CN201427553Y - Alarm system of vehicle departure from lane - Google Patents
Alarm system of vehicle departure from lane Download PDFInfo
- Publication number
- CN201427553Y CN201427553Y CN2009200336939U CN200920033693U CN201427553Y CN 201427553 Y CN201427553 Y CN 201427553Y CN 2009200336939 U CN2009200336939 U CN 2009200336939U CN 200920033693 U CN200920033693 U CN 200920033693U CN 201427553 Y CN201427553 Y CN 201427553Y
- Authority
- CN
- China
- Prior art keywords
- image processor
- vehicle
- image
- acquisition device
- lane
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The utility model relates to the field of the lane marking line identification and alarm, in particular to an alarm system of vehicle departure from a lane. The alarm system of vehicle departure fromthe lane in the prior art has the defects of complicated structure, high cost and complex use. The alarm system comprises an image acquisition device, an alarm device, an image processor and a departure inclination analyzer, wherein the image processor is used for extracting lane making lines in the imaged collected by the image acquisition device through gradation processing, smooth filtering, edge detection and binarization processing, expansion and corrosion processing and Hough transformation, the input end of the image processor is connected with the image acquisition device, the output end of the image processor is connected with the departure inclination analyzer, and the departure inclination analyzer is connected with the alarm device. The utility model has the advantages of convenient use, high efficiency and low cost. Only the camera is required to be added, and the vehicle-mounted computer and audio device can adopt the existing equipment of the vehicle, thereby making theuse easier to be understood.
Description
One, technical field:
The utility model relates to traffic lane line identification and warning field, relates in particular to a kind of automotive run-off-road warning.
Two, background technology:
Worldwide, road traffic accident causes surprising personal casualty and economic loss.Therefore, the safety of automobile more and more is subjected to people's attention, and road safety is in order to prevent accident and to protect the pedestrian, though the security configuration of vehicle is more and more higher, effective method is still learnt and trouble-saving generation.According to statistics, there have 44% car accedent and vehicle to depart from normal lanes approximately to be relevant, and its major cause is the absent minded or fatigue driving of chaufeur, causes the unconscious of vehicle to depart from.According to the data that French ValeosA company provides, there was traffic accident to cause in 2002 owing to deviation or change lane above 410,000.According to another statistics, in annual nearly 1,500,000 traffic accidents of the U.S. owing to unconscious deviation causes.At home, just more by the traffic accident that deviation or change lane cause, because domestic too many traffic accident is because lorry, passenger vehicle driver's super fatigue driving causes, caused many an innocent persons' people to lose life.
The automotive run-off-road warning just is being based on the Vehicle security system of basic traffic regulation, can make the driver keep straight-line travelling, sends the generation of warning to avoid traffic accident when the drowsy run-off-road of driver.The automotive run-off-road warning is behind safety strap, safety air bag, another the safety device of in automobile, installing, because warning has the potentiality that significantly improve the vehicle ' active safety, obtained domestic and international researchist and more and more paid attention to, so warning has market potential and using value widely.But the automotive run-off-road warning of present research and development, complex structure, the cost height uses also more complicated, and many car owners are unwilling to spend too many cost mounting vehicle run-off-road warning onboard.
Three, utility model content:
The purpose of this utility model is to provide a kind of automotive run-off-road warning, and to overcome the automotive run-off-road warning complex structure that prior art exists, the cost height uses complicated shortcoming.
In order to reach above-mentioned technical purpose, the technical solution adopted in the utility model is:
A kind of automotive run-off-road warning comprises image acquisition device, annunciator, it is characterized in that: this system also comprises image processor and departs from the trend analysis instrument; The image processor that described image processor extracts for the traffic lane line in the picture that image acquisition device is collected through gray scale processing, smothing filtering, rim detection and binary conversion treatment, expansion and corrosion treatment, Hough conversion; Described image processor input end is connected with image acquisition device, mouth with depart from the trend analysis instrument and be connected; Departing from the trend analysis instrument is connected with annunciator.
Described annunciator is a sound equipment.
