CN103832357A - Lane departure warning system and method based on machine vision - Google Patents
Lane departure warning system and method based on machine vision Download PDFInfo
- Publication number
- CN103832357A CN103832357A CN201210486538.9A CN201210486538A CN103832357A CN 103832357 A CN103832357 A CN 103832357A CN 201210486538 A CN201210486538 A CN 201210486538A CN 103832357 A CN103832357 A CN 103832357A
- Authority
- CN
- China
- Prior art keywords
- processing unit
- automobile
- digital signal
- lane
- image
- 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.)
- Granted
Links
Images
Landscapes
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
A lane departure warning system based on machine vision comprises an interface processing unit, a forward-looking camera, a digital signal processing unit and a power source module, wherein the forward-looking camera is installed at the middle upper portion of an automobile front windshield, and the position where the forward-looking camera is installed does not shield the sight of a driver and can be cleaned by a windscreen wiper; the forward-looking camera collects the image in front of an automobile and transmits the image to the digital signal processing unit; the digital signal processing unit intelligently decides whether the automobile will deviate from a lane or not; image information processed by the digital signal processing unit is transmitted to the interface processing unit; the interface processing unit controls a warning device to work; the power source module supplies power to other modules. By the adoption of an advanced vision mode recognition algorithm, a high-speed digital signal processor is combined to analyze the road traffic of the camera installed on the automobile, when it is forecasted that the automobile will deviate from the lane and a driver is not conscious of deviation of the automobile, the driver is warned on the aspect of visual sense or sense of hearing or sense of touch, the driver is reminded to drive safely, and accidents are reduced effectively.
Description
Technical field
The present invention discloses a kind of vehicle warning system, particularly a kind of lane-departure warning system and method based on machine vision.
Background technology
Along with the development gradually of automobile industry, automobile pollution increases day by day, and automobile is lived the convenience brought with fast self-evident to people, and the flourish of auto trade brings very large contribution to economy, but also produce a series of social concerns, wherein traffic accident is the most serious problem simultaneously.According to statistics, in 2011, Kuomintang-Communist occurs 210812, death toll: 62387 people.Wherein the cause of most accidents is that driver drives rashly, due to not observing traffic rules and regulations, in this, be that driver crosses over two tracks and causes in driving procedure greatly, although highway is provided with track warning line, but in driving procedure, whether line ball of vehicle, relies on driver's driving experience judgement completely, very inaccurate.
Summary of the invention
For easy line ball in the above-mentioned vehicle drive process of the prior art of mentioning, cause the shortcoming of traffic accident, the invention provides a kind of new lane-departure warning system based on machine vision and method, it adopts advanced computer vision algorithm for pattern recognition, in conjunction with high speed digital signal processor to vehicle-mounted camera driving road-condition real-time analysis, can predict vehicle will run-off-road, also in unconscious situation about doing like this, send vision to chaufeur but driver is actual, the warning of the sense of hearing or sense of touch aspect, take care and travel with prompting driver, effectively minimizing accident occurs.
The technical scheme that the present invention solves its technical matters employing is: a kind of lane-departure warning system based on machine vision, system comprises interface processing unit, forward sight camera, digital signal processing unit and power module, described forward sight camera is arranged on shield glass middle and upper part and does not block the position that driver's sight line and windscreen wiper can clean, gather vehicle front image, and by image transmitting to digital signal processing unit, whether digital signal processing unit intelligent decision vehicle will run-off-road, through digital signal processing unit image transmission after treatment to interface processing unit, interface is processed the work of unit controls warning device, power module is given other module for power supply.
