed multi-visual information
CN103029750A (en) * 2012-12-11 2013-04-10 昆山研达电脑科技有限公司 System and method for automatically reminding driver of postures of steering wheel operation
CN105404862A (en) * 2015-11-13 2016-03-16 山东大学 Hand tracking based safe driving detection method

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107403554A (en) * 2017-09-01 2017-11-28 北京壹卡行科技有限公司 Binocular integrated driving person's behavioural analysis apparatus and method for
CN107403554B (en) * 2017-09-01 2023-07-11 北京九州安华信息安全技术有限公司 Binocular integrated driver behavior analysis device and method
CN107948620A (en) * 2017-12-28 2018-04-20 智车优行科技(北京)有限公司 Binocular camera adjustment method based on advanced drive assist system
CN107948620B (en) * 2017-12-28 2020-06-23 智车优行科技(北京)有限公司 Binocular camera debugging method based on advanced driving assistance system
CN111444763A (en) * 2020-02-24 2020-07-24 珠海格力电器股份有限公司 Security control method and device, storage medium and air conditioner
CN112329555A (en) * 2020-10-20 2021-02-05 易显智能科技有限责任公司 Intelligent mixed sensing system for hand action gesture of driver

Also Published As

Publication number Publication date
CN106228754B (en) 2019-01-08

Similar Documents

Publication Publication Date Title
CN102712317B (en) Vehicular safety systems combining driver and environment sensing
US7884705B2 (en) Safety-drive assistance device
CN106585624B (en) Driver status monitoring method and device
CN104013414B (en) A kind of Study in Driver Fatigue State Surveillance System based on intelligent movable mobile phone
KR101867041B1 (en) Method and device for detecting safe driving state of driver
CN110532976A (en) Method for detecting fatigue driving and system based on machine learning and multiple features fusion
WO2019028798A1 (en) Method and device for monitoring driving condition, and electronic device
CN106228754A (en) A kind of hands based on binocular vision detection equipment
CN104751600B (en) Anti-fatigue-driving safety means and its application method based on iris recognition
CN105303830A (en) Driving behavior analysis system and analysis method
US9662977B2 (en) Driver state monitoring system
CN207637164U (en) A kind of vehicle-mounted fatigue driving monitoring system
CN110826369A (en) Driver attention detection method and system during driving
JPWO2011064831A1 (en) Diagnostic device and diagnostic method
CN103839046A (en) Automatic driver attention identification system and identification method thereof
CN104408878A (en) Vehicle fleet fatigue driving early warning monitoring system and method
CN106965675A (en) A kind of lorry swarm intelligence safety work system
Pech et al. Head tracking based glance area estimation for driver behaviour modelling during lane change execution
CN107563933A (en) A kind of method that vehicle-mounted accident reports automatically
CN114872713A (en) Device and method for monitoring abnormal driving state of driver
CN104299363A (en) Fatigue driving pre-warning system based on multi-feature fusion
CN111294564A (en) Information display method and wearable device
CN103956027A (en) Driver eye fatigue detection device and method
WO2022244747A1 (en) Workplace management system, workplace management method, and workplace management program
CN107590762A (en) The system that a kind of vehicle-mounted accident reports automatically

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20190108

Termination date: 20200810

CF01 Termination of patent right due to non-payment of annual fee