CN103366506A - Device and method for automatically monitoring telephone call behavior of driver when driving - Google Patents

Device and method for automatically monitoring telephone call behavior of driver when driving Download PDF

Info

Publication number
CN103366506A
CN103366506A CN2013102611378A CN201310261137A CN103366506A CN 103366506 A CN103366506 A CN 103366506A CN 2013102611378 A CN2013102611378 A CN 2013102611378A CN 201310261137 A CN201310261137 A CN 201310261137A CN 103366506 A CN103366506 A CN 103366506A
Authority
CN
China
Prior art keywords
driver
mobile telephone
image
phoning
warning
Prior art date
Application number
CN2013102611378A
Other languages
Chinese (zh)
Inventor
王丹
裴明涛
Original Assignee
北京理工大学
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 北京理工大学 filed Critical 北京理工大学
Priority to CN2013102611378A priority Critical patent/CN103366506A/en
Publication of CN103366506A publication Critical patent/CN103366506A/en

Links

Abstract

The invention relates to a device and a method for automatically monitoring a telephone call behavior of a driver when driving and belongs to the fields of intelligent traffic and aided driving. The device comprises an image acquisition device, a calculating device, a warning device and a wireless transmission device. The method comprises the following steps of firstly acquiring a head and nearby area image of the driver, secondly, obtaining the positions of the face and both hands of the driver in the image by skin color detection, and classifying by a support vector machine to determine whether the driver makes a telephone call or not; warning the driver if the driver makes the telephone call; uploading the image that the driver makes the telephone call to the monitoring center of the road transport bureau through a wireless network if the warning is useless to be used as an evidence that the driver breaks the law. According to the device and the method for automatically monitoring the telephone call behavior of the driver when driving disclosed by the invention, the unlawful act of the driver can be effectively monitored, the working strength of law enforcement personnel is relieved, the working efficiency is improved, and the occurrence rate of traffic accidents is reduced.

Description

Connect automatic monitoring device and the method for the behavior of phoning with mobile telephone in a kind of driver drives vehicle way

Technical field

The present invention relates to intelligent transportation field and auxiliary driving field.

Background technology

Along with popularizing that mobile phone uses, while the driver is driving to dial or the behavior of answering cell phone is seen everywhere.Because the driver is connecing when phoning with mobile telephone, the one-hand control bearing circle can not be controlled vehicle well often; The more important thing is, connecing phones with mobile telephone can disperse driver's notice, in case run into accident, often reacts too late, very easily causes traffic hazard.Studies show that, use mobile phone during driving, slow 30% when the reaction velocity ratio of brain is driven when intoxicated, high more than 4 times when using risk that mobile phone gets into an accident than normal driving during driving.It is that driver attention is not concentrated and caused that 70% fatal traffic hazard is arranged, and mobile phone is to cause scatterbrained one of the main reasons.Connect the harmfulness of phoning with mobile telephone to traffic safety in view of driving, existing approximately 50 countries and regions are prohibited the driver and are phoned with mobile telephone connecing on the run in the world at present.Up-to-date " law on road traffic safety implementing regulations " of China are clear " driver dials in the way of travelling or answering cell phone, remembers 3 minutes, imposes a fine 100 yuan " also.

But because the behavior occurs on the automobile of running at high speed, outside car, be difficult to catch.The monitoring that at present driver's driving connects the behavior of phoning with mobile telephone mainly contains three kinds of methods.The first is law enfrocement official's on-site law-enforcing, but the law enfrocement official generally only appears at a few regions such as crossing, and therefore this method has significant limitation.The second is the outer camera head monitor of car.This mode can photograph the driver uses the behavior of mobile phone when driving, and enlarges although monitoring range is compared with first method to some extent, also is only limited in the scope that the camera monitoring is arrived, in most of zone or monitor less than the behavior.In addition, the method also needs the monitor staff constantly to stare at watch-dog to judge this illegal activities, and working strength is large, and efficient is low, and night efficient lower.The third is the oriented antenna monitoring to be installed from the mobile phone signal on the vehicle in travelling in fixed area, carries out scene evidence taking if the signal of conversing then starts image documentation equipment.Although the method can play the function of automatic monitoring, can take the vehicle that all detect the mobile phone signal of conversing, and this moment not necessarily the driver making a phone call, also may be that others has the situation of a lot of flase drops in conversation in the car.Camera all is positioned on outside the car in rear two kinds of methods, sometimes because weather or the reason such as block so that the picture that photographs can not be seen situation in the car very clearly, has undetected and flase drop occurs.

Based on above reason, " connect in the driving way and phone with mobile telephone " behavior can't effectively be monitored, so that this behavior is seen everywhere, traffic safety has been caused very large hidden danger.At present, also not based on camera in the car to connecing the device that automatic monitoring is carried out in the behavior of phoning with mobile telephone in the driver drives vehicle way.

Summary of the invention

For addressing the above problem, the invention provides the automatic monitoring device and the method that connect the behavior of phoning with mobile telephone in a kind of driver drives vehicle way.By camera collection driver head in the car and near zone image, utilize image processing techniques and mode identification method automatically to identify connecing the behavior of phoning with mobile telephone in the driver drives vehicle way, and with its in violation of rules and regulations picture shooting networking of getting off upload to the Surveillance center of Department of Communications, as the violation evidence.The invention provides a kind of to connecing the method that automatic monitoring is carried out in the behavior of phoning with mobile telephone in the driver drives vehicle way.Can greatly reduce law enforcement intensity, improve law enforcement efficiency, effectively avoid because of the traffic hazard of dialing in the driver drives vehicle way or the answering cell phone behavior causes.And the present invention is installed in camera on the front windshield in the car, can photograph very clearly driver's behavior, and not need other electron devices auxiliary, can not have influence on driver's normal driving.

Connect the automatic monitoring device of the behavior of phoning with mobile telephone in a kind of driver drives vehicle way, comprising: image acquiring device, calculation element, warning device and radio transmitting device; Wherein,

Image acquiring device adopts the video camera that is fixed on the interior front windshield of car to obtain driver's head and near zone image, and sends image to calculation element;

Calculation element obtains driver's face and the position of hand in image by Face Detection, calculate face and the histogram of gradients feature of hand region and driver's lip shape feature, obtaining the driver uses under the mobile phone state and does not use feature under the mobile phone state, classify by support vector machine, thereby determining whether the driver connects in driving procedure phones with mobile telephone, and whether the driver is connect the information of phoning with mobile telephone passes to warning device;

Warning device is after receiving driver that calculation element sends and connecing the information of phoning with mobile telephone, the driver is given a warning, connect the information of phoning with mobile telephone if still receive the driver that calculation element sends after giving a warning, then transmitting a signal to radio transmitting device;

Radio transmitting device meets the driver image of phoning with mobile telephone uploads to Department of Communications by wireless network Surveillance center, as its illegal evidence.

Connect the automatic monitoring method of the behavior of phoning with mobile telephone in a kind of driver drives vehicle way, performing step is as follows:

Step 1: supervising device is opened automatically when vehicle motor starts, device carries out self check operation, checks in the video pictures that photographs whether people's face is arranged, and whether people's face is in the specific zone (prevent the driver from moving or radical occlusion device), if above condition all satisfies, then bearing circle release; Otherwise bearing circle is in the lock state, and the driver can not steering vehicle.

Step 2: device is normal start after, begin to monitor the head zone image, if find have the driver to connect and phone with mobile telephone posture in the process of Vehicle Driving Cycle certain hour occurs to surpass, and simultaneously with the lip action, judge that then it phones with mobile telephone connecing.

Step 3: alarm device generation alarm, if after alarm sent for 3 seconds, the driver does not still stop using mobile phone, then camera uses the image of mobile phone to upload to the Surveillance center of Department of Communications by network it, as its illegal evidence, make things convenient for the law enfrocement official that these illegal activities are processed.

Step 4: this device is only opened in the Vehicle Driving Cycle way, and when vehicle stop, device quits work automatically.

Advantage of the present invention:

1. can in driver's driving way, connect the unlawful practice of phoning with mobile telephone by Real Time Monitoring.

2. can automatically be delivered to Surveillance center with recording in violation of rules and regulations, alleviate law enfrocement official's work load, increase work efficiency.

3. this device is automatically operation, does not need driver's operation, is simple and easy to use.

4. this device is solar obligation, and can guarantee the realization of this function, can effective monitoring driver illegal activities, and reduce this illegal activities, thereby reduce the incidence of traffic hazard.

5. camera is mounted in the car, is not subjected to external environment such as weather, the impact of factor such as blocks, and can photograph clearly image.

Description of drawings

Fig. 1 is the process flow diagram that connects monitoring, warning and the automatic evidence-collecting of the behavior of phoning with mobile telephone among the present invention in the driver drives vehicle way;

Fig. 2 is used for the rectangular characteristic that driver people's face detects among the present invention.

