CN208569650U - A kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously - Google Patents
A kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously Download PDFInfo
- Publication number
- CN208569650U CN208569650U CN201821119495.XU CN201821119495U CN208569650U CN 208569650 U CN208569650 U CN 208569650U CN 201821119495 U CN201821119495 U CN 201821119495U CN 208569650 U CN208569650 U CN 208569650U
- Authority
- CN
- China
- Prior art keywords
- copilot
- module
- driver
- driving behavior
- behavior analysis
- 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.)
- Active
Links
Abstract
The utility model discloses a kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously, comprising: binocular obtuse angle type camera module, setting is driving indoor front, for acquiring driver's facial image and copilot's facial image.Driving behavior analysis module is identified for the face to driver and copilot；Loudspeaker module, for sounding an alarm；GPS module positions in real time for vehicle；4G network communication module, is used for transmission face recognition result；Wherein, the binocular obtuse angle type camera module, comprising: left camera, right camera and obtuse triangle pedestal, the left camera and the right camera are separately mounted on two obtuse angle edges of the obtuse triangle pedestal；The obtuse triangle pedestal is pasted on Auto Instrument desk.
Description
Technical field
The utility model relates to field of face identification more particularly to a kind of support driver to identify simultaneously with copilot identity
Driving behavior analysis instrument.
Background technique
Road traffic accident takes place frequently in recent years, has seriously threatened the security of the lives and property of people and the hair of social economy
Exhibition.Traffic accident has been listed in one of the killer for leading to population in the world death, has become a global problem.Fatigue
It drives because having stronger concealment and subjectivity, is less susceptible to be found, greatly danger will be generated when traffic accident occurs
Evil.Allegro life brings huge pressure to the people of modern society, while quick with China Logistics carrier
Development, phenomenon of driving over a long distance is generally existing so that because caused by driver tired driving traffic accident quantity it is high.
Now with the development of computer vision technique, driving behavior analysis instrument has begun universal be used to driver's
Dangerous driving behavior carries out early warning.In general, driving behavior analysis instrument is mounted in front of driver, and the camera lens visual field only includes to drive
The person of sailing.And in long-distance truck Driving Scene, generally requiring two drivers alternately drives, and reduces fatigue driving accident
Occur.Therefore the identity of driver and copilot are identified, give warning in advance being necessary simultaneously.
Utility model content
The utility model provides a kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously, this
Utility model is equipped on vehicle, especially suitable for long haul vehicle, detects applied to the identity of driver and copilot,
It is described below:
A kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously, the driving behavior analysis instrument
Include:
Binocular obtuse angle type camera module, setting is driving indoor front, for acquiring driver's facial image and pair
Driver's facial image.
Driving behavior analysis module is identified for the face to driver and copilot；
Loudspeaker module, for sounding an alarm；GPS module positions in real time for vehicle；
4G network communication module, is used for transmission face recognition result；
Wherein, the binocular obtuse angle type camera module, comprising: left camera, right camera and obtuse triangle base
Seat,
The left camera and the right camera are separately mounted on two obtuse angle edges of the obtuse triangle pedestal；Institute
Obtuse triangle pedestal is stated to be pasted on Auto Instrument desk.
The obtuse angle of the obtuse triangle pedestal is between 100-120 degree.The material of the obtuse triangle pedestal is modeling
Expect material or metal material.
The driving behavior analysis instrument further include: after being sent to the GPS information of the result of recognition of face and current vehicle
Platform server.
The beneficial effect of technical solution provided by the utility model is:
1, left camera and right camera shooting by camera module integral installation on bridge instrumentation platform, in camera module
Head be separately mounted on two obtuse angle edges of an obtuse triangle pedestal, two-way camera can respectively simultaneously obtain driver and
The image of copilot realizes driver and identification while copilot, is conducive to special messenger's special train and exempts generation to drive.
2, the device improves Face datection speed using Haar (Haar wavelet transform) feature, uses depth characteristic (CNN feature)
So that face recognition result is accurate.
3, the device directly uses the hardware configuration of driving behavior analysis instrument, does not need additional hardware deployment, has warp
It helps convenient feature.
Detailed description of the invention
Fig. 1 is a kind of structural schematic diagram of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously；
Fig. 2 is the structural schematic diagram of binocular obtuse angle type camera module.
In attached drawing, parts list represented by the reference numerals are as follows:
1: binocular obtuse angle type camera module；2: driving behavior analysis module；
3: loudspeaker module；4:GPS module；
5:4G network communication module；
11: left camera；12: right camera；
13: pedestal.
Specific embodiment
To keep the purpose of this utility model, technical solution and advantage clearer, below to the utility model embodiment
It is described in further detail.
Field of face identification research starts from the last century 60's, and by years of researches, face recognition technology is achieved
Significant progress has emerged in large numbers large quantities of representative technologies.Representative algorithm mainly has: PCA (principal component analysis) method,
LDA (linear discriminant analysis) method, Elastic Matching technology and bayes method etc..In recent years, neural network and deep learning
Development so that field of face identification has huge progress again.For at present, even if recognition of face has been achieved for academicly
Significant progress, but under actual environment, the variability of complicated illumination condition and face have recognition of face still to choose
War property.
Embodiment 1
A kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously, referring to Fig. 1, the driving behavior
Analyzer includes following part:
Binocular obtuse angle type camera module 1 is mounted on and drives indoor front, for acquiring driver's facial image and pair
Driver's facial image.
Driving behavior analysis module 2 is identified for the face to driver and copilot.
Loudspeaker module 3, for sounding an alarm.
GPS module 4 positions in real time for vehicle.
4G network communication module 5, is used for transmission face recognition result.
Below with reference to Fig. 2, the design principle of binocular obtuse angle type camera module 1 is described below:
The advantages of binocular obtuse angle type camera module 1 is designed as obtuse angle triangular form pedestal is: two cameras (11 in left and right
It is big with 12) total field range, it may include driver and copilot.It is then easy to shine vehicle window if it is acute angle triangular form,
Difficulty shines driver.If two cameras are in alignment, allowing for driver and copilot, the installation of camera will divide
Open very much, it is not easy to be integrally formed, can be integrally formed not as good as the structure of obtuse angle triangular form, realize once mounting.
The principle of the utility model design is exactly both to have wished that two cameras (11 and 12) in left and right can be than more completely shining driver
Face, and wish that camera module 1 can be integrally formed, facilitate installation and management.
Embodiment 2
It is introduced, is detailed in down below with reference to operating process of the Fig. 1 and Fig. 2 to the driving behavior analysis instrument in embodiment 1
Text description:
1) image of driver and copilot are obtained by left and right two-way camera (11 and 12)；
2) driver's image and copilot's image are detected respectively using the cascade classifier of Haar (Haar wavelet transform) feature
In have face?
If driver and copilot's image have one to detect face, then follow the steps 3)；If driver and copilot
Member's image does not detect face, then return step 1), reacquire next frame image.
Wherein, the cascade classifier of above-mentioned Haar feature is known to those skilled in the art, the utility model embodiment
This is not repeated them here.
3) from the face CNN extracted in the human face region detected in CNN (convolutional neural networks) feature, with face database
Feature does dot product one by one, obtains similarity score；
Descending arrangement is carried out to these scores, the face to rank the first is judged whether to surpass to (i.e. most like face to)
Given threshold value (empirical value 0.6 to 0.8) is crossed, this face is to being considered as same people if being more than given threshold value.
Wherein, above-mentioned CNN feature, given threshold are known to those skilled in the art, and the utility model embodiment is to this
It does not repeat them here.
4) GPS information of the result of recognition of face and current vehicle is sent to background server.The CNN of above-mentioned design and
Haar feature is technology well known in the art, and the utility model is to have used to have there is no the improvement to software technology
, mature technological means.
Embodiment 3
Below with reference to Fig. 1 and Fig. 2, the scheme in Examples 1 and 2 is further introduced, described below:
Wherein, the lens focus of binocular obtuse angle type camera module 1 is 6mm, and image sensor resolutions are
1920x1080 is mounted on and drives indoor front, and left camera 11 and right camera 12 are separately mounted to an obtuse triangle
On two obtuse angle edges of pedestal 13, left camera 11 is responsible for acquisition driver's facial image, and right camera 12 is responsible for acquisition copilot
Member's facial image.
Wherein, ranging preferably from for obtuse angle is preferred between 100-120 degree, and 110 degree are best.The material of pedestal 13 is plastics
Material is also possible to metal material.Pedestal 13 without left and right, be rotated up and down device, with sticking double faced adhesive tape on Auto Instrument desk i.e.
It can.
The model of driving behavior analysis module 2 are as follows: one card row CTTIT-CM10, for carrying out driver and copilot
Recognition of face.
4 ohm 10 watts of the model of loudspeaker module 3, for sounding an alarm.
Section's microelectronics ATGM332D-5N31 in the model of GPS module 4 is positioned in real time for carrying out vehicle.
The model of 4G network communication module moves remote EC20, is used for transmission face recognition result.
To the model of each device in addition to doing specified otherwise, the model of other devices does not limit the utility model embodiment
System, as long as the device of above-mentioned function can be completed.
It will be appreciated by those skilled in the art that attached drawing is the schematic diagram of a preferred embodiment, above-mentioned the utility model is real
It is for illustration only to apply a serial number, does not represent the advantages or disadvantages of the embodiments.
The above is only the preferred embodiment of the present invention, is not intended to limit the utility model, all practical at this
Within novel spirit and principle, any modification, equivalent replacement, improvement and so on should be included in the guarantor of the utility model
Within the scope of shield.
Claims (2)
1. a kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously, which is characterized in that the driving
Behavioural analysis instrument includes:
Binocular obtuse angle type camera module, setting is driving indoor front, for acquiring driver's facial image and copilot
Member's facial image；Driving behavior analysis module is identified for the face to driver and copilot；
Loudspeaker module, for sounding an alarm, 4 ohm 10 watts of model；GPS module positions in real time for vehicle；
4G network communication module, is used for transmission face recognition result；
Wherein, the binocular obtuse angle type camera module, comprising: left camera, right camera and obtuse triangle pedestal,
The left camera and the right camera are separately mounted on two obtuse angle edges of the obtuse triangle pedestal；It is described blunt
Angle triangular base is pasted on Auto Instrument desk；
The obtuse angle of the obtuse triangle pedestal is between 100-120 degree；
The material of the obtuse triangle pedestal is plastic material or metal material.
2. a kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously according to claim 1,
It is characterized in that, the driving behavior analysis instrument further include: the GPS information of the result of recognition of face and current vehicle to be sent to
Background server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201821119495.XU CN208569650U (en) | 2018-07-13 | 2018-07-13 | A kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201821119495.XU CN208569650U (en) | 2018-07-13 | 2018-07-13 | A kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN208569650U true CN208569650U (en) | 2019-03-01 |
Family
ID=65493202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201821119495.XU Active CN208569650U (en) | 2018-07-13 | 2018-07-13 | A kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN208569650U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112455462A (en) * | 2020-11-11 | 2021-03-09 | 上汽大众汽车有限公司 | Passenger cabin system |
-
2018
- 2018-07-13 CN CN201821119495.XU patent/CN208569650U/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112455462A (en) * | 2020-11-11 | 2021-03-09 | 上汽大众汽车有限公司 | Passenger cabin system |
| CN112455462B (en) * | 2020-11-11 | 2022-03-25 | 上汽大众汽车有限公司 | Passenger cabin system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105488453B (en) | A kind of driver based on image procossing does not fasten the safety belt detection recognition method | |
| Pavlić et al. | Image based fog detection in vehicles | |
| CN101512617B (en) | Travel information providing device | |
| Zhang et al. | Driver fatigue detection based intelligent vehicle control | |
| Pavlic et al. | Classification of images in fog and fog-free scenes for use in vehicles | |
| CN104013414A (en) | Driver fatigue detecting system based on smart mobile phone | |
| CN111259719B (en) | Cab scene analysis method based on multi-view infrared vision system | |
| CN202257856U (en) | Driver fatigue-driving monitoring device | |
| CN103824420A (en) | Fatigue driving identification system based on heart rate variability non-contact measuring | |
| CN111062292B (en) | Fatigue driving detection device and method | |
| CN110826369A (en) | Driver attention detection method and system during driving | |
| CN110222596B (en) | Driver behavior analysis anti-cheating method based on vision | |
| CN110733447A (en) | Method, system, computer-readable storage medium and vehicle for automatically adjusting HUD based on driver identity | |
| Paone et al. | Baseline face detection, head pose estimation, and coarse direction detection for facial data in the SHRP2 naturalistic driving study | |
| DE102013222322A1 (en) | Method and device for providing Augmented Reality | |
| CN110807352B (en) | In-vehicle scene visual analysis method for dangerous driving behavior early warning | |
| CN104881956A (en) | Fatigue driving early warning system | |
| CN112016429A (en) | Fatigue driving detection method based on train cab scene | |
| CN106919939B (en) | A kind of traffic signboard tracks and identifies method and system | |
| Sacco et al. | Driver fatigue monitoring system using support vector machines | |
| CN106627529A (en) | Intelligent monitoring method and device for vehicle | |
| CN104881661A (en) | Vehicle detection method based on structure similarity | |
| CN208569650U (en) | A kind of driving behavior analysis instrument for supporting driver and copilot identity to identify simultaneously | |
| CN103927548A (en) | Novel vehicle collision avoiding brake behavior detection method | |
| Kovačić et al. | Computer vision systems in road vehicles: a review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |