CN107301384A - A kind of driver takes phone behavioral value method and system - Google Patents
A kind of driver takes phone behavioral value method and system Download PDFInfo
- Publication number
- CN107301384A CN107301384A CN201710430623.6A CN201710430623A CN107301384A CN 107301384 A CN107301384 A CN 107301384A CN 201710430623 A CN201710430623 A CN 201710430623A CN 107301384 A CN107301384 A CN 107301384A
- Authority
- CN
- China
- Prior art keywords
- driver
- image
- binaryzation
- present frame
- phone
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
Abstract
Phone behavioral value method and system are taken the invention discloses a kind of driver, wherein method is:Collection driver's image, binaryzation is carried out to present frame driver image in real time, while carrying out Face datection to present frame driver image and going out to take phone detection zone according to face range computation by default mapping relations;Determine present frame driver's image after binaryzation takes phone detection zone for first area, it is the first ratio to count specific pixel point ratio in first area, the first ratio for obtaining continuous driver's image is in the continuous frame number of preset range, judge whether continuous frame number is more than first threshold, if greater than first threshold, then it is assumed that driver has the behavior for taking phone.Beneficial effect:Binaryzation is carried out to driver's image by different methods under natural light and infrared light filling scene, the binaryzation degree of accuracy is higher;The step of detection driver takes phone is simple, and amount of calculation is small, and speed is fast, and Detection accuracy is high.
Description
Technical field
The present invention relates to Computer Image Processing field, phone behavioral value method is taken more particularly, to a kind of driver
And system.
Background technology
It is a kind of behavior violated the traffic regulations that driver takes phone in driving procedure.Taking phone can not only make to drive
The singlehanded even both hands off-direction disk of the person of sailing, can also disperse the notice of driver, influence judgement of the driver to running environment,
Reaction speed is reduced, easily triggers traffic accident.
In existing patent and document, the detection method of phone behavior is taken to driver mainly two major classes:It is based on
Sensor detecting method and based on Computer Vision Detection method.Wherein the detection method based on computer vision has based on SVM
Driver take phone-monitoring method, the driver based on skin color range takes phone behavioral value method, based on Kinect
Driver take phone-monitoring method, the driver based on accumulation difference image takes phone behavior monitoring method etc..
Existing detection method calculates complex, and computationally intensive, speed is slower, and rarely has and be related to night or illumination
Detection method when intensity is very low.
The content of the invention
It is an object of the invention to overcome above-mentioned technical deficiency, propose a kind of driver take phone behavioral value method and
System, solves above-mentioned technical problem of the prior art.
To reach above-mentioned technical purpose, technical scheme provides a kind of driver and takes phone behavioral value side
Method, including:
S1, using the camera with infrared light filling function driver's image is gathered in real time, then to present frame driver
Image carries out binaryzation, and while binaryzation is carried out to present frame driver image, pedestrian is entered to present frame driver's image
Face detection obtains face scope, and goes out connecing for present frame driver's image according to face range computation by default mapping relations
Make a phone call detection zone;
S2, phone detection zone taken according to the present frame driver image after binaryzation and present frame driver's image
Determine present frame driver's image after binaryzation takes phone detection zone for first area, specific in statistics first area
The ratio of pixel is the first ratio, and the first ratio for obtaining continuous driver's image is in the successive frame of preset range
Number;
S3, judge S2 obtain continuous frame number whether be more than first threshold, if greater than first threshold, then it is assumed that driver
There is the behavior for taking phone, give a warning prompting driver.
The present invention also provides a kind of driver and takes phone behavioral value system, including:
Binaryzation and face detection module:Driver's image is gathered in real time using the camera with infrared light filling function,
Then binaryzation is carried out to present frame driver image, while binaryzation is carried out to present frame driver image, to current
Frame driver image carries out Face datection and obtains face scope, and goes out to work as according to face range computation by default mapping relations
Previous frame driver's image takes phone detection zone;
Multiframe statistical module:Electricity is taken according to the present frame driver image after binaryzation and present frame driver's image
Words detection zone determines that the phone detection zone that takes of present frame driver's image after binaryzation is first area, statistics first
The ratio of specific pixel point is the first ratio in region, and the first ratio for obtaining continuous driver's image is in preset range
Continuous frame number;
Judge module:Judge whether the continuous frame number that is obtained in multiframe statistical module is more than first threshold, if greater than the
One threshold value, then it is assumed that driver has the behavior for taking phone, give a warning prompting driver.