Embodiment

Core thinking of the present invention is: the driver is connecing when phoning with mobile telephone, and certainly has handheld mobile phone near the action of ear, and with lip movement.By video analysis, judge whether to produce these behaviors, thereby judge that whether it phone with mobile telephone connecing.In case determine its illegal activities, in the situation that warning is invalid, send its violation image to Surveillance center at once, and form an in violation of rules and regulations record, be convenient to the law enfrocement official and collect evidence.

Automatic monitoring device of the present invention comprises: image acquiring device, calculation element, warning device and radio transmitting device; Wherein,

Image acquiring device adopts the video camera that is fixed on the interior front windshield of car to obtain driver's head and near zone image;

Calculation element obtains driver's face and the position of hand in image by Face Detection, calculate face and the histogram of gradients feature of hand region and driver's lip shape feature, obtaining the driver uses under the mobile phone state and does not use feature under the mobile phone state, classify by support vector machine, thereby determining whether the driver connects in driving procedure phones with mobile telephone;

Warning device calculation element determine the driver connecing phone with mobile telephone after, the driver is given a warning;

Radio transmitting device meets the driver image of phoning with mobile telephone uploads to Department of Communications by wireless network Surveillance center, as its illegal evidence.

Connect the process flow diagram of the behavior monitoring of phoning with mobile telephone, warning and automatic evidence-collecting in the driver drives vehicle way based on camera in the car among the present invention as shown in Figure 1, the implementation step is as follows:

Step 1: supervising device is opened automatically when vehicle motor starts, device carries out self check operation, checks in the video pictures that photographs whether people's face is arranged, and whether people's face is in the specific zone (prevent the driver from moving or radical occlusion device), if above condition all satisfies, then bearing circle release; Otherwise bearing circle is in the lock state, and the driver can not steering vehicle.

The location of driver people's face is carried out in employing based on the method for detecting human face of AdaBoost.The method is picked out a small amount of key feature with the AdaBoost method again take rectangular characteristic as according to constructing Weak Classifier, constructs strong classifier thereby corresponding Weak Classifier is weighted summation, and it is used for the detection of people's face as final sorter.Wherein, each rectangular characteristic is comprised of 2-3 rectangle, and as shown in Figure 2, its value deducts the interior pixel value sum of black rectangle for the pixel value sum in the white rectangle.

Each Weak Classifier is comprised of a rectangular characteristic, strong classifier the training flow process as follows:

(1) given training data (x 1, y 1) ... (x n, y n), y wherein i=0 expression negative sample, y iThe positive sample of=1 expression, n is the number of training sample.

(2) initialization weights, y i=0 o'clock y i=1 o'clock M, l are respectively the numbers of negative sample and positive sample.

(3) corresponding t=1 ..., T:

A. normalization weights w t , i ← w t , i Σ j = 1 n w t , j

B. to each feature j, training Weak Classifier h jIf the error of this sorter is ε j=∑ iw i| h j(x i)-y i|

C. select sorter h with least error t

D. refreshing weight E wherein iIf=0 x iCorrectly classified, otherwise e i=1, β t = ϵ t 1 - ϵ t

(4) then final strong classifier is

h ( x ) = 1 Σ t = 1 T α t h t ( x ) ≥ 1 2 Σ t = 1 T α t 0 otherwise , Wherein α t = log 1 β t

After obtaining strong classifier, use strong classifier that image is scanned, obtain people's face position of driver, if people's face in the central area of image, then installs normal operation.The self check success, the bearing circle release, the driver can actuating vehicle.

Step 2: after installing normal the startup, automatic monitoring head zone image in the Vehicle Driving Cycle process is phoned with mobile telephone the posture generation above certain hour if find have the driver to connect, and simultaneously with the lip action, judges that then it is using mobile phone.

Because driver's abnormal driving state and the use state that hand is placed on ear during mobile phone is compared very large difference is arranged.Therefore we adopt the mode of training svm classifier device to judge that whether the driver phones with mobile telephone connecing.Because the driver is speaking and when silent, the lip state has obvious difference, judge therefore whether driver's lip moves the mode that also adopts training svm classifier device.Comprehensive above two clues, the driver has made and has connect the posture of phoning with mobile telephone and surpass certain hour, and therebetween with the lip action, judges that then the driver phones with mobile telephone connecing.

1) the HOG feature of extraction driver head zone

The employed feature of training classifier is the HOG feature.HOG is histogram of orientedgradient(gradient orientation histogram), be the Feature Descriptor for target detection, it calculates the direction gradient number of times that image local occurs.The method is by being divided into entire image little join domain (being called cells), and each cell generates a histograms of oriented gradients, and these histogrammic combinations can be expressed the descriptor of the target that detects.For improving accuracy rate, can be with all the cells normalization in the larger zone (being called block) in the image.Finished better irradiation/shade unchangeability by the normalization process.

The HOG feature extracting method is as follows:

(1) image is converted into gray level image.

(2) image is divided into little cells(eg:2*2).

(3) calculate the gradient of each pixel among each cell.

Gradient magnitude: R ( x , y ) = ( I ( x + 1 , y ) - I ( x - 1 , y ) ) 2 + ( I ( x , y + 1 ) - I ( x , y - 1 ) ) 2

Gradient direction: Ang (x, y)=arctan ((I (x+1, y)-I (x-1, y))/(I (x, y+1)-I (x, y-1)))

(4) all cells among each block of normalization.Adopt L2-norm to carry out normalization:

L2-norm: v → v / | | v | | 2 2 + ϵ 2

(5) generate the HOG feature.Calculate the HOG feature among all block in the detection window, and connect into final proper vector for classifying.

2) use SVM that the HOG feature is classified

After having extracted the HOG feature of driver's head zone, with its input as the svm classifier device, classify, to judge driver's head pose.

SVM is Support Vector Machine(support vector machine), it is a kind of method of supervising formula study, shows many distinctive advantages in solving small sample, non-linear and higher-dimension pattern-recognition.SVM based on the structural risk minimization theory in feature space construction optimum segmentation lineoid so that sorter obtains global optimization, and satisfy certain upper bound in the expected risk of whole sample space with certain probability.

The mathematical form of supposing lineoid is: wx-b=0.Wherein x is the point on the lineoid, and w is perpendicular to the vector of lineoid.(x (i), y (i)) be training sample.x (i)Feature input for training sample; y (i)Be its corresponding label, wherein y (i)∈ 1 ,-1}.Then in the situation that linear separability, optimum lineoid can obtain by separating following double optimization problem:

min 1 2 | | w | | 2

Satisfy constraint condition: y (i)(w Tx (i)+ b) 〉=1, and i=1,2 ..., m

3) judge driver's lip state

The process of judging driver's lip state is:

1. detect people's face position by the Adaboost learning algorithm

2. lip position coarse positioning.According to priori, lip is positioned at the latter half of people's face.

3. lip shape and location positioning.Training skin color and lip color are determined respectively its color gamut, utilize the Fisher linear classifier that skin color and lip chromatic zones are separated, and are partitioned into mouth region.

4. elimination noise.Corrode first the method for rear expansion by the mouth region that previous step is partitioned into, eliminate little connected region, reach the purpose of removing noise.Zone behind the removal noise is exactly mouth region.

5. the mouth profile is determined.The detected mouth region of previous step is carried out the horizontal and vertical projection, obtain the mouth profile.

6. feature extraction.Calculate the breadth extreme W of mouth region according to the mouth profile Max, maximum height H Max, and the height H between upper lip and the lower lip mThese several values have obvious different when the people speaks and be silent, so are taken as feature.F=(W amx,H max,H m).

7. training svm classifier device is classified to the lip feature, differentiates driver's mouth state.4) judge that whether the driver phones with mobile telephone connecing

When using SVM that the HOG feature of driver's head zone is classified, judging that it belongs to connects the posture of phoning with mobile telephone, judge simultaneously driver's lip state for speaking state, and this type of situation duration when surpassing given threshold value, judge that then the driver phones with mobile telephone connecing.

Step 3: alarm device gives the alarm, if after alarm sent for 3 seconds, the driver does not still stop using mobile phone, and then radio transmitting device uploads to the image of its use mobile phone law enfrocement official's Surveillance center by network, as its illegal evidence.And with its illegal activities, the content records such as time get off, and make things convenient for the law enfrocement official that these illegal activities are processed.

Step 4: this device is only opened in the Vehicle Driving Cycle way, and when vehicle stop, device quits work automatically.

Claims (2)

1. connect the automatic monitoring device of the behavior of phoning with mobile telephone in the driver drives vehicle way, it is characterized in that: this automatic monitoring device comprises image acquiring device, calculation element, warning device and radio transmitting device; Wherein,
Image acquiring device adopts the video camera that is fixed on the interior front windshield of car to obtain driver's head and near zone image, and sends image to calculation element;
Calculation element passes through training sample, obtaining the driver connects under the state of phoning with mobile telephone and the non-feature that connects under the state of phoning with mobile telephone, can classify to each sub-picture that image acquiring device obtains, thereby can determine further whether the driver connects in driving procedure phones with mobile telephone, and whether the driver is connect the information of phoning with mobile telephone passes to warning device;
Warning device is after receiving driver that calculation element sends and connecing the information of phoning with mobile telephone, the driver is given a warning, connect the information of phoning with mobile telephone if still receive the driver that calculation element sends after giving a warning, then transmitting a signal to radio transmitting device;
Radio transmitting device meets the driver image of phoning with mobile telephone uploads to Department of Communications by wireless network Surveillance center, as its illegal evidence.
2. connect the automatic monitoring method of the behavior of phoning with mobile telephone in the driver drives vehicle way, it is characterized in that:
Step 1: supervising device is opened automatically when vehicle motor starts, and device carries out self check operation, checks in the video pictures that photographs whether people's face is arranged, and whether people's face be in the specific zone, if above condition all satisfies, and then bearing circle release; Otherwise bearing circle is in the lock state, and the driver can not steering vehicle;
Step 2: after the normal startup of device, begin to monitor the head zone image.Calculation element obtains driver's face and the position of hand in image by Face Detection, calculate face and the histogram of gradients feature of hand region and driver's lip shape feature, classify by support vector machine, thereby determine that whether the driver phones with mobile telephone connecing.Occur to surpass certain hour if in the process of Vehicle Driving Cycle, find have the driver to connect and phone with mobile telephone posture, judge that then it phones with mobile telephone connecing;
Step 3: alarm device generation alarm, if after alarm sent for 3 seconds, the driver does not still stop using mobile phone, then camera uses the image of mobile phone to upload to the Surveillance center of Department of Communications by network it, as its illegal evidence, make things convenient for the law enfrocement official that these illegal activities are processed;
Step 4: this device is only opened in the Vehicle Driving Cycle way, and when vehicle stop, device quits work automatically.
CN2013102611378A 2013-06-27 2013-06-27 Device and method for automatically monitoring telephone call behavior of driver when driving CN103366506A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2013102611378A CN103366506A (en) 2013-06-27 2013-06-27 Device and method for automatically monitoring telephone call behavior of driver when driving

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2013102611378A CN103366506A (en) 2013-06-27 2013-06-27 Device and method for automatically monitoring telephone call behavior of driver when driving

Publications (1)

Publication Number Publication Date
CN103366506A true CN103366506A (en) 2013-10-23

Family

ID=49367754

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2013102611378A CN103366506A (en) 2013-06-27 2013-06-27 Device and method for automatically monitoring telephone call behavior of driver when driving

Country Status (1)

Country Link
CN (1) CN103366506A (en)

Cited By (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103942961A (en) * 2014-04-30 2014-07-23 中国计量学院 Dangerous-driving-behavior-oriented intelligent monitoring recognition system
CN104228679A (en) * 2014-09-30 2014-12-24 浙江吉利控股集团有限公司 Device for prompting phone call receiving and making in running process of vehicle
CN104505089A (en) * 2014-12-17 2015-04-08 福建网龙计算机网络信息技术有限公司 Method and equipment for oral error correction
CN104517444A (en) * 2015-01-08 2015-04-15 北京理工大学 Detection system for unlawful act of using cell phones while driving
CN104573724A (en) * 2015-01-09 2015-04-29 安徽清新互联信息科技有限公司 Method for monitoring call making and receiving behaviors of driver
CN104573659A (en) * 2015-01-09 2015-04-29 安徽清新互联信息科技有限公司 Driver call-making and call-answering monitoring method based on svm
CN104683847A (en) * 2015-02-04 2015-06-03 四川长虹电器股份有限公司 Television capable of controlling volume intelligently and method
CN104751663A (en) * 2015-02-28 2015-07-01 北京壹卡行科技有限公司 Safe driving auxiliary system and safe driving auxiliary method for driver
CN105015341A (en) * 2015-07-23 2015-11-04 江苏大学 Device of preventing dangerous driving caused by using mobile phone during driving and method of preventing dangerous driving caused by using mobile phone during driving
CN105260705A (en) * 2015-09-15 2016-01-20 西安邦威电子科技有限公司 Detection method suitable for call receiving and making behavior of driver under multiple postures
CN105469073A (en) * 2015-12-16 2016-04-06 安徽创世科技有限公司 Kinect-based call making and answering monitoring method of driver
CN105516917A (en) * 2014-09-30 2016-04-20 小米科技有限责任公司 Method and device for realizing safe driving
CN105573206A (en) * 2015-09-14 2016-05-11 赵立 Method for limiting driver to use cellphone during driving
CN105989328A (en) * 2014-12-11 2016-10-05 由田新技股份有限公司 Method and apparatus for detecting person to use handheld device
CN105989329A (en) * 2014-12-11 2016-10-05 由田新技股份有限公司 Method and apparatus for detecting person to use handheld device
CN106056071A (en) * 2016-05-30 2016-10-26 北京智芯原动科技有限公司 Method and device for detection of driver' behavior of making call
CN106203385A (en) * 2016-07-20 2016-12-07 东方网力科技股份有限公司 A kind of driver's hand-held phone behavioral value method and device
CN106447303A (en) * 2016-10-22 2017-02-22 辽宁科技大学 Device and method for observing behavior safety of enterprise employees
CN106682601A (en) * 2016-12-16 2017-05-17 华南理工大学 Driver violation conversation detection method based on multidimensional information characteristic fusion
CN106815574A (en) * 2017-01-20 2017-06-09 博康智能信息技术有限公司北京海淀分公司 Set up detection model, detect the method and apparatus for taking mobile phone behavior
CN107392187A (en) * 2017-08-30 2017-11-24 西安建筑科技大学 A kind of human face in-vivo detection method based on gradient orientation histogram
CN107545225A (en) * 2016-06-23 2018-01-05 杭州海康威视数字技术股份有限公司 A kind of method, apparatus and electronic equipment for detecting vehicle carried driving person's unlawful practice
CN107891807A (en) * 2017-11-01 2018-04-10 北京汽车研究总院有限公司 A kind of auto alarm method and vehicle-mounted alarm system
CN108259817A (en) * 2016-12-28 2018-07-06 南宁富桂精密工业有限公司 Picture shooting system and method
WO2018133874A1 (en) * 2017-01-23 2018-07-26 杭州海康威视数字技术股份有限公司 Method and device for sending warning message
CN108509902A (en) * 2018-03-30 2018-09-07 湖北文理学院 A kind of hand-held telephone relation behavioral value method during driver drives vehicle
CN108564034A (en) * 2018-04-13 2018-09-21 湖北文理学院 The detection method of operating handset behavior in a kind of driver drives vehicle
CN108608940A (en) * 2018-04-27 2018-10-02 长沙硕铠电子科技有限公司 A method of judge smart mobile phone whether in driver's seat region
CN108682158A (en) * 2018-03-23 2018-10-19 深圳融易保科技有限公司 Video analysis and scoring method for early warning and system
CN108682157A (en) * 2018-03-23 2018-10-19 深圳融易保科技有限公司 Video analysis and method for early warning and system
CN109285327A (en) * 2018-07-05 2019-01-29 惠州市德赛西威汽车电子股份有限公司 A kind of processing method using mobile phone for driver in driving conditions
CN110677579A (en) * 2019-08-19 2020-01-10 北京达佳互联信息技术有限公司 Early warning method and device based on shooting scene, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102023703A (en) * 2009-09-22 2011-04-20 现代自动车株式会社 Combined lip reading and voice recognition multimodal interface system
CN102390349A (en) * 2011-09-28 2012-03-28 福州海景科技开发有限公司 Vehicle anti-theft system based on infrared and face recognition technology
CN102567743A (en) * 2011-12-20 2012-07-11 东南大学 Automatic identification method of driver gestures based on video images
CN102592143A (en) * 2012-01-09 2012-07-18 清华大学 Method for detecting phone holding violation of driver in driving
CN103129492A (en) * 2013-03-01 2013-06-05 公安部第三研究所 Vehicular intelligent multimedia terminal device
KR20130068945A (en) * 2011-12-16 2013-06-26 현대자동차주식회사 Interaction system for vehicles

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102023703A (en) * 2009-09-22 2011-04-20 现代自动车株式会社 Combined lip reading and voice recognition multimodal interface system
CN102390349A (en) * 2011-09-28 2012-03-28 福州海景科技开发有限公司 Vehicle anti-theft system based on infrared and face recognition technology
KR20130068945A (en) * 2011-12-16 2013-06-26 현대자동차주식회사 Interaction system for vehicles
CN102567743A (en) * 2011-12-20 2012-07-11 东南大学 Automatic identification method of driver gestures based on video images
CN102592143A (en) * 2012-01-09 2012-07-18 清华大学 Method for detecting phone holding violation of driver in driving
CN103129492A (en) * 2013-03-01 2013-06-05 公安部第三研究所 Vehicular intelligent multimedia terminal device

Cited By (44)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103942961A (en) * 2014-04-30 2014-07-23 中国计量学院 Dangerous-driving-behavior-oriented intelligent monitoring recognition system
CN105516917A (en) * 2014-09-30 2016-04-20 小米科技有限责任公司 Method and device for realizing safe driving
CN104228679A (en) * 2014-09-30 2014-12-24 浙江吉利控股集团有限公司 Device for prompting phone call receiving and making in running process of vehicle
CN105989329A (en) * 2014-12-11 2016-10-05 由田新技股份有限公司 Method and apparatus for detecting person to use handheld device
CN105989328A (en) * 2014-12-11 2016-10-05 由田新技股份有限公司 Method and apparatus for detecting person to use handheld device
CN104505089A (en) * 2014-12-17 2015-04-08 福建网龙计算机网络信息技术有限公司 Method and equipment for oral error correction
CN104505089B (en) * 2014-12-17 2018-05-18 福建网龙计算机网络信息技术有限公司 Spoken error correction method and equipment
CN104517444A (en) * 2015-01-08 2015-04-15 北京理工大学 Detection system for unlawful act of using cell phones while driving
CN104573724A (en) * 2015-01-09 2015-04-29 安徽清新互联信息科技有限公司 Method for monitoring call making and receiving behaviors of driver
CN104573659B (en) * 2015-01-09 2018-01-09 安徽清新互联信息科技有限公司 A kind of driver based on svm takes phone-monitoring method
CN104573659A (en) * 2015-01-09 2015-04-29 安徽清新互联信息科技有限公司 Driver call-making and call-answering monitoring method based on svm
CN104683847A (en) * 2015-02-04 2015-06-03 四川长虹电器股份有限公司 Television capable of controlling volume intelligently and method
CN104751663A (en) * 2015-02-28 2015-07-01 北京壹卡行科技有限公司 Safe driving auxiliary system and safe driving auxiliary method for driver
CN105015341A (en) * 2015-07-23 2015-11-04 江苏大学 Device of preventing dangerous driving caused by using mobile phone during driving and method of preventing dangerous driving caused by using mobile phone during driving
CN105573206A (en) * 2015-09-14 2016-05-11 赵立 Method for limiting driver to use cellphone during driving
CN105260705A (en) * 2015-09-15 2016-01-20 西安邦威电子科技有限公司 Detection method suitable for call receiving and making behavior of driver under multiple postures
CN105260705B (en) * 2015-09-15 2019-07-05 西安邦威电子科技有限公司 A kind of driver's making and receiving calls behavioral value method suitable under multi-pose
CN105469073A (en) * 2015-12-16 2016-04-06 安徽创世科技有限公司 Kinect-based call making and answering monitoring method of driver
CN106056071A (en) * 2016-05-30 2016-10-26 北京智芯原动科技有限公司 Method and device for detection of driver' behavior of making call
CN106056071B (en) * 2016-05-30 2019-05-10 北京智芯原动科技有限公司 A kind of driver makes a phone call the detection method and device of behavior
CN107545225A (en) * 2016-06-23 2018-01-05 杭州海康威视数字技术股份有限公司 A kind of method, apparatus and electronic equipment for detecting vehicle carried driving person's unlawful practice
CN106203385B (en) * 2016-07-20 2019-07-09 东方网力科技股份有限公司 A kind of hand-held phone behavioral value method and device of driver
CN106203385A (en) * 2016-07-20 2016-12-07 东方网力科技股份有限公司 A kind of driver's hand-held phone behavioral value method and device
CN106447303A (en) * 2016-10-22 2017-02-22 辽宁科技大学 Device and method for observing behavior safety of enterprise employees
CN106682601B (en) * 2016-12-16 2019-11-15 华南理工大学 A kind of driver's violation call detection method based on multidimensional information Fusion Features
CN106682601A (en) * 2016-12-16 2017-05-17 华南理工大学 Driver violation conversation detection method based on multidimensional information characteristic fusion
CN108259817A (en) * 2016-12-28 2018-07-06 南宁富桂精密工业有限公司 Picture shooting system and method
CN106815574A (en) * 2017-01-20 2017-06-09 博康智能信息技术有限公司北京海淀分公司 Set up detection model, detect the method and apparatus for taking mobile phone behavior
CN106815574B (en) * 2017-01-20 2020-10-02 博康智能信息技术有限公司北京海淀分公司 Method and device for establishing detection model and detecting behavior of connecting and calling mobile phone
CN108345819B (en) * 2017-01-23 2020-09-15 杭州海康威视数字技术股份有限公司 Method and device for sending alarm message
WO2018133874A1 (en) * 2017-01-23 2018-07-26 杭州海康威视数字技术股份有限公司 Method and device for sending warning message
CN108345819A (en) * 2017-01-23 2018-07-31 杭州海康威视数字技术股份有限公司 A kind of method and apparatus sending warning message
CN107392187B (en) * 2017-08-30 2020-08-11 西安建筑科技大学 Face in-vivo detection method based on gradient direction histogram
CN107392187A (en) * 2017-08-30 2017-11-24 西安建筑科技大学 A kind of human face in-vivo detection method based on gradient orientation histogram
CN107891807B (en) * 2017-11-01 2020-05-26 北京汽车研究总院有限公司 Automobile alarm method and vehicle-mounted alarm system
CN107891807A (en) * 2017-11-01 2018-04-10 北京汽车研究总院有限公司 A kind of auto alarm method and vehicle-mounted alarm system
CN108682157A (en) * 2018-03-23 2018-10-19 深圳融易保科技有限公司 Video analysis and method for early warning and system
CN108682158A (en) * 2018-03-23 2018-10-19 深圳融易保科技有限公司 Video analysis and scoring method for early warning and system
CN108509902A (en) * 2018-03-30 2018-09-07 湖北文理学院 A kind of hand-held telephone relation behavioral value method during driver drives vehicle
CN108509902B (en) * 2018-03-30 2020-07-03 湖北文理学院 Method for detecting call behavior of handheld phone in driving process of driver
CN108564034A (en) * 2018-04-13 2018-09-21 湖北文理学院 The detection method of operating handset behavior in a kind of driver drives vehicle
CN108608940A (en) * 2018-04-27 2018-10-02 长沙硕铠电子科技有限公司 A method of judge smart mobile phone whether in driver's seat region
CN109285327A (en) * 2018-07-05 2019-01-29 惠州市德赛西威汽车电子股份有限公司 A kind of processing method using mobile phone for driver in driving conditions
CN110677579A (en) * 2019-08-19 2020-01-10 北京达佳互联信息技术有限公司 Early warning method and device based on shooting scene, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
Bas et al. Automatic vehicle counting from video for traffic flow analysis
CN105208343B (en) Can be used for intelligent monitor system and the method for video monitoring equipment
US10706330B2 (en) Methods and systems for accurately recognizing vehicle license plates
Wang et al. Walksafe: a pedestrian safety app for mobile phone users who walk and talk while crossing roads
US8339282B2 (en) Security systems
CN104537788B (en) High voltage electric transmission line external damage-proof intelligent image pre-warning system and method
CN103246876B (en) Image feature comparison based counterfeit vehicle registration plate identification method
CN102592143B (en) Method for detecting phone holding violation of driver in driving
CN100446043C (en) Video safety prevention and monitoring method based on biology sensing and image information fusion
KR101215948B1 (en) Image information masking method of monitoring system based on face recognition and body information
CN101639894B (en) Method for detecting train driver behavior and fatigue state on line and detection system thereof
CN104013414A (en) Driver fatigue detecting system based on smart mobile phone
US20150186714A1 (en) Driver behavior monitoring systems and methods for driver behavior monitoring
CN105744232B (en) A kind of method of the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology
CN105488453B (en) A kind of driver based on image procossing does not fasten the safety belt detection recognition method
CN101587544B (en) Based on the carried on vehicle antitracking device of computer vision
CN102665071B (en) Intelligent processing and search method for social security video monitoring images
CN104123544A (en) Video analysis based abnormal behavior detection method and system
CN100545867C (en) Aerial shooting traffic video frequency vehicle rapid checking method
CN103839373A (en) Sudden abnormal event intelligent identification alarm device and system
CN105185123A (en) Fake plate vehicle recognition system and method
KR100918436B1 (en) Fire detection system and method basedon visual data
CN103729858B (en) A kind of video monitoring system is left over the detection method of article
CN101179710B (en) Intelligent video monitoring apparatus of railway crossing
CN103208185A (en) Method and system for nighttime vehicle detection on basis of vehicle light identification

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20131023

C02 Deemed withdrawal of patent application after publication (patent law 2001)