Adopt above-mentioned system to realize blind spot detecting test of vehicle and the method for warming based on machine vision, the method comprises the steps:
A, igniting: system powers on;
B, enter idle pulley in the do not walk front or too low system of speed of automobile, now can't start lane departur warning function;
After C, disengaging idle condition, system detects side-marker lamp's on off state, if side-marker lamp does not open, camera enters a day inter mode;
If D side-marker lamp opens, enter night vision pattern;
E, system open camera and carry out AGC to road conditions Real-time Collection and according to light power, and the image of distortion is corrected, the information collecting with 25 frames the per second or 30 frames digital signal processing unit that is sent to per second;
F, digital signal processing unit are converted into the vision signal of receiving the colour picture of rgb format;
G, YUV coding: the image of rgb format is converted into yuv format through matrixer: obtain brightness signal Y and two colour difference signal R-Y, i.e. U, B-Y, i.e. V, separates brightness signal Y with carrier chrominance signal U, V;
H, picture breakdown are upper and lower two parts, only retain the latter half and use as calculating when processing;
I, pattern analysis: confirm weather conditions;
If J wiper system or fog lamp system are opened, system will be analyzed as rain, mist, snow weather, now adopt digital filter to carry out image noise reduction; If wiper system or fog lamp system, without unlatching, directly enter K flow process;
K, lane identification analysis: adopt Hough mapping algorithm, rim detection identification is carried out in track: track enters deviation identification process L if detected; If otherwise there is no track, system enters idle condition;
L, deviation identification:
The track identifying is analyzed, take 1 pixel as unit, in the time that X1 > α and θ 1 are greater than β and spend, deviation left-lane;
When X2 is less than α ', and θ 2 deviation right lane while being greater than β ';
Wherein α, β, α ', and the value of β ' is according to different automobile types, different installation sites timing is set;
If vehicle does not have run-off-road, this returns to idle condition and again detects;
If deviation detected, enter into step M;
M, in the time that track is about to depart from, detect turn signal swich state:
If the steering indicating light of corresponding orientation is opened, think initiatively circuit switched of driver, return to idle condition;
Otherwise, if without opening corresponding orientation steering indicating light, think the unconscious tangent line of driver;
N, steering wheel inclination angle detect: whether assistant analysis vehicle turns to behavior;
If O system analysis result is unconscious tangent line, according to different hazard levels sound, image or vibrations warning signal.
The technical scheme that the present invention solves its technical matters employing further comprises:
The invention has the beneficial effects as follows: the present invention adopts advanced computer vision algorithm for pattern recognition, in conjunction with high speed digital signal processor to vehicle-mounted camera driving road-condition real-time analysis, can predict vehicle will run-off-road, also in unconscious situation about doing like this, send vision to chaufeur but driver is actual, the warning of the sense of hearing or sense of touch aspect, take care and travel with prompting driver, effectively minimizing accident occurs.
Below in conjunction with the drawings and specific embodiments, the present invention will be further described.
Accompanying drawing explanation
Fig. 1 is system block diagram of the present invention.
Fig. 2 is mounting structure schematic diagram of the present invention.
Fig. 3 is method of calculating schematic diagram of the present invention.
Fig. 4 is system flowchart of the present invention.
In figure, 1-car body, 2-forward sight camera, 3-warns panel, 4-road, the road route mark after 5-Hough conversion.
The specific embodiment
The present embodiment is the preferred embodiment for the present invention, and other all its principles are identical with the present embodiment or approximate with basic structure, all within protection domain of the present invention.
Please refer to accompanying drawing 1 and accompanying drawing 2, the lane-departure warning system based on machine vision in the present invention, comprise interface processing unit, forward sight camera 2, digital signal processing unit and power module, forward sight camera 2 is arranged on car body 1 front windshield middle and upper part and does not block the position that driver's sight line and windscreen wiper can clean, gather vehicle front image, and by image transmitting to digital signal processing unit, whether digital signal processing unit intelligent decision vehicle will run-off-road, through digital signal processing unit image transmission after treatment to interface processing unit, interface is processed the work of unit controls warning device, power module is given other module for power supply, in the present embodiment, power module is power interface, power interface is connected with automobile power source, (be automobile batteries by automobile power source, 12V or 24V) to system power supply.In the present embodiment, interface microcontroller processing unit is connected with the sensor in automobile by I/O mouth or CAN bus bus, whether obtain information of vehicles, in the present embodiment, the signal that need to obtain comprises: (1) turn signal swich: be driver's active steering for analyzing; (2) vehicle speed signal: for activation or the sleep pattern of decision system; (3) steering wheel angle: whether assistant analysis vehicle turns to; (4) side-marker lamp's signal: for identifying pattern switching at day/night; (5) fog lamp signal: for identifying mist synoptic model; (6) windscreen wiper signal: for identifying rainy day gas switch mode; (7) ignition signal: whether light a fire for identifying vehicle launch.In the present embodiment, digital signal processing unit adopts DSP high speed digital signal processor, DSP high speed digital signal processor does not block the position that driver's sight line and windscreen wiper can clean forward sight camera 2 by being arranged on car body 1 front windshield middle and upper part obtains the road conditions image in driving, carry out complicated Machine Vision Recognition in conjunction with speed information, whether intelligent decision vehicle will run-off-road.DSP high speed digital signal processor can according to vehicle shift situation make interface microcontroller processing unit by CAN bus bus send different brackets warning message to warning panel 3, independently warn panel 3 receiving after warning message and will on panel, show different warning messages to chaufeur.
The present invention is connected to power supply and warning panel 3 by wire harness and adaptor union.User only need plug adaptor union, and plug and play is without carrying out complexity setting, convenient and swift.
Please refer to accompanying drawing 4, the method for the lane departur warning based on machine vision of the present invention comprises the steps:
A, igniting: system powers on;
B, power on after because car is moving, or speed is too low without starting lane departur warning function, thus system enters idle condition; When speed during higher than 10KPH (i.e. 10 kilometer per hours are defined as the moving and motionless demarcation line of car in the present invention) system depart from idle condition;
After C, disengaging idle condition, system detects side-marker lamp's on off state, if side-marker lamp does not open, camera enters a day inter mode;
If D side-marker lamp opens, camera enters night vision pattern;
E, system are opened camera and are carried out AGC (i.e. braking gain is controlled) to road conditions Real-time Collection and according to light power, and the image of distortion is corrected (in the present embodiment, AGC and image are corrected and are automatically completed by camera module), and the information collecting is sent to dsp processor with 25 frames (pal mode) per second or 30 frames (TSC-system formula) per second;
F, dsp processor are converted into the vision signal of receiving the colour picture of rgb format;
G, YUV coding: the image of rgb format is converted into yuv format through matrixer: obtain brightness signal Y and two colour difference signal R-Y (being U), B-Y (being V), brightness signal Y is separated with carrier chrominance signal U, V, there is no U, V signal component if only have Y-signal component, the image so representing is exactly black and white gray level image;
H, picture breakdown are two parts: due to camera collection to picture useful information be: track is in image the latter half, for reducing the calculated amount of arithmetic and logic unit, reduce track analysis (being step K) the erroneous judgement interference that the first half data produce, in the present embodiment, picture is divided into upper and lower two parts, when processing, only retains the latter half and use as calculating;
I, pattern analysis: confirm weather conditions: fine, rain, mist, snow, etc.;
If J wiper system or fog lamp system are opened, system will be analyzed as rain, mist, snow weather, now, due to misty rain snow block vision, cause drawing unintelligible, need to adopt digital filter to carry out image noise reduction, if without unlatching, this directly enters K flow process;
K, lane identification analysis: adopt Hough mapping algorithm, rim detection identification is carried out in track, if detected, track enters deviation identification process L; If otherwise there is no track, system enters idle condition;
L, deviation identification:
Please refer to accompanying drawing 3, in the present invention, the track identifying analyzed, take 1 pixel as unit, in the time that X1 > α and θ 1 are greater than β and spend, deviation left-lane is described,
When X2 is less than α ', and θ 2 deviation right lane while being greater than β ';
In the present embodiment, X1 is the extended line of left-lane and the intersection point of the image bottom line distance to image left side edge, X2 is that the intersection point of right lane extended line and image bottom line is to the distance of image left side edge, θ 1 is the extended line of left-lane and the angle of image bottom line, θ 2 is angles of right lane extended line and image bottom line, when α is normal vehicle operation, the intersection point of the extended line of left-lane and image bottom line is to the maximum limit of the distance of image left side edge, when β is normal vehicle operation, the maxim of the angle of the extended line of left-lane and image bottom line, when α ' is normal vehicle operation, when the intersection point of the extended line of right lane and image bottom line is normal vehicle operation to the minimum limit value of the distance of image left side edge and β ', the maxim of the angle of the extended line of right lane and image bottom line, α, β, the value of α ' and β ' need be set (according to different automobile types according to actual installation timing, different installation sites, its numeral is different),
If vehicle does not have run-off-road, return to idle condition and again detect;
If deviation detected, enter into step M;
M, in the time that track is about to depart from, detect turn signal swich state:
If the steering indicating light of corresponding orientation is opened, think initiatively circuit switched of driver, return to idle condition;
Otherwise, if without opening corresponding orientation steering indicating light, think the unconscious tangent line of driver;
N, steering wheel inclination angle detect: whether assistant analysis vehicle turns to behavior;
If O system analysis result is unconscious tangent line, according to different hazard levels sound, the warning signal such as image, vibrations, or three kinds of signals send simultaneously.
The present invention adopts advanced computer vision algorithm for pattern recognition, in conjunction with high speed digital signal processor to vehicle-mounted camera driving road-condition real-time analysis, can predict vehicle will run-off-road, also in unconscious situation about doing like this, send vision to chaufeur but driver is actual, the warning of the sense of hearing or sense of touch aspect, take care and travel with prompting driver, effectively minimizing accident occurs.
Claims (5)
1. the lane-departure warning system based on machine vision, it is characterized in that: described system comprises interface processing unit, forward sight camera, digital signal processing unit and power module, described forward sight camera is arranged on shield glass middle and upper part and does not block the position that driver's sight line and windscreen wiper can clean, gather vehicle front image, and by image transmitting to digital signal processing unit, whether digital signal processing unit intelligent decision vehicle will run-off-road, through digital signal processing unit image transmission after treatment to interface processing unit, interface is processed the work of unit controls warning device, power module is given other module for power supply.
2. the lane-departure warning system based on machine vision according to claim 1, is characterized in that: described interface processing unit is connected with the sensor in automobile by I/O mouth or CAN bus bus.
3. the lane-departure warning system based on machine vision according to claim 1, is characterized in that: described power module is power interface, and power interface is connected with automobile power source, by automobile power source to system power supply.
4. the system of employing as described in claim 1 or 2 or 3 realizes blind spot detecting test of vehicle and the method for warming based on machine vision, it is characterized in that: described method comprises the steps:
A, igniting: system powers on;
B, enter idle pulley in the do not walk front or too low system of speed of automobile, now can't start lane departur warning function;
After C, disengaging idle condition, system detects side-marker lamp's on off state, if side-marker lamp does not open, camera enters a day inter mode;
If D side-marker lamp opens, enter night vision pattern;
E, system open camera and carry out AGC to road conditions Real-time Collection and according to light power, and the image of distortion is corrected, the information collecting with 25 frames the per second or 30 frames digital signal processing unit that is sent to per second;
F, digital signal processing unit are converted into the vision signal of receiving the colour picture of rgb format;
G, YUV coding: the image of rgb format is converted into yuv format through matrixer: obtain brightness signal Y and two colour difference signal R-Y, i.e. U, B-Y, i.e. V, separates brightness signal Y with carrier chrominance signal U, V;
H, picture breakdown are upper and lower two parts, only retain the latter half and use as calculating when processing;
I, pattern analysis: confirm weather conditions;
If J wiper system or fog lamp system are opened, system will be analyzed as rain, mist, snow weather, now adopt digital filter to carry out image noise reduction; If wiper system or fog lamp system, without unlatching, directly enter K flow process;
K, lane identification analysis: adopt Hough mapping algorithm, rim detection identification is carried out in track: track enters deviation identification process L if detected; If otherwise there is no track, system enters idle condition;
L, deviation identification:
The track identifying is analyzed, take 1 pixel as unit, in the time that X1 > α and θ 1 are greater than β and spend, deviation left-lane;
When X2 is less than α ', and θ 2 deviation right lane while being greater than β ';
Wherein α, β, α ', and the value of β ' is according to different automobile types, different installation sites timing is set;
If vehicle does not have run-off-road, this returns to idle condition and again detects;
If deviation detected, enter into step M;
M, in the time that track is about to depart from, detect turn signal swich state:
If the steering indicating light of corresponding orientation is opened, think owner to move circuit switched, return to idle condition;
Otherwise, if without opening corresponding orientation steering indicating light, think the unconscious tangent line of driver;
N, steering wheel inclination angle detect: whether assistant analysis vehicle turns to behavior;
If O system analysis result is unconscious tangent line, according to different hazard levels sound, image or vibrations warning signal.