Compared with prior art, beneficial effects of the present invention include:Under natural light scene, driven using complexion model
The person's of sailing image binaryzation, is adapted to light change, improves the accuracy of colour of skin binaryzation;Pass through under infrared light filling scene
The method of Y channel luminance threshold values is set to carry out binaryzation to driver's image, the characteristics of using infrared light filling, it is to avoid background
Interference;The step of detection driver takes phone is simple, and amount of calculation is small, and speed is fast, and Detection accuracy is high.
Brief description of the drawings
Fig. 1 is that a kind of driver that the present invention is provided takes phone behavioral value method flow diagram;
Fig. 2 is that a kind of driver that the present invention is provided takes phone behavioral value system architecture diagram;
Fig. 3 is the face scope of driver's image and takes phone detection zone schematic diagram.
In accompanying drawing:1st, driver takes phone behavioral value system, 11, binaryzation and face detection module, and 12, multiframe system
Count module, 13, judge module.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Phone behavioral value method is taken the invention provides a kind of driver, including:
S1, using the camera with infrared light filling function driver's image is gathered in real time, then to present frame driver
Image carries out binaryzation, and while binaryzation is carried out to present frame driver image, pedestrian is entered to present frame driver's image
Face detection obtains face scope, and goes out connecing for present frame driver's image according to face range computation by default mapping relations
Make a phone call detection zone;
S2, phone detection zone taken according to the present frame driver image after binaryzation and present frame driver's image
Determine present frame driver's image after binaryzation takes phone detection zone for first area, specific in statistics first area
The ratio of pixel is the first ratio, and the first ratio for obtaining continuous driver's image is in the successive frame of preset range
Number;
S3, judge S2 obtain continuous frame number whether be more than first threshold, if greater than first threshold, then it is assumed that driver
There is the behavior for taking phone, give a warning prompting driver.
Driver of the present invention is taken in phone behavioral value method, step S1:
When driver's cabin intensity of illumination is less than default intensity of illumination, starts the infrared light filling function of camera, work as driver's cabin
When intensity of illumination is higher than default intensity of illumination, the infrared light filling function of camera is not started, camera has infrared light filling function
And the image under infrared image and natural light scene can be sensed, in the infrared light filling function of not actuated camera, collection is driven
Image under the natural light scene for the person of sailing, when starting the infrared light filling function of camera, gathers the infrared light filling scene of driver
Under image.
Driver of the present invention is taken in phone behavioral value method, step S1:
As shown in figure 3, the face scope for carrying out Face datection acquisition to driver's image is the rectangle frame for including face,
The rectangle frame is named as the first rectangle frame;Go out present frame driver according to face range computation by default mapping relations to scheme
Picture takes phone detection zone, is specially:It is two adjacent with the first rectangle frame symmetrical squares to take phone detection zone
Two rectangle frames for taking phone detection zone are named as the second rectangle frame, two the second rectangle frames are respectively first by shape frame
The both sides of rectangle frame, the base of two the second rectangle frames and the first rectangle frame point-blank, the one of two the second rectangle frames
Side is on the side of the first rectangle frame, the n% of a width of first rectangle width of frame of the second rectangle frame, the second rectangle frame it is a height of
The m% of first rectangle frame height, n%, m% can adjust according to actual conditions, by test of many times, and n% is that 1/2, m% is
When 2/3, it can make to take phone accuracy in detection higher.
Driver of the present invention takes in phone behavioral value method, step S1 and present frame driver image is carried out
The step of binarization operation is:
Driver's image of RGB forms is gathered in real time using the camera with infrared light filling function, first by RGB forms
Driver's image be converted to YCrCb forms, judge collection present frame driver's image when camera whether open infrared light filling
Function, if being not turned on infrared light filling function, binaryzation is carried out using complexion model to present frame driver image, if
Infrared light filling function is opened, then by setting the method for Y channel luminance threshold values to carry out binaryzation to present frame driver image;
Use complexion model to present frame driver image carry out binaryzation method for:
For driver's image of YCrCb forms, using colour of skin empirical value, if wherein certain pixel meets 133≤Cr
≤ 173,77≤Cb≤127, then the point is considered as colour of skin point, are just otherwise non-colour of skin point, by the gray scale of all colour of skin points
Value is set to 255, and the gray value of all non-colour of skin points is set to 0, so as to realize the binaryzation of driver's image;
It is by the method for setting Y channel luminances threshold value to carry out binaryzation to present frame driver image:
For driver's image of YCrCb forms, the Y channel values (i.e. brightness value) of some pixel are taken, if the pixel
The brightness value of point is more than T threshold, then it is assumed that the point is foreground point, is just otherwise background dot, the gray value of all foreground points is set
255 are set to, the gray value of all background dots is set to 0, so as to realize the binaryzation of driver's image.
Driver of the present invention is taken in phone behavioral value method, step S3:
Judge that the continuous frame number that S2 is obtained is less than or equal to first threshold, then do not give a warning.
Driver of the present invention is taken in phone behavioral value method, step S2:
First ratio is the ratio of the pixel that gray value is 255 in first area, that is, is using complexion model to current
When frame driver image carries out binaryzation, the ratio of the skin pixel point in statistics first area is the first ratio, in driver
When taking phone, hand occurs in first area, now, hand is skin pixel point, and remainder pixel is the non-colour of skin
Pixel;When carrying out binaryzation to present frame driver image using Y channel luminances threshold value, the prospect in statistics first area
Point pixel ratio is the first ratio, and hand and mobile phone occur when driver takes phone, in first area, now, hand
Portion and mobile phone are foreground point;
When the first ratio of the first area pixel of frame driver's image is in preset range, it is believed that this frame is driven
The similar action for taking phone is occurred in that in the person's of sailing image, it is preferred that preset range is 15%-90%;
When continuous multiple frames driver image occur it is similar take the action of phone and continuous frame number reaches first threshold, then
It is strictly to take phone to think driver, and give a warning prompting driver, it is preferred that first threshold is 100 frames.
The present invention also provides a kind of driver and takes phone behavioral value system 1, including:
Binaryzation and face detection module 11:Driver's figure is gathered in real time using the camera with infrared light filling function
Picture, then carries out binaryzation to present frame driver image, while binaryzation is carried out to present frame driver image, to working as
Previous frame driver image carries out Face datection and obtains face scope, and is gone out by default mapping relations according to face range computation
Present frame driver's image takes phone detection zone;
Multiframe statistical module 12:According to taking for the present frame driver image after binaryzation and present frame driver's image
What phone detection zone determined present frame driver's image after binaryzation takes phone detection zone for first area, statistics the
The ratio of specific pixel point is the first ratio in one region, and the first ratio for obtaining continuous driver's image is in default model
The continuous frame number enclosed;
Judge module 13:Judge whether the continuous frame number obtained in multiframe statistical module is more than first threshold, if greater than
First threshold, then it is assumed that driver has the behavior for taking phone, give a warning prompting driver.
Driver of the present invention is taken in phone behavioral value system 1, binaryzation and face detection module 11:
When driver's cabin intensity of illumination is less than default intensity of illumination, starts the infrared light filling function of camera, work as driver's cabin
When intensity of illumination is higher than default intensity of illumination, the infrared light filling function of camera is not started.
Driver of the present invention is taken in phone behavioral value system 1, binaryzation and face detection module 11:
Driver's image of RGB forms is gathered in real time using the camera with infrared light filling function, first by RGB forms
Driver's image be converted to YCrCb forms, judge collection present frame driver's image when camera whether open infrared light filling
Function, if being not turned on infrared light filling function, binaryzation is carried out using complexion model to present frame driver image so that
The gray value of skin pixel point is 255, and the gray value of non-skin pixel point is 0;If opening infrared light filling function, pass through
The method of Y channel luminance threshold values is set to carry out binaryzation to present frame driver image:Y channel values are set to be more than the picture of T threshold
Vegetarian refreshments is foreground point, and the pixel for setting Y channel values to be less than or equal to T threshold is background dot, by the gray value of all foreground points
255 are set to, the gray value of all background dots is set to 0.
Driver of the present invention is taken in phone behavioral value system 1, judge module 13:
Judge that the continuous frame number obtained in multiframe statistical module 12 is less than or equal to first threshold, then do not give a warning.
Driver of the present invention is taken in phone behavioral value system 1, multiframe statistical module 12:
First ratio is the ratio of the pixel that gray value is 255 in first area.
Compared with prior art, beneficial effects of the present invention include:Under natural light scene, driven using complexion model
The person's of sailing image binaryzation, is adapted to light change, improves the accuracy of colour of skin binaryzation;Pass through under infrared light filling scene
The method of Y channel luminance threshold values is set to carry out binaryzation to driver's image, the characteristics of using infrared light filling, it is to avoid background
Interference;The step of detection driver takes phone is simple, and amount of calculation is small, and speed is fast, and Detection accuracy is high.
The embodiment of present invention described above, is not intended to limit the scope of the present invention..Any basis
Various other corresponding changes and deformation that the technical concept of the present invention is made, should be included in the guarantor of the claims in the present invention
In the range of shield.
Claims (10)
1. a kind of driver takes phone behavioral value method, it is characterised in that including:
S1, using the camera with infrared light filling function driver's image is gathered in real time, then to present frame driver's image
Binaryzation is carried out, while binaryzation is carried out to present frame driver image, face inspection is carried out to present frame driver image
Survey and obtain face scope, and electricity is taken according to what face range computation went out present frame driver's image by default mapping relations
Talk about detection zone;
S2, determined according to the phone detection zone that takes of the present frame driver image after binaryzation and present frame driver's image
The phone detection zone that takes of present frame driver's image after binaryzation is first area, counts specific in the first area
The ratio of pixel is the first ratio, and first ratio for obtaining continuous driver's image is in the continuous of preset range
Frame number;
S3, judge S2 obtain continuous frame number whether be more than first threshold, if greater than the first threshold, then it is assumed that driver
There is the behavior for taking phone, give a warning prompting driver.
2. driver as claimed in claim 1 takes phone behavioral value method, it is characterised in that in step S1:
When driver's cabin intensity of illumination is less than default intensity of illumination, start the infrared light filling function of camera, when driver's cabin illumination
When intensity is higher than default intensity of illumination, the infrared light filling function of camera is not started.
3. driver as claimed in claim 1 takes phone behavioral value method, it is characterised in that to present frame in step S1
Driver's image carry out binarization operation the step of be:
Gather driver's image of RGB forms, first driving RGB forms in real time using the camera with infrared light filling function
The person's of sailing image is converted to YCrCb forms, judges whether camera opens infrared light filling function during collection present frame driver's image,
If being not turned on infrared light filling function, binaryzation is carried out to present frame driver image using complexion model so that the colour of skin
The gray value of pixel is 255, and the gray value of non-skin pixel point is 0;If opening infrared light filling function, by setting
The method of Y channel luminance threshold values carries out binaryzation to present frame driver image:Y channel values are set to be more than the pixel of T threshold
For foreground point, the pixel for setting Y channel values to be less than or equal to T threshold is background dot, and the gray value of all foreground points is set
For 255, the gray value of all background dots is set to 0.
4. driver as claimed in claim 1 takes phone behavioral value method, it is characterised in that in step S3:
Judge that the continuous frame number that S2 is obtained is less than or equal to first threshold, then do not give a warning.
5. driver as claimed in claim 3 takes phone behavioral value method, it is characterised in that in step S2:
First ratio is the ratio of the pixel that gray value is 255 in the first area.
6. a kind of driver takes phone behavioral value system, it is characterised in that including:
Binaryzation and face detection module:Driver's image is gathered in real time using the camera with infrared light filling function, then
Binaryzation is carried out to present frame driver image, while binaryzation is carried out to present frame driver image, present frame driven
The person's of sailing image carries out Face datection and obtains face scope, and goes out present frame according to face range computation by default mapping relations
Driver's image takes phone detection zone;
Multiframe statistical module:Examined according to the phone that takes of the present frame driver image after binaryzation and present frame driver's image
Survey region and determine that the phone detection zone that takes of present frame driver's image after binaryzation is first area, count first area
The ratio of interior specific pixel point is first ratio, and first ratio for obtaining continuous driver's image is in presetting
The continuous frame number of scope;
Judge module:Judge whether the continuous frame number obtained in multiframe statistical module is more than the first threshold, if greater than institute
State first threshold, then it is assumed that driver has the behavior for taking phone, give a warning prompting driver.
7. driver as claimed in claim 6 takes phone behavioral value system, it is characterised in that binaryzation and Face datection
In module:
When driver's cabin intensity of illumination is less than default intensity of illumination, start the infrared light filling function of camera, when driver's cabin illumination
When intensity is higher than default intensity of illumination, the infrared light filling function of camera is not started.
8. driver as claimed in claim 6 takes phone behavioral value system, it is characterised in that binaryzation and Face datection
In module:
Gather driver's image of RGB forms, first driving RGB forms in real time using the camera with infrared light filling function
The person's of sailing image is converted to YCrCb forms, judges whether camera opens infrared light filling function during collection present frame driver's image,
If being not turned on infrared light filling function, binaryzation is carried out to present frame driver image using complexion model so that the colour of skin
The gray value of pixel is 255, and the gray value of non-skin pixel point is 0;If opening infrared light filling function, by setting
The method of Y channel luminance threshold values carries out binaryzation to present frame driver image:Y channel values are set to be more than the pixel of T threshold
For foreground point, the pixel for setting Y channel values to be less than or equal to T threshold is background dot, and the gray value of all foreground points is set
For 255, the gray value of all background dots is set to 0.
9. driver as claimed in claim 6 takes phone behavioral value system, it is characterised in that in judge module:
Judge that the continuous frame number obtained in multiframe statistical module is less than or equal to the first threshold, then do not give a warning.
10. driver as claimed in claim 8 takes phone behavioral value system, it is characterised in that in multiframe statistical module:
First ratio is the ratio of the pixel that gray value is 255 in the first area.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710430623.6A CN107301384A (en) | 2017-06-09 | 2017-06-09 | A kind of driver takes phone behavioral value method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710430623.6A CN107301384A (en) | 2017-06-09 | 2017-06-09 | A kind of driver takes phone behavioral value method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107301384A true CN107301384A (en) | 2017-10-27 |
Family
ID=60135742
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710430623.6A Pending CN107301384A (en) | 2017-06-09 | 2017-06-09 | A kind of driver takes phone behavioral value method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107301384A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108710857A (en) * | 2018-05-22 | 2018-10-26 | 深圳前海华夏智信数据科技有限公司 | People's vehicle recognition methods based on infrared light filling and device |
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 |
CN109086729A (en) * | 2018-08-13 | 2018-12-25 | 成都盯盯科技有限公司 | Communication behavior detection method, device, equipment and storage medium |
CN109165607A (en) * | 2018-08-29 | 2019-01-08 | 浙江工业大学 | A kind of hand-held phone detection method of the driver based on deep learning |
CN109409259A (en) * | 2018-10-11 | 2019-03-01 | 百度在线网络技术(北京)有限公司 | Drive monitoring method, device, equipment and computer-readable medium |
CN109684990A (en) * | 2018-12-20 | 2019-04-26 | 天津天地伟业信息系统集成有限公司 | A kind of behavioral value method of making a phone call based on video |
CN110718067A (en) * | 2019-09-23 | 2020-01-21 | 浙江大华技术股份有限公司 | Violation behavior warning method and related device |
CN111062319A (en) * | 2019-12-16 | 2020-04-24 | 武汉极目智能技术有限公司 | Driver call detection method based on active infrared image |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101090482A (en) * | 2006-06-13 | 2007-12-19 | 唐琎 | Driver fatigue monitoring system and method based on image process and information mixing technology |
CN102592143A (en) * | 2012-01-09 | 2012-07-18 | 清华大学 | Method for detecting phone holding violation of driver in driving |
CN103279750A (en) * | 2013-06-14 | 2013-09-04 | 清华大学 | Detecting method of mobile telephone holding behavior of driver based on skin color range |
CN106585629A (en) * | 2016-12-06 | 2017-04-26 | 广州市科恩电脑有限公司 | Automobile control method and device |
CN106709420A (en) * | 2016-11-21 | 2017-05-24 | 厦门瑞为信息技术有限公司 | Method for monitoring driving behaviors of driver of commercial vehicle |