The utility model has the advantages that conveniently, efficient, cost is low, only needing increases camera, car-mounted computer and sound equipment then utilize the automobile existing installation, use and are easily understood.
Four, description of drawings:
Fig. 1 is the utility model structural representation;
Fig. 2 is the utility model image processor principle flow chart;
Fig. 3 is a track angle-off set principle schematic;
Fig. 4 departs from the left-lane scheme drawing for vehicle;
Fig. 5 departs from the right lane scheme drawing for vehicle.
Five, the specific embodiment:
Below in conjunction with drawings and Examples the utility model is further described:
As shown in Figure 1: a kind of automotive run-off-road warning comprises image acquisition device, image processor, departs from trend analysis instrument and annunciator; After the processing of image process gray scale, smothing filtering, rim detection and binary conversion treatment, expansion and the corrosion treatment that described image processor is gathered image acquisition device, the Hough conversion, the traffic lane line in the image is extracted.Described image processor input end is connected with image acquisition device, mouth with depart from the trend analysis instrument and be connected; Departing from the trend analysis instrument is connected with annunciator.
Principle of work of the present utility model is: image acquisition device is installed on the longitudinal centerline of vehicle front, and road pavement is constantly taken, and image acquisition device is transferred to the image that collects on the image processor; Image processor carries out gray scale processing, smothing filtering, rim detection, binary conversion treatment, expansion and corrosion treatment based on the matlab software platform to the image that collects, and utilizes the Hough conversion to extract traffic lane line again.Image processor sends the image of the traffic lane line that extracts to and departs from the trend analysis instrument, departs from the trend analysis instrument and judges by the track angle-off set whether vehicle departs from track and warning reminding chaufeur correction vehicle heading whether.
As shown in Figure 2: image processor receives the image that image acquisition device is gathered, and is as follows to the step of image processing:
1. system initialization;
2. the image that earlier image acquisition device is collected changes gray-scale map into.
3. gray-scale map is carried out smothing filtering: because the interference of climatic conditions, ambient temperature, vehicle movement and electromagnetism, image acquisition device can be subjected to the noise influence of (also claiming stochastic signal) in the process of images acquired, and noise can make image thicken.In the images acquired process, except being subjected to The noise, also can be subjected to the influence of quantizing error, quantizing error can make the border of image border drop on a plurality of pixels, makes image boundary become unintelligible.Image processor adopts the bidimensional convolution algorithm that gray level image is carried out smothing filtering.In image processing process, the bidimensional convolution algorithm is the process of weighted sum, and each pixel in the image-region that uses multiplies each other respectively at each element correspondence of convolution kernel (weight matrix), and all sum of products are as the new value of regional center pixel.The concrete formula of bidimensional convolution algorithm is:
h(x,y)=f(u,v)×g(u,v)=∫∫f(u,v)g(x-u,y-v)
It is first that (u, v) around its initial point Rotate 180 degree, its initial point of translation as last translation x, looks like last translation y on the u axle on the v axle then with g.Right latter two function integration that multiplies each other obtains the output at a some place.By this computing, the weighted sum of utilizing the input pixel to face the territory pixel replaces this input pixel, just can make the border of gray level image become comparatively smoothly clear.
4. more filtered gray level image is carried out rim detection: because traffic lane line and road surface background have stronger contrast ratio, the edge, track is more obvious, utilizes edge detection algorithm to detect the traffic lane line edge.In rim detection, adopt Sobel operator template: the Sobel operator has two, a detection level edge, another detection of vertical edge.Sobel operator template combines the direction calculus of differences with local average, have certain noise inhibiting ability.And, be convenient to the employing of real-time system because the calculated amount of Sobel operator is smaller.In native system,, can adopt the Sobel operator respectively the horizontal edge in track, the left and right sides to be detected at track, the left and right sides.It is as follows to get fixed Sobel operator:
Sobel=[-1-2-1;0?0?0;1?2?1];
After utilizing edge detection method to detect the edge of traffic lane line, utilize the Ostu method that the image sequence that the edge strengthens is carried out binary conversion treatment again, this algorithm can be determined segmentation threshold automatically, makes the variance maximum of prospect and background.
5. still there are some noises in image, as salt-pepper noise after process smothing filtering and rim detection; For follow-up processing is more prone to, reduce traffic lane line and in testing process, be subjected to interference of noise, image processor has adopted the treating process of first expansion post-etching to eliminate and has left over noise.This is a kind of closed operation, utilizes it can fill tiny cavity in the object, connects approaching object, level and smooth its border, but simultaneously and the area of the original object of not obvious change.Expansion algorithm is meant as long as there is a white pixel in the territory of facing of certain pixel, and this pixel will bleach from black so, and remaining remains unchanged simultaneously; Erosion algorithm is meant that this pixel will be black from leucismus so as long as there is a black picture element in the territory of facing of certain pixel, and remaining remains unchanged simultaneously.Because salt-pepper noise is exactly the white point on the picture black, the stain on the white image according to above-mentioned principle, utilizes the expansion corrosion process just can well eliminate and leaves over noise.
6. both comprised traffic lane line through in the image of above-mentioned processing, comprised a lot of spuious lines again, therefore will discern, traffic lane line need have been extracted from spuious lines lane mark.Owing to occur the probability that the probability of straight way occurs much larger than bend in the real road, so native system has adopted the road model of simplifying, promptly straight line track model utilizes the Hough conversion to detect traffic lane line.The Hough conversion is a kind of method that is used for the zone boundary shape description, and its basic thought is that the image space territory is transformed to parameter space, and certain parametric form that satisfies with most of marginal points is described the curve in the image.The point that the Hough conversion is transformed into parameter space with the curve or the straight line of given shape in the original image so just the detection problem of curve in the original image or straight line, is transformed into the problem of seeking peak dot in the parameter space.The polar equation of straight line is as follows:
ρ=xcosθ+ysinθ
(x y) is transformed to two-dimensional parameter space (ρ, θ) point on the point on the straight line to utilize the hough conversion.(ρ θ) changes discrete zone into, and the quantity that falls into the point in this zone is added up with parameter space then.After conversion was finished fully, just ((ρ θ) was the Straight Line Fitting Parameters of image space for ρ, the θ) common ground on corresponding to the two-dimensional parameter space in the quantity that adds up many zones.After system's acquisition Straight Line Fitting Parameters after the Hough conversion, transform in the original image coordinate just the traffic lane line line drawing to be come out later through suitable.Image processor is followed the tracks of traffic lane line by filter again, the state that dopes traffic lane line in the next frame image line parameter of going forward side by side calculates, and this parameter passed to the hough conversion, the detection of traffic lane line in the next frame image is carried out in the hough conversion again on according to the basis of this parameter, reduce the calculated load of hough conversion.Described filter is the Kalman filter.
Image processor is through after above-mentioned steps extracts traffic lane line, the traffic lane line after extracting sent to depart from the trend analysis instrument, departs from the trend analysis instrument and judges whether run-off-road of vehicle according to the track angle-off set again:
As Fig. 3, Fig. 4 and shown in Figure 5, described track angle-off set is:
1) when θ 1+ θ 2>α 1+ α 2, illustrates that vehicle has departed from left-lane, alarm equipment alarm.
2) when θ 1+ θ 2<β 1+ β 2, illustrate that vehicle has departed from right lane, alarm equipment alarm.
3) when (α 1+ α 2)<(θ 1+ θ 2)<(β 1+ β 2), not run-off-road of vehicle is described, annunciator is not reported to the police.
In the above-mentioned formula,
Claims (2)
1. an automotive run-off-road warning comprises image acquisition device, annunciator, it is characterized in that: this system also comprises image processor and departs from the trend analysis instrument; The image processor that described image processor extracts for the traffic lane line in the picture that image acquisition device is collected through gray scale processing, smothing filtering, rim detection and binary conversion treatment, expansion and corrosion treatment, Hough conversion; Described image processor input end is connected with image acquisition device, mouth with depart from the trend analysis instrument and be connected; Departing from the trend analysis instrument is connected with annunciator.
2. a kind of automotive run-off-road warning according to claim 1 is characterized in that: described annunciator is a sound equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2009200336939U CN201427553Y (en) | 2009-06-26 | 2009-06-26 | Alarm system of vehicle departure from lane |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2009200336939U CN201427553Y (en) | 2009-06-26 | 2009-06-26 | Alarm system of vehicle departure from lane |
Publications (1)
Publication Number | Publication Date |
---|---|
CN201427553Y true CN201427553Y (en) | 2010-03-24 |
Family
ID=42031282
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2009200336939U Expired - Fee Related CN201427553Y (en) | 2009-06-26 | 2009-06-26 | Alarm system of vehicle departure from lane |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN201427553Y (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101984478A (en) * | 2010-08-03 | 2011-03-09 | 浙江大学 | Abnormal S-type driving warning method based on binocular vision lane marking detection |
CN102314599A (en) * | 2011-10-11 | 2012-01-11 | 东华大学 | Identification and deviation-detection method for lane |
CN102556066A (en) * | 2012-03-07 | 2012-07-11 | 长安大学 | Lane departure warning device for passenger vehicle and judgment method thereof |
CN103448724A (en) * | 2013-08-23 | 2013-12-18 | 奇瑞汽车股份有限公司 | Lane departure early warning method and device |
CN103496370A (en) * | 2013-10-15 | 2014-01-08 | 扬州瑞控汽车电子有限公司 | Lane departure early warning method |
CN103523013A (en) * | 2012-07-03 | 2014-01-22 | 歌乐株式会社 | Lane departure warning device |
CN103895512A (en) * | 2012-12-26 | 2014-07-02 | 比亚迪股份有限公司 | Traffic safety warning method and traffic safety warning system |
CN103909881A (en) * | 2013-01-08 | 2014-07-09 | 能晶科技股份有限公司 | Environment information detection system and environment information detection method |
CN104309606A (en) * | 2014-11-06 | 2015-01-28 | 中科院微电子研究所昆山分所 | 360-degree panorama based lane departure warning method |
CN105550652A (en) * | 2015-12-14 | 2016-05-04 | 宁波裕兰信息科技有限公司 | Realization method of LDW based on four-camera 360-degree look-around |
CN106032967A (en) * | 2015-02-11 | 2016-10-19 | 贵州景浩科技有限公司 | An automatic magnifying ratio adjusting method for an electronic sight |
CN106529404A (en) * | 2016-09-30 | 2017-03-22 | 张家港长安大学汽车工程研究院 | Imaging principle-based recognition method for pilotless automobile to recognize road marker line |
CN108216229A (en) * | 2017-09-08 | 2018-06-29 | 北京市商汤科技开发有限公司 | The vehicles, road detection and driving control method and device |
CN109591697A (en) * | 2018-11-30 | 2019-04-09 | 长安大学 | A kind of security alerting system based on deviation |
-
2009
- 2009-06-26 CN CN2009200336939U patent/CN201427553Y/en not_active Expired - Fee Related
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101984478B (en) * | 2010-08-03 | 2012-08-08 | 浙江大学 | Abnormal S-type driving warning method based on binocular vision lane marking detection |
CN101984478A (en) * | 2010-08-03 | 2011-03-09 | 浙江大学 | Abnormal S-type driving warning method based on binocular vision lane marking detection |
CN102314599A (en) * | 2011-10-11 | 2012-01-11 | 东华大学 | Identification and deviation-detection method for lane |
CN102556066A (en) * | 2012-03-07 | 2012-07-11 | 长安大学 | Lane departure warning device for passenger vehicle and judgment method thereof |
CN102556066B (en) * | 2012-03-07 | 2014-06-18 | 长安大学 | Lane departure warning device for passenger vehicle and judgment method thereof |
CN103523013A (en) * | 2012-07-03 | 2014-01-22 | 歌乐株式会社 | Lane departure warning device |
CN103523013B (en) * | 2012-07-03 | 2016-03-30 | 歌乐株式会社 | Deviation alarm device |
CN103895512A (en) * | 2012-12-26 | 2014-07-02 | 比亚迪股份有限公司 | Traffic safety warning method and traffic safety warning system |
CN103909881B (en) * | 2013-01-08 | 2016-08-24 | 能晶科技股份有限公司 | Environment information detecting system and environment information method for detecting |
CN103909881A (en) * | 2013-01-08 | 2014-07-09 | 能晶科技股份有限公司 | Environment information detection system and environment information detection method |
CN103448724A (en) * | 2013-08-23 | 2013-12-18 | 奇瑞汽车股份有限公司 | Lane departure early warning method and device |
CN103448724B (en) * | 2013-08-23 | 2016-12-28 | 奇瑞汽车股份有限公司 | Lane departure warning method and device |
CN103496370A (en) * | 2013-10-15 | 2014-01-08 | 扬州瑞控汽车电子有限公司 | Lane departure early warning method |
CN103496370B (en) * | 2013-10-15 | 2018-01-30 | 扬州瑞控汽车电子有限公司 | A kind of lane departure warning method |
CN104309606A (en) * | 2014-11-06 | 2015-01-28 | 中科院微电子研究所昆山分所 | 360-degree panorama based lane departure warning method |
CN106032967A (en) * | 2015-02-11 | 2016-10-19 | 贵州景浩科技有限公司 | An automatic magnifying ratio adjusting method for an electronic sight |
CN105550652A (en) * | 2015-12-14 | 2016-05-04 | 宁波裕兰信息科技有限公司 | Realization method of LDW based on four-camera 360-degree look-around |
CN106529404A (en) * | 2016-09-30 | 2017-03-22 | 张家港长安大学汽车工程研究院 | Imaging principle-based recognition method for pilotless automobile to recognize road marker line |
CN108216229A (en) * | 2017-09-08 | 2018-06-29 | 北京市商汤科技开发有限公司 | The vehicles, road detection and driving control method and device |
CN108216229B (en) * | 2017-09-08 | 2020-01-10 | 北京市商汤科技开发有限公司 | Vehicle, road line detection and driving control method and device |
CN109591697A (en) * | 2018-11-30 | 2019-04-09 | 长安大学 | A kind of security alerting system based on deviation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN201427553Y (en) | Alarm system of vehicle departure from lane | |
CN104008645B (en) | One is applicable to the prediction of urban road lane line and method for early warning | |
CN101135558B (en) | Vehicle anti-collision early warning method and apparatus based on machine vision | |
CN102556066B (en) | Lane departure warning device for passenger vehicle and judgment method thereof | |
CN102737248B (en) | Method and device for extracting characteristic points of lane line under complex road condition | |
CN101739829B (en) | Video-based vehicle overspeed monitoring method and system | |
CN104992145B (en) | A kind of square samples track tracking detection method | |
CN103021177B (en) | Method and system for processing traffic monitoring video image in foggy day | |
CN102514572B (en) | Lane departure early warning method | |
CN102509291B (en) | Pavement disease detecting and recognizing method based on wireless online video sensor | |
CN201325462Y (en) | Train intelligent traffic monitoring system based on driven thermal infrared imager | |
CN105005771A (en) | Method for detecting full line of lane based on optical flow point locus statistics | |
Guo et al. | Image-based seat belt detection | |
CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
CN102862574A (en) | Method for realizing active safety of vehicle on the basis of smart phone | |
CN102419820A (en) | Method for rapidly detecting car logo in videos and images | |
CN201825037U (en) | Lane departure alarm device for vehicles on highway | |
CN105336217A (en) | Driving safety prewarning system based on machine vision and Android platform | |
CN107097794B (en) | System and method for detecting lane line of road | |
CN202134079U (en) | Unmanned vehicle lane marker line identification and alarm device | |
CN109325389A (en) | Lane detection method, apparatus and vehicle | |
CN103440785B (en) | One is