5. method according to claim 4, is characterized in that: described automobile is less than 10KPH for automobile speed per hour before not walking.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210486538.9A CN103832357B (en) | 2012-11-23 | 2012-11-23 | A kind of lane-departure warning system and method based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210486538.9A CN103832357B (en) | 2012-11-23 | 2012-11-23 | A kind of lane-departure warning system and method based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103832357A true CN103832357A (en) | 2014-06-04 |
CN103832357B CN103832357B (en) | 2017-10-13 |
Family
ID=50796357
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210486538.9A Active CN103832357B (en) | 2012-11-23 | 2012-11-23 | A kind of lane-departure warning system and method based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103832357B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104691333A (en) * | 2015-03-30 | 2015-06-10 | 吉林大学 | Lane departure frequency-based method for evaluating state of fatigue of long-distance bus driver |
US20160101729A1 (en) * | 2014-10-08 | 2016-04-14 | Myine Electronics, Inc. | System and method for monitoring driving behavior |
CN105539293A (en) * | 2016-02-03 | 2016-05-04 | 北京中科慧眼科技有限公司 | Lane-departure early warning method and device and automobile driving assistance system |
CN106558248A (en) * | 2016-12-13 | 2017-04-05 | 天津泓耘财科技发展有限公司 | A kind of panorama sees deviation prewarning monitoring system |
CN106828308A (en) * | 2017-01-24 | 2017-06-13 | 桂林师范高等专科学校 | Lane departure warning device |
CN108630014A (en) * | 2018-05-10 | 2018-10-09 | 苏州天瞳威视电子科技有限公司 | A kind of lane deviates early warning system and method |
CN108973855A (en) * | 2018-07-19 | 2018-12-11 | 南京地平线机器人技术有限公司 | Method and apparatus for lane departure warning |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070147660A1 (en) * | 2003-02-22 | 2007-06-28 | Daimier Chrysler Ag | Image processing system for motor vehicles |
CN101264755A (en) * | 2008-03-06 | 2008-09-17 | 上海交通大学 | Vehicle running safety intelligence monitoring and controlling device |
CN102303609A (en) * | 2011-06-16 | 2012-01-04 | 广东铁将军防盗设备有限公司 | System and method for prewarning lane deviation |
CN202413787U (en) * | 2011-12-12 | 2012-09-05 | 浙江吉利汽车研究院有限公司 | Prewarning control system for automobile lane deviation |
CN203293984U (en) * | 2012-11-23 | 2013-11-20 | 深圳华一汽车科技有限公司 | Lane departure warning system based on machine vision |
-
2012
- 2012-11-23 CN CN201210486538.9A patent/CN103832357B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070147660A1 (en) * | 2003-02-22 | 2007-06-28 | Daimier Chrysler Ag | Image processing system for motor vehicles |
CN101264755A (en) * | 2008-03-06 | 2008-09-17 | 上海交通大学 | Vehicle running safety intelligence monitoring and controlling device |
CN102303609A (en) * | 2011-06-16 | 2012-01-04 | 广东铁将军防盗设备有限公司 | System and method for prewarning lane deviation |
CN202413787U (en) * | 2011-12-12 | 2012-09-05 | 浙江吉利汽车研究院有限公司 | Prewarning control system for automobile lane deviation |
CN203293984U (en) * | 2012-11-23 | 2013-11-20 | 深圳华一汽车科技有限公司 | Lane departure warning system based on machine vision |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160101729A1 (en) * | 2014-10-08 | 2016-04-14 | Myine Electronics, Inc. | System and method for monitoring driving behavior |
US9764689B2 (en) * | 2014-10-08 | 2017-09-19 | Livio, Inc. | System and method for monitoring driving behavior |