-
2017
- 2017-06-09 CN CN201710430623.6A patent/CN107301384A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101090482A (en) * | 2006-06-13 | 2007-12-19 | 唐琎 | Driver fatigue monitoring system and method based on image process and information mixing technology |
CN102592143A (en) * | 2012-01-09 | 2012-07-18 | 清华大学 | Method for detecting phone holding violation of driver in driving |
CN103279750A (en) * | 2013-06-14 | 2013-09-04 | 清华大学 | Detecting method of mobile telephone holding behavior of driver based on skin color range |
CN106709420A (en) * | 2016-11-21 | 2017-05-24 | 厦门瑞为信息技术有限公司 | Method for monitoring driving behaviors of driver of commercial vehicle |
CN106585629A (en) * | 2016-12-06 | 2017-04-26 | 广州市科恩电脑有限公司 | Automobile control method and device |
Non-Patent Citations (2)
Title |
---|
刘洪榛: "《基于机器视觉的疲劳驾驶检测算法研究》", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
王暕来: "《红外图像预处理技术的研究及 FPGA 实现》", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN108710857A (en) * | 2018-05-22 | 2018-10-26 | 深圳前海华夏智信数据科技有限公司 | People's vehicle recognition methods based on infrared light filling and device |
CN109086729A (en) * | 2018-08-13 | 2018-12-25 | 成都盯盯科技有限公司 | Communication behavior detection method, device, equipment and storage medium |
CN109165607A (en) * | 2018-08-29 | 2019-01-08 | 浙江工业大学 | A kind of hand-held phone detection method of the driver based on deep learning |
CN109165607B (en) * | 2018-08-29 | 2021-12-14 | 浙江工业大学 | Driver handheld phone detection method based on deep learning |
CN109409259A (en) * | 2018-10-11 | 2019-03-01 | 百度在线网络技术(北京)有限公司 | Drive monitoring method, device, equipment and computer-readable medium |
CN109684990A (en) * | 2018-12-20 | 2019-04-26 | 天津天地伟业信息系统集成有限公司 | A kind of behavioral value method of making a phone call based on video |
CN110718067A (en) * | 2019-09-23 | 2020-01-21 | 浙江大华技术股份有限公司 | Violation behavior warning method and related device |
CN111062319A (en) * | 2019-12-16 | 2020-04-24 | 武汉极目智能技术有限公司 | Driver call detection method based on active infrared image |
CN111062319B (en) * | 2019-12-16 | 2023-02-10 | 武汉极目智能技术有限公司 | Driver call detection method based on active infrared image |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107301384A (en) | A kind of driver takes phone behavioral value method and system | |
CN104809445A (en) | Fatigue driving detection method based on eye and mouth states | |
CN101916370B (en) | Method for processing non-feature regional images in face detection | |
CN103488987B (en) | Video-based method and device for detecting traffic lights | |
CN104769652B (en) | Method and system for detecting traffic lights | |
CN106682601B (en) | A kind of driver's violation call detection method based on multidimensional information Fusion Features | |
CN102202163B (en) | Adaptive enhancement method and device for monitored video | |
CN103279750B (en) | Based on driver's cell-phone behavioral value method of skin color range | |
CN104766071B (en) | A kind of traffic lights fast algorithm of detecting applied to pilotless automobile | |
CN102183224B (en) | Method for detecting screen dot of measurement and control strip based on machine vision | |
US20210029290A1 (en) | Imaging device and apparatus | |
CN106067016B (en) | A kind of facial image eyeglass detection method and device | |
CN105374013A (en) | Method and image processing apparatus for image visibility restoration on the base of dual dark channel prior | |
EP3889825A1 (en) | Vehicle lane line detection method, vehicle, and computing device | |
US20130208981A1 (en) | Method and wireless handheld device for determining image hue | |
CN108701214A (en) | Image processing method, device and equipment | |
CN101343012B (en) | Control method and system for escalator | |
KR101246120B1 (en) | A system for recognizing license plate using both images taken from front and back faces of vehicle | |
GB0226787D0 (en) | Measurement of mitotic activity | |
CN105609086A (en) | Brightness adjustment method and device of display interface | |
EP3203308B1 (en) | Display system, eyewear, and method for controlling display system | |
CN101604446B (en) | Lip image segmenting method and system for fatigue detection | |
CN104809482A (en) | Fatigue detecting method based on individual learning | |
CN107480629A (en) | A kind of method for detecting fatigue driving and device based on depth information | |
CN108257189A (en) | A kind of strong light detection method, device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171027 |