CN109034132A - A kind of detection method driving abnormal behaviour - Google Patents
A kind of detection method driving abnormal behaviour Download PDFInfo
- Publication number
- CN109034132A CN109034132A CN201811022082.4A CN201811022082A CN109034132A CN 109034132 A CN109034132 A CN 109034132A CN 201811022082 A CN201811022082 A CN 201811022082A CN 109034132 A CN109034132 A CN 109034132A
- Authority
- CN
- China
- Prior art keywords
- face
- driver
- face datection
- learning model
- heart rate
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Image Processing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention discloses a kind of detection method for driving abnormal behaviour, it is divided into Face datection learning model training stage and face abnormal state detection stage, the face abnormal state detection stage is the detection that driver status is carried out based on Face datection learning model training stage Face datection learning model generated, and the face abnormal state detection stage, specific step is as follows: a, human face data Image Acquisition；B, Face datection and facial modeling；C, chrominance C r and Cb are extracted from color space YCbCr carries out series of values variation to calculate heart rate；D, heart rate will be calculated and is sent into the Face datection learning model, and export driver status；E, it when driver is when in an abnormal state, sounds an alarm.The present invention is to acquire driver's facial image using camera, then selects interested human face region, according to the mutation analysis driver of RGB color with the presence or absence of fatigue, to analyze the possibility whether driver has heart attack.
Description
Technical field
The present invention relates to intelligent transportation fields, and in particular to a kind of detection method for driving abnormal behaviour.
Background technique
Current traffic accidents take place frequently, and reason has fatigue driving, drink-driving, burst disease etc..According to the investigation of WHO in recent years
Report shows that death caused by cardiovascular disease ranks the first.More than any other disease.Heart rate is assessment cardiovascular disease
One important parameter.And can heart rate speed to determine whether awake.Generally under sleep quality, heart rate becomes slow.
Therefore it can detect whether the person of sailing dozes off, sleeps and have a heart attack when driving with heart rate.Compared to other detection methods, nothing
Non-contact method for measuring heart rate is created, it is simple and quick accurate, it is chainless to driver.
There are three types of methods for traditional driving fatigue detection:
1, judged according to travelling data
2, judged according to physiological signal
3, judged using driver's facial image video of acquisition
Three kinds of methods above, respectively there is advantage and disadvantage.The advantages of present invention incorporates second the third methods, using the people of acquisition
Face image determines the heart rate of driver the characteristics of different moments, RGB color value was fluctuated with heart.And traditional RGB color is empty
Between be easier influence by factors such as illumination, the present invention selects impacted less YCbCr color space to analyze heart rate.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide it is a kind of drive abnormal behaviour detection method,
Driver's facial image is acquired using camera, interested human face region is then selected, is driven according to the mutation analysis of RGB color
Whether the person of sailing has the possibility of heart attack with the presence or absence of fatigue, analysis driver.
Technical scheme is as follows:
A kind of detection method driving abnormal behaviour, is divided into Face datection learning model training stage and face exception shape
State detection-phase, the face abnormal state detection stage are generated based on the Face datection learning model training stage
Face datection learning model carries out the detection of driver status, and the face abnormal state detection stage, specific step is as follows:
A, human face data Image Acquisition；
B, Face datection and facial modeling；
C, chrominance C r and Cb are extracted from color space YCbCr carries out series of values variation to calculate heart rate；
D, heart rate will be calculated and is sent into the Face datection learning model, and export driver status；
E, it when driver is when in an abnormal state, sounds an alarm.
Further, in the step d in the face abnormal state detection stage, the driver status include doze off,
Awake and ventricular fibrillation state, described doze off with ventricular fibrillation state is then abnormality.
Further, the Face datection learning model training stage, specific step is as follows:
A, human face data Image Acquisition；
B, Face datection and facial modeling；
C, chrominance C r and Cb are extracted from color space YCbCr carries out series of values variation to calculate heart rate；
D, according to the heart rate value of driver, the training of Face datection learning model is carried out to driver status；
E, Face datection learning model is generated.