CN104691333A (en) * | 2015-03-30 | 2015-06-10 | 吉林大学 | Lane departure frequency-based method for evaluating state of fatigue of long-distance bus driver |
CN104691333B (en) * | 2015-03-30 | 2017-03-15 | 吉林大学 | Coach driver fatigue state evaluation method based on the deviation frequency |
CN105539293A (en) * | 2016-02-03 | 2016-05-04 | 北京中科慧眼科技有限公司 | Lane-departure early warning method and device and automobile driving assistance system |
CN106558248A (en) * | 2016-12-13 | 2017-04-05 | 天津泓耘财科技发展有限公司 | A kind of panorama sees deviation prewarning monitoring system |
CN106828308A (en) * | 2017-01-24 | 2017-06-13 | 桂林师范高等专科学校 | Lane departure warning device |
CN108630014A (en) * | 2018-05-10 | 2018-10-09 | 苏州天瞳威视电子科技有限公司 | A kind of lane deviates early warning system and method |
CN108973855A (en) * | 2018-07-19 | 2018-12-11 | 南京地平线机器人技术有限公司 | Method and apparatus for lane departure warning |
Also Published As
Publication number | Publication date |
---|---|
CN103832357B (en) | 2017-10-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103832357A (en) | Lane departure warning system and method based on machine vision | |
CN105799574B (en) | Night intelligence DAS (Driver Assistant System) | |
CN102431556B (en) | Based on the integrated driver prior-warning device that bus or train route is collaborative | |
CN102424016B (en) | Automobile headlamp automatic control system based on machine vision | |
CN201824950U (en) | Automobile safe running anti-collision system | |
US20140049973A1 (en) | Headlamp control apparatus | |
CN101984478B (en) | Abnormal S-type driving warning method based on binocular vision lane marking detection | |
CN108372825B (en) | Automatic light switching method for tunnel portal vehicle based on image recognition | |
CN103434442B (en) | Based on the night safe meeting truck system of machine vision and the control method of this system | |
CN105374221B (en) | Traffic signal light condition system for prompting and based reminding method | |
CN205469262U (en) | Car lane keeps auxiliary system based on embedded recognition technology that makes a video recording | |
CN103723073B (en) | A kind of danger of Fusion is overtaken other vehicles prior-warning device and method for early warning thereof | |
CN201325462Y (en) | Train intelligent traffic monitoring system based on driven thermal infrared imager | |
CN101016052A (en) | Warning method and system for preventing deviation for vehicle on high standard highway | |
CN205768952U (en) | Night intelligence auxiliary driving device | |
CN103832380A (en) | Dead zone automobile detection and warning system and method based on machine vision | |
CN103057470A (en) | Pre-prompt device and pre-prompt method for regulation violation line-rolling of vehicles | |
CN203293984U (en) | Lane departure warning system based on machine vision | |
CN104527427A (en) | Velocity-limiting mark recognizing and vehicle-velocity control method and system based on vehicle traveling recording instrument | |
CN102395009A (en) | Vehicle-mounted infrared night vision system with pedestrian identification function | |
CN203332106U (en) | Automobile warning anti-collision system based on monocular vision | |
CN105667386A (en) | Automobile light control system | |
CN111619449A (en) | T-shaped intersection automobile blind area monitoring system and monitoring method | |
CN114954307A (en) | Driving assistance system based on artificial intelligence | |
CN104228670A (en) | Event data recorder of large vehicle and implementation method thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |