CN106503673A - A kind of recognition methodss of traffic driving behavior, device and a kind of video acquisition device - Google Patents
A kind of recognition methodss of traffic driving behavior, device and a kind of video acquisition device Download PDFInfo
- Publication number
- CN106503673A CN106503673A CN201610959443.2A CN201610959443A CN106503673A CN 106503673 A CN106503673 A CN 106503673A CN 201610959443 A CN201610959443 A CN 201610959443A CN 106503673 A CN106503673 A CN 106503673A
- Authority
- CN
- China
- Prior art keywords
- driver
- target vehicle
- car plate
- image
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of recognition methodss of traffic driving behavior, device and a kind of video acquisition device, wherein, the recognition methodss of the traffic driving behavior include:Obtain testing image;From the testing image, the position of driver information of target vehicle is obtained;According to the position of driver information, the driving behavior of the target vehicle driver is recognized.The present invention is by obtaining driver's driving image in target vehicle in real time, and carries out automatic identification to which automatically.Using technical solution of the present invention, the driving behavior of driver in the case where the driving behavior of driver need not be affected, can be real-time monitored, such that it is able to effectively avoid due to vehicle accident caused by bad steering behavior.
Description
Technical field
The present invention relates to intelligent traffic monitoring technical field, more particularly to a kind of recognition methodss of traffic driving behavior, dress
Put and a kind of video acquisition device.
Background technology
With the continuous improvement of economic level and living standards of the people, in each big-and-middle small city, vehicle constantly increases.With
This simultaneously, thing followed traffic problems also increasingly receive much concern.In the driving procedure of vehicle, driver is not only needed to need
Consummate driving ability is wanted, has a good driving habit with greater need for driver.The detection technique of existing driving behavior is main
Driver driving behavior is detected by using sensor;The sensor needs directly to contact with driver's body to be detected.
Therefore, during the automatic identification of inventor's developing intellectual resource traffic driving behavior, find in prior art extremely
It is few that there are the following problems:
Used in prior art, sensor detection driver driving behavior, sensor is directly contacted with driver's body, right
Driving is interfered, and can not comprehensively recognize bad steering behavior, for example:Make a phone call in driving, do not fasten the safety belt, bow
Drive, eat.
Content of the invention
In view of the above problems, it is proposed that the present invention so as to provide one kind overcome the problems referred to above or at least in part solve on
Problem is stated, be the technical scheme is that and be achieved in that:
On the one hand, the invention provides a kind of recognition methodss of traffic driving behavior, including:
Obtain testing image;
From the testing image, the position of driver information of target vehicle is obtained;
According to the position of driver information, the driving behavior of the target vehicle driver is recognized.
Present invention also offers a kind of identifying device of traffic driving behavior, including:
Image acquisition unit, for obtaining testing image;
Position determination unit, for, from the testing image, obtaining the position of driver information of target vehicle;
Recognition unit, for according to the position of driver information, recognizing the driving behavior of the target vehicle driver.
Present invention also offers a kind of video acquisition device, including the identifying device of traffic driving behavior as described above.
, by positioning the car plate of target vehicle in testing image, further locating human face is confirming for technical scheme
The image of human pilot, on the premise of driver is not disturbed, drives row for round-the-clock or section in limited time automatic detection traffic
For effectively whether identification driver has unlawful practice during driving, and effectively can avoid making because of driver's violation operation
Into vehicle accident, while sunshade board status can be recognized, feed back the dubiety of vehicle in time.
Description of the drawings
Fig. 1 is a kind of recognition methodss flow chart of traffic driving behavior provided in an embodiment of the present invention;
Fig. 2 is the recognition methodss flow chart of another kind of traffic driving behavior provided in an embodiment of the present invention;
Fig. 3 is a kind of identifying device structural representation of traffic driving behavior provided in an embodiment of the present invention;
Fig. 4 is a kind of video acquisition device structural representation provided in an embodiment of the present invention.
Specific embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing to embodiment party of the present invention
Formula is described in further detail.
If Fig. 1 is the recognition methodss flow chart for showing a kind of traffic driving behavior provided in an embodiment of the present invention;The party
Method includes:
101:Obtain testing image;
102:From the testing image, the position of driver information of target vehicle is obtained;The step is specifically included:From institute
State in testing image, obtain the car plate positional information of the target vehicle;According to the car plate positional information of the target vehicle, really
With the presence or absence of driver's face and its position in the fixed target vehicle image;If there is the driver in the testing image
Face, according to driver's face location in the target vehicle, obtains the position of driver information of the target vehicle;If described
There is no driver's face in testing image, carry out sunshading board detection, determine current for opening sunshade board status.
103:According to the position of driver information, the driving behavior of the target vehicle driver is recognized.
Above example is based on, as shown in Fig. 2 the identification for another kind of traffic driving behavior provided in an embodiment of the present invention
Method flow diagram;The method includes:
201:Obtain testing image;
202:From the testing image, the car plate positional information of the target vehicle is obtained;The step was implemented
Journey:Detected by sliding window, determine the car plate positional information of the target vehicle;The car plate positional information includes:Car plate
The coordinate of position and size.
203:According to the car plate positional information of the target vehicle, determine in the target vehicle image with the presence or absence of driving
Member's face and its position;The step implements process:According to the car plate positional information of the target vehicle, the mesh is determined
Driver's human face region in mark vehicle;In the target vehicle in driver's human face region, Face datection is carried out, judged described
With the presence or absence of driver's face and its position in testing image;If there is no the driver people in the testing image
Face, carries out sunshading board detection, determines current for opening sunshade board status.
204:If there is driver's face in the testing image, according to driver's face position in the target vehicle
Put, obtain the position of driver information of the target vehicle.
205:If there is no driver's face in the testing image, sunshading board detection is carried out, determine that current is to beat
Open sunshade board status.
206:According to position of driver information described in above step 204, the driving of the target vehicle driver is recognized
Behavior;The step implements process:According to position of driver information in the target vehicle, obtain in the target vehicle
Driver's image;By driver's image in the target vehicle, the driving behavior of the target vehicle driver is recognized.
It should be noted that driver's image is obtained in the target vehicle;Specifically acquisition process is:According to the face
Driver's face location in the target vehicle that detector training determines, obtains driver's image in the target vehicle;Due to institute
State driver's image in target vehicle to there are many interference noises, block, add that driver's dressing is different, attitudes vibration ten thousand
Thousand, so technical solution of the present invention adopts deep learning method convolutional neural networks (Convolutional Neural
Network, abbreviation CNN), learning network is built, by some convolutional layers, pond layer, full articulamentum, Dropout layers, is revised linear
Unit (Relu) layer, Softmax layers are constituted, and make full use of mass data information to train vehicle attribute identification model, practice card
The bright driving behavior identification based on depth convolutional network has very high accuracy of identification.
CNN networks are made up of 4 convolutional layers, 1 full articulamentum and a softmax layer, wherein after three first layers convolutional layer
Plus pond (pooling) layer, the activation primitive of neuron is using ReLU functions.
Ground floor is convolutional layer, and the convolution kernel using 5 × 5 carries out convolution to input picture, and step-length is 1, generates 20 width volume
Product characteristic pattern, characteristic pattern size is 80 × 80, and each characteristic pattern carries out dimensionality reduction through a down-sampling, and the core window of down-sampling is big
Little is 2 × 2, and characteristic pattern size is changed into 40 × 40, obtains the characteristic pattern after dimensionality reduction through down-sampling and is input to the second layer;
The second layer is convolutional layer, and for carrying out convolution to the characteristic pattern that obtains on upper strata, the convolution kernel window of the convolutional layer is big
Little is 5 × 5, export 50 characteristic patterns, characteristic pattern size be 36 × 36, each characteristic pattern through a down-sampling, down-sampling
Core window size is 2 × 2, and characteristic pattern size is changed into 18 × 18, obtains the characteristic pattern after dimensionality reduction through down-sampling and is input to the 3rd
Layer;
Third layer is convolutional layer, and for carrying out convolution to the characteristic pattern that obtains on upper strata, the convolution kernel window of the convolutional layer is big
Little is 3 × 3, exports 30 characteristic patterns, and characteristic pattern size is 15 × 15, is input to the 4th layer;
4th layer is full articulamentum, and the layer has 300 neurons, and as the convolution number of plies is higher, the feature for obtaining is more global
Change, in order to take into account the global and local feature of image, by the 2nd pooling layer and the 3rd convolutional layer all with full articulamentum phase
Even, nonlinear transformation obtains 300 dimensional vectors and is input to layer 5;
Layer 5 is softmax layers, and the layer has N number of output node, the classification number that N is recognized.
Also, it should be noted before the recognition methodss of the traffic driving behavior are carried out, needing first to be instructed as follows
Practice:
(1) car plate detector training;Need to prepare car plate positive sample and negative sample, training is based on Ha Er (Haar) feature
Self adaptation car plate detector Adaboost.For example:If the training sample of the car plate detector is:20000 positive samples and
50000 negative samples;Car plate positive sample includes different illumination conditions, the license plate grey level image sample of different angles, negative sample bag
Include the non-license plate area gray level image sample such as road surface, vehicle body, windshield, exhaust screen.Positive and negative sample standard deviation is normalized to unite
One pixel size, trains car plate detector.During detection according to picture tone, saturation, brightness (Hue, Saturation,
Value, abbreviation HSV) component and local zero-crossing rate screened to the region that car plate in image is likely to occur, so as to filter out
The most of non-license plate area of picture, does gray processing process, completes the Adaboost car plates based on Haar features to candidate region
Detector is trained.
During the recognition methodss for realizing the traffic driving behavior, can adopt above-mentioned based on Haar features
Adaboost car plates detector carries out sliding window detection, obtains the license plate area of the target vehicle in the testing image.
(2) face, the training of sunshading board detector;The face, sunshading board detector are still adopted based on Haar features
Self adaptation (Adaboost) Algorithm for Training is obtained.
It should be noted that described according to car plate position size information determine face, sunshading board detection zone and
Range scale, and face is carried out in the detection zone and sunshading board is detected and exports testing result.The detection zone relative to
More than 50% can be reduced for view picture figure, greatly improve treatment effeciency.
(3) classifier training;
Coloured image is converted into gray level image, and is contracted based on step (1) (2) by the acquisition of the classifier training sample
84 × 84 sizes are put into, are the robustness for strengthening model, original training set is carried out rotating, translates, scales, add initial data
Concentrate, constitute new training set.
, by positioning the car plate of target vehicle in testing image, further locating human face is confirming for technical scheme
The image of human pilot, on the premise of driver is not disturbed, drives row for round-the-clock or section in limited time automatic detection traffic
For effectively whether identification driver has unlawful practice during driving, and effectively can avoid making because of driver's violation operation
Into vehicle accident.
As shown in figure 3, for a kind of identifying device of traffic driving behavior provided in an embodiment of the present invention;The device includes:
Image acquisition unit 301, for obtaining testing image;
Position determination unit 302, for, from the testing image, obtaining the position of driver information of target vehicle;
Recognition unit 303, for according to the position of driver information, recognizing the driving row of the target vehicle driver
For.
Wherein, the position determination unit, specifically includes:
Car plate detection sub-unit, for, from the testing image, obtaining the car plate positional information of the target vehicle;
Face datection subelement, for the car plate positional information according to the target vehicle, determines the target vehicle figure
With the presence or absence of driver's face and its position as in;
Position determination subelement, for the car plate positional information according to the target vehicle, determines the target vehicle figure
With the presence or absence of driver's face and its position as in;If there is driver's face in the testing image, according to the mesh
Driver's face location in mark vehicle, obtains the position of driver information of the target vehicle;
Sunshading board detection sub-unit, if for there is no driver's face in the testing image, carry out sunshading board
Detection, determines current for opening sunshade board status.
It should be noted that the car plate detection sub-unit, specifically for detecting by sliding window, determines the target
The license plate area of vehicle;According to the license plate area of the target vehicle, the car plate positional information of the target vehicle is obtained;Described
Car plate positional information includes:The coordinate of car plate position and size.
The Face datection subelement, specifically for the car plate positional information according to the target vehicle, determines the mesh
Driver's human face region in mark vehicle;In the target vehicle in driver's human face region, Face datection is carried out, judged described
With the presence or absence of driver's face and its position in testing image.
The recognition unit, specifically for according to position of driver information in the target vehicle, obtaining the target carriage
Middle driver's image;By driver's image in the target vehicle, the driving behavior of the target vehicle driver is recognized.
As shown in figure 4, being a kind of video acquisition device provided in an embodiment of the present invention;The video acquisition device includes:Such as
The identifying device of the upper traffic driving behavior.
, by positioning the car plate of target vehicle in testing image, further locating human face is confirming for technical scheme
The image of human pilot, on the premise of driver is not disturbed, drives row for round-the-clock or section in limited time automatic detection traffic
For effectively whether identification driver has unlawful practice during driving, and effectively can avoid making because of driver's violation operation
Into vehicle accident, while sunshade board status can be recognized, feed back the dubiety of vehicle in time.
Presently preferred embodiments of the present invention is the foregoing is only, protection scope of the present invention is not intended to limit.All
Any modification, equivalent substitution and improvements that is made within the spirit and principles in the present invention etc., are all contained in protection scope of the present invention
Interior.
Claims (11)
1. a kind of recognition methodss of traffic driving behavior, it is characterised in that include:
Obtain testing image;
From the testing image, the position of driver information of target vehicle is obtained;
According to the position of driver information, the driving behavior of the target vehicle driver is recognized.
2. method according to claim 1, it is characterised in that described from the testing image, obtains target vehicle
The step of position of driver information, specifically include:
From the testing image, the car plate positional information of the target vehicle is obtained;
According to the car plate positional information of the target vehicle, determine in the target vehicle image with the presence or absence of driver's face and
Its position;
If there is driver's face in the testing image, according to driver's face location in the target vehicle, obtain
The position of driver information of the target vehicle;
If there is no driver's face in the testing image, sunshading board detection is carried out, determined current for opening sunshading board
State.
3. method according to claim 2, it is characterised in that described from the testing image, obtains the target carriage
Car plate positional information step, specifically include:
Detected by sliding window, determine the car plate positional information of the target vehicle;The car plate positional information includes:Car plate
The coordinate of position and size.
4. method according to claim 3, it is characterised in that the car plate positional information according to the target vehicle,
Determine in the target vehicle image with the presence or absence of driver's face and its position step, specifically include:
According to the car plate positional information of the target vehicle, driver's human face region in the target vehicle is determined;
In the target vehicle in driver's human face region, Face datection is carried out, judge to whether there is in the testing image
Driver's face and its position.
5. method according to claim 4, it is characterised in that described according to the position of driver information, identification is described
The driving behavior step of target vehicle driver, specifically includes:
According to position of driver information in the target vehicle, driver's image in the target vehicle is obtained;
By driver's image in the target vehicle, the driving behavior of the target vehicle driver is recognized.
6. a kind of identifying device of traffic driving behavior, it is characterised in that include:
Image acquisition unit, for obtaining testing image;
Position determination unit, for, from the testing image, obtaining the position of driver information of target vehicle;
Recognition unit, for according to the position of driver information, recognizing the driving behavior of the target vehicle driver.
7. device according to claim 6, it is characterised in that the position determination unit, specifically includes:
Car plate detection sub-unit, for, from the testing image, obtaining the car plate position size information of the target vehicle;
Face datection subelement, for the car plate positional information according to the target vehicle, determines in the target vehicle image
With the presence or absence of driver's face and its position;
Position determination subelement, for the car plate positional information according to the target vehicle, determines in the target vehicle image
With the presence or absence of driver's face and its position;If there is driver's face in the testing image, according to the target carriage
Middle driver's face location, obtains the position of driver information of the target vehicle;
Sunshading board detection sub-unit, if for there is no driver's face in the testing image, carrying out sunshading board detection,
Determine current for opening sunshade board status.
8. device according to claim 7, it is characterised in that the car plate detection sub-unit, specifically, specifically for passing through
Sliding window detection, determines the car plate positional information of the target vehicle;The car plate positional information includes:The seat of car plate position
Mark and size.
9. device according to claim 8, it is characterised in that the Face datection subelement, specifically for according to described
The car plate positional information of target vehicle, determines driver's human face region in the target vehicle;Drive in the target vehicle
In member's human face region, Face datection is carried out, judged in the testing image with the presence or absence of driver's face and its position.
10. device according to claim 9, it is characterised in that the recognition unit, specifically for according to the target carriage
Middle position of driver information, obtains driver's image in the target vehicle;By driver's image in the target vehicle,
Recognize the driving behavior of the target vehicle driver.
11. a kind of video acquisition devices, it is characterised in that include:As described in any one in claim 6-10, traffic drives
The identifying device of behavior.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610959443.2A CN106503673A (en) | 2016-11-03 | 2016-11-03 | A kind of recognition methodss of traffic driving behavior, device and a kind of video acquisition device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610959443.2A CN106503673A (en) | 2016-11-03 | 2016-11-03 | A kind of recognition methodss of traffic driving behavior, device and a kind of video acquisition device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106503673A true CN106503673A (en) | 2017-03-15 |
Family
ID=58321506
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610959443.2A Pending CN106503673A (en) | 2016-11-03 | 2016-11-03 | A kind of recognition methodss of traffic driving behavior, device and a kind of video acquisition device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106503673A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107341447A (en) * | 2017-06-13 | 2017-11-10 | 华南理工大学 | A kind of face verification mechanism based on depth convolutional neural networks and evidence k nearest neighbor |
CN107862276A (en) * | 2017-11-01 | 2018-03-30 | 北京旋极信息技术股份有限公司 | A kind of Activity recognition method and terminal |
CN108694408A (en) * | 2017-04-11 | 2018-10-23 | 西安邮电大学 | A kind of driving behavior recognition methods based on depth sparseness filtering convolutional neural networks |
CN108764034A (en) * | 2018-04-18 | 2018-11-06 | 浙江零跑科技有限公司 | A kind of driving behavior method for early warning of diverting attention based on driver's cabin near infrared camera |
CN109214438A (en) * | 2018-08-22 | 2019-01-15 | 重庆信络威科技有限公司 | A kind of building method of the driving behavior identifying system based on convolutional neural networks |
CN109583268A (en) * | 2017-09-28 | 2019-04-05 | 杭州海康威视数字技术股份有限公司 | A kind of attribute recognition approach of target, device and electronic equipment |
CN110399766A (en) * | 2019-01-28 | 2019-11-01 | 浙江浩腾电子科技股份有限公司 | Smoking testing and analysis system based on deep learning |
CN112132040A (en) * | 2020-09-24 | 2020-12-25 | 明见(厦门)软件开发有限公司 | Vision-based safety belt real-time monitoring method, terminal equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102982316A (en) * | 2012-11-05 | 2013-03-20 | 安维思电子科技(广州)有限公司 | Driver abnormal driving behavior recognition device and method thereof |
US20130073114A1 (en) * | 2011-09-16 | 2013-03-21 | Drivecam, Inc. | Driver identification based on face data |
CN103268468A (en) * | 2012-07-06 | 2013-08-28 | 华南理工大学 | Automatic detection method for fastening of safety belts by front sitting persons on motor vehicle |
CN104376561A (en) * | 2014-11-19 | 2015-02-25 | 青岛海信网络科技股份有限公司 | Safety belt detection method |
CN105488453A (en) * | 2015-11-30 | 2016-04-13 | 杭州全实鹰科技有限公司 | Detection identification method of no-seat-belt-fastening behavior of driver based on image processing |
CN105946867A (en) * | 2016-05-06 | 2016-09-21 | 深圳市元征科技股份有限公司 | Vehicle alarming method and 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 |
-
2016
- 2016-11-03 CN CN201610959443.2A patent/CN106503673A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130073114A1 (en) * | 2011-09-16 | 2013-03-21 | Drivecam, Inc. | Driver identification based on face data |
CN103268468A (en) * | 2012-07-06 | 2013-08-28 | 华南理工大学 | Automatic detection method for fastening of safety belts by front sitting persons on motor vehicle |
CN102982316A (en) * | 2012-11-05 | 2013-03-20 | 安维思电子科技(广州)有限公司 | Driver abnormal driving behavior recognition device and method thereof |
CN104376561A (en) * | 2014-11-19 | 2015-02-25 | 青岛海信网络科技股份有限公司 | Safety belt detection method |
CN105488453A (en) * | 2015-11-30 | 2016-04-13 | 杭州全实鹰科技有限公司 | Detection identification method of no-seat-belt-fastening behavior of driver based on image processing |
CN105946867A (en) * | 2016-05-06 | 2016-09-21 | 深圳市元征科技股份有限公司 | Vehicle alarming method and 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 |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108694408A (en) * | 2017-04-11 | 2018-10-23 | 西安邮电大学 | A kind of driving behavior recognition methods based on depth sparseness filtering convolutional neural networks |
CN107341447A (en) * | 2017-06-13 | 2017-11-10 | 华南理工大学 | A kind of face verification mechanism based on depth convolutional neural networks and evidence k nearest neighbor |
CN109583268A (en) * | 2017-09-28 | 2019-04-05 | 杭州海康威视数字技术股份有限公司 | A kind of attribute recognition approach of target, device and electronic equipment |
CN107862276A (en) * | 2017-11-01 | 2018-03-30 | 北京旋极信息技术股份有限公司 | A kind of Activity recognition method and terminal |
CN107862276B (en) * | 2017-11-01 | 2021-05-18 | 北京旋极信息技术股份有限公司 | Behavior identification method and terminal |
CN108764034A (en) * | 2018-04-18 | 2018-11-06 | 浙江零跑科技有限公司 | A kind of driving behavior method for early warning of diverting attention based on driver's cabin near infrared camera |
CN109214438A (en) * | 2018-08-22 | 2019-01-15 | 重庆信络威科技有限公司 | A kind of building method of the driving behavior identifying system based on convolutional neural networks |
CN110399766A (en) * | 2019-01-28 | 2019-11-01 | 浙江浩腾电子科技股份有限公司 | Smoking testing and analysis system based on deep learning |
CN112132040A (en) * | 2020-09-24 | 2020-12-25 | 明见(厦门)软件开发有限公司 | Vision-based safety belt real-time monitoring method, terminal equipment and storage medium |
CN112132040B (en) * | 2020-09-24 | 2024-03-15 | 明见(厦门)软件开发有限公司 | Vision-based safety belt real-time monitoring method, terminal equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106503673A (en) | A kind of recognition methodss of traffic driving behavior, device and a kind of video acquisition device | |
CN107133974B (en) | Gaussian Background models the vehicle type classification method combined with Recognition with Recurrent Neural Network | |
CN102289660B (en) | Method for detecting illegal driving behavior based on hand gesture tracking | |
CN109635656A (en) | Vehicle attribute recognition methods, device, equipment and medium neural network based | |
JP7259078B2 (en) | CHILD STATE DETECTION METHOD AND DEVICE, ELECTRONIC DEVICE, STORAGE MEDIUM | |
CN101587544B (en) | Based on the carried on vehicle antitracking device of computer vision | |
CN105286802B (en) | Driver Fatigue Detection based on video information | |
CN108537197A (en) | A kind of lane detection prior-warning device and method for early warning based on deep learning | |
CN108446645B (en) | Vehicle-mounted face recognition method based on deep learning | |
CN106845487A (en) | A kind of licence plate recognition method end to end | |
WO2015025704A1 (en) | Video processing device, video processing method, and video processing program | |
CN109460699A (en) | A kind of pilot harness's wearing recognition methods based on deep learning | |
KR101845769B1 (en) | Car rear detection system using convolution neural network, and method thereof | |
CN106687037A (en) | Device, method, and computer program for detecting momentary sleep | |
CN110226170A (en) | A kind of traffic sign recognition method in rain and snow weather | |
CN108647708A (en) | Driver evaluation's method, apparatus, equipment and storage medium | |
CN105868690A (en) | Method and apparatus for identifying mobile phone use behavior of driver | |
CN110503831A (en) | A kind of method and apparatus identifying driver's illegal activities | |
CN109840523A (en) | A kind of municipal rail train Train number recognition algorithm based on image procossing | |
CN111553214B (en) | Method and system for detecting smoking behavior of driver | |
CN106503710A (en) | A kind of automobile logo identification method and device | |
CN106570444A (en) | On-board smart prompting method and system based on behavior identification | |
CN108205649A (en) | Driver drives to take the state identification method and device of phone | |
CN110245544A (en) | A kind of method and device of determining dead ship condition | |
CN109325408A (en) | A kind of gesture judging method and storage medium |
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 | ||
CB02 | Change of applicant information |
Address after: 8 floors of Block E, No.2 Building, 9 Yuan, Fenghao East Road, Haidian District, Beijing 100094 Applicant after: Wen'an Beijing intelligent technology Limited by Share Ltd Address before: 100085 4th Floor, No. 1 Courtyard, Shangdi East Road, Haidian District, Beijing Applicant before: Wen'an Beijing intelligent technology Limited by Share Ltd |
|
CB02 | Change of applicant information | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170315 |
|
RJ01 | Rejection of invention patent application after publication |