Further, in step a described above, the human face data image of the driver the taking the photograph in the car by installation
As head is acquired.
Further, in step b described above, Face datection, application are carried out using Viola-jones algorithm
Supervised descent method algorithm carries out facial modeling.
Further, in step b described above and step c, by the way that the characteristic point of positioning is converted to from rgb space
The space YCrCb, to extract the YCbCr color value of characteristic point.
Further, following steps have been specifically included in step c described above:
C1, chrominance C r and Cb progress serial analysis are extracted；
C2, the series of extraction is filtered；
C3, the signal that fixed window size is chosen from filtered waveform, carry out spectrum analysis, calculate basic frequency point,
This basic frequency point is the heart rate of driver.
Compared with the existing technology, the beneficial effects of the present invention are: the present invention is based on hearts rate abnormal to have to analyze to drive
Objectivity compares other methods, and the present invention can not only detect common abnormal driving behavior such as fatigue driving, can also be according to heart rate
To analyze whether the cardiac function of driver has exception.
Detailed description of the invention
Fig. 1 is overall flow figure of the invention；
Fig. 2 is the specific steps flow chart in face abnormal state detection stage of the present invention.
Specific embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.
Fig. 1, Fig. 2 are please referred to, the present invention provides a kind of detection method for driving abnormal behaviour, is divided into Face datection study
Model training stage and face abnormal state detection stage, the face abnormal state detection stage are based on the Face datection
The learning model training stage, Face datection learning model generated carried out the detection of driver status, the face abnormality
Specific step is as follows for detection-phase:
A, interested human face region may be selected in human face data Image Acquisition；
It is acquired by the camera of installation in the car.
B, Face datection and facial modeling；
Specifically, Face datection is carried out using Viola-jones (abbreviation VJ) algorithm, using Supervised descent
Method (SDM) algorithm carries out facial modeling.
By the way that the characteristic point of positioning is converted to the space YCrCb from rgb space, to extract the YCbCr color value of characteristic point.
C, chrominance C r and Cb are extracted from color space YCbCr carries out series of values variation to calculate heart rate；
Specifically include following steps:
C1, chrominance C r and Cb progress serial analysis are extracted；
C2, the series of extraction is filtered；
C3, the signal that fixed window size is chosen from filtered waveform, carry out spectrum analysis, calculate basic frequency point,
This basic frequency point is the heart rate of driver.
D, heart rate will be calculated and is sent into the Face datection learning model, and export driver status；
Driver status includes dozing off, regaining consciousness and ventricular fibrillation state
E, it when driver is when in an abnormal state, sounds an alarm.
Described doze off with ventricular fibrillation state is then abnormality.
The Face datection learning model training stage, specific step is as follows:
A, human face data Image Acquisition；
B, Face datection and facial modeling；
C, chrominance C r and Cb are extracted from color space YCbCr carries out series of values variation to calculate heart rate；
D, according to the heart rate value of driver, the training of Face datection learning model is carried out to driver status；
E, Face datection learning model is generated.
Exception is driven with objectivity to analyze in conclusion the present invention is based on hearts rate, compares other methods, the present invention is not
It is only capable of detecting common abnormal driving behavior such as fatigue driving, whether the cardiac function that can also analyze driver according to heart rate has
It is abnormal.
The above is merely preferred embodiments of the present invention, be not intended to restrict the invention, it is all in spirit of the invention and
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within principle.
Claims (7)
1. it is a kind of drive abnormal behaviour detection method, which is characterized in that its be divided into the Face datection learning model training stage and
Face abnormal state detection stage, the face abnormal state detection stage are based on Face datection learning model training rank
Section Face datection learning model generated carries out the detection of driver status, the face abnormal state detection stage it is specific
Steps are as follows:
A, human face data Image Acquisition；
B, Face datection and facial modeling；
C, chrominance C r and Cb are extracted from color space YCbCr carries out series of values variation to calculate heart rate；
D, heart rate will be calculated and is sent into the Face datection learning model, and export driver status；
E, it when driver is when in an abnormal state, sounds an alarm.
2. a kind of detection method for driving abnormal behaviour according to claim 1, which is characterized in that abnormal in the face
In the step d in state-detection stage, the driver status includes dozing off, regaining consciousness and ventricular fibrillation state, described to doze off and ventricular fibrillation shape
State is then abnormality.
3. a kind of detection method for driving abnormal behaviour according to claim 1, which is characterized in that the Face datection
Practising model training stage, specific step is as follows:
A, human face data Image Acquisition；
B, Face datection and facial modeling；
C, chrominance C r and Cb are extracted from color space YCbCr carries out series of values variation to calculate heart rate；
D, according to the heart rate value of driver, the training of Face datection learning model is carried out to driver status；
E, Face datection learning model is generated.
4. a kind of detection method for driving abnormal behaviour according to claim 1 or 3, which is characterized in that in step a,
The human face data image of the driver is acquired by the camera of installation in the car.
5. a kind of detection method for driving abnormal behaviour according to claim 1 or 3, which is characterized in that in stepb,
Face datection is carried out using Viola-jones algorithm, carries out face characteristic using Supervised descent method algorithm
Point location.
6. a kind of detection method for driving abnormal behaviour according to claim 1 or 3, which is characterized in that in step b and step
In rapid c, by the way that the characteristic point of positioning is converted to the space YCrCb from rgb space, to extract the YCbCr color value of characteristic point.
7. a kind of detection method for driving abnormal behaviour according to claim 1 or 3, which is characterized in that have in step c
Body includes following steps:
C1, chrominance C r and Cb progress serial analysis are extracted；
C2, the series of extraction is filtered；
C3, the signal that fixed window size is chosen from filtered waveform, carry out spectrum analysis, calculate basic frequency point, this master
Frequency point is the heart rate of driver.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811022082.4A CN109034132A (en) | 2018-09-03 | 2018-09-03 | A kind of detection method driving abnormal behaviour |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811022082.4A CN109034132A (en) | 2018-09-03 | 2018-09-03 | A kind of detection method driving abnormal behaviour |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109034132A true CN109034132A (en) | 2018-12-18 |
Family
ID=64622981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811022082.4A Pending CN109034132A (en) | 2018-09-03 | 2018-09-03 | A kind of detection method driving abnormal behaviour |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109034132A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751051A (en) * | 2019-09-23 | 2020-02-04 | 江苏大学 | Abnormal driving behavior detection method based on machine vision |
| CN113879317A (en) * | 2020-07-02 | 2022-01-04 | 丰田自动车株式会社 | Driver monitoring device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120219189A1 (en) * | 2009-10-30 | 2012-08-30 | Shenzhen Safdao Technology Corporation Limited | Method and device for detecting fatigue driving and the automobile using the same |
| CN103714660A (en) * | 2013-12-26 | 2014-04-09 | 苏州清研微视电子科技有限公司 | System for achieving fatigue driving judgment on basis of image processing and fusion between heart rate characteristic and expression characteristic |
| CN103824420A (en) * | 2013-12-26 | 2014-05-28 | 苏州清研微视电子科技有限公司 | Fatigue driving identification system based on heart rate variability non-contact measuring |
| CN106355838A (en) * | 2016-10-28 | 2017-01-25 | 深圳市美通视讯科技有限公司 | Fatigue driving detection method and system |
| CN106548132A (en) * | 2016-10-16 | 2017-03-29 | 北海益生源农贸有限责任公司 | The method for detecting fatigue driving of fusion eye state and heart rate detection |
| CN107506716A (en) * | 2017-08-17 | 2017-12-22 | 华东师范大学 | A kind of contactless real-time method for measuring heart rate based on video image |
| CN108176033A (en) * | 2018-01-31 | 2018-06-19 | 华南农业大学 | A kind of marathon runner's heart rate measurement and system for prompting and method |
-
2018
- 2018-09-03 CN CN201811022082.4A patent/CN109034132A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120219189A1 (en) * | 2009-10-30 | 2012-08-30 | Shenzhen Safdao Technology Corporation Limited | Method and device for detecting fatigue driving and the automobile using the same |
| CN103714660A (en) * | 2013-12-26 | 2014-04-09 | 苏州清研微视电子科技有限公司 | System for achieving fatigue driving judgment on basis of image processing and fusion between heart rate characteristic and expression characteristic |
| CN103824420A (en) * | 2013-12-26 | 2014-05-28 | 苏州清研微视电子科技有限公司 | Fatigue driving identification system based on heart rate variability non-contact measuring |
| CN106548132A (en) * | 2016-10-16 | 2017-03-29 | 北海益生源农贸有限责任公司 | The method for detecting fatigue driving of fusion eye state and heart rate detection |
| CN106355838A (en) * | 2016-10-28 | 2017-01-25 | 深圳市美通视讯科技有限公司 | Fatigue driving detection method and system |
| CN107506716A (en) * | 2017-08-17 | 2017-12-22 | 华东师范大学 | A kind of contactless real-time method for measuring heart rate based on video image |
| CN108176033A (en) * | 2018-01-31 | 2018-06-19 | 华南农业大学 | A kind of marathon runner's heart rate measurement and system for prompting and method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751051A (en) * | 2019-09-23 | 2020-02-04 | 江苏大学 | Abnormal driving behavior detection method based on machine vision |
| CN110751051B (en) * | 2019-09-23 | 2024-03-19 | 江苏大学 | Abnormal driving behavior detection method based on machine vision |
| CN113879317A (en) * | 2020-07-02 | 2022-01-04 | 丰田自动车株式会社 | Driver monitoring device |
| CN113879317B (en) * | 2020-07-02 | 2023-08-22 | 丰田自动车株式会社 | driver monitoring device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104809445B (en) | method for detecting fatigue driving based on eye and mouth state | |
| CN108216254B (en) | Road anger emotion recognition method based on fusion of facial image and pulse information | |
| CN108053615B (en) | Method for detecting fatigue driving state of driver based on micro-expression | |
| CN101090482B (en) | Driver fatigue monitoring system and method based on image process and information mixing technology | |
| CN109389806A (en) | Fatigue driving detection method for early warning, system and medium based on multi-information fusion | |
| KR101078466B1 (en) | Awake state judging model making device, awake state judging device, warning device, vehicle, awake state judging model making method, awake state judging method, computer readable medium recording the awake state judging model making method, and computer readable medium recording the awake state judging method | |
| CN101593425B (en) | Machine vision based fatigue driving monitoring method and system | |
| CN110751051B (en) | Abnormal driving behavior detection method based on machine vision | |
| CN110532976A (en) | Method for detecting fatigue driving and system based on machine learning and multiple features fusion | |
| CN110728241A (en) | Driver fatigue detection method based on deep learning multi-feature fusion | |
| CN107578008B (en) | Fatigue state detection method based on block feature matrix algorithm and SVM | |
| CN109598899A (en) | A kind of system and method for personalization fatigue monitoring and prompting | |
| CN102938058A (en) | Method and system for video driving intelligent perception and facing safe city | |
| CN102263937A (en) | Driver's driving behavior monitoring device and monitoring method based on video detection | |
| CN101604382A (en) | A kind of learning fatigue recognition interference method based on human facial expression recognition | |
| Liu et al. | Driver fatigue detection through pupil detection and yawing analysis | |
| Pimplaskar et al. | Real time eye blinking detection and tracking using opencv | |
| CN101551934B (en) | Device and method for monitoring fatigue driving of driver | |
| CN109034132A (en) | A kind of detection method driving abnormal behaviour | |
| CN109953763A (en) | A kind of vehicle carried driving behavioral value early warning system and method based on deep learning | |
| Tabrizi et al. | Open/closed eye analysis for drowsiness detection | |
| CN106600903A (en) | Image-identification-based early-warning method and apparatus | |
| CN107832721A (en) | Method and apparatus for output information | |
| CN109567832A (en) | A kind of method and system of the angry driving condition of detection based on Intelligent bracelet | |
| CN113887386A (en) | Fatigue detection method based on multi-feature fusion of deep learning and machine learning |
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 |
Application publication date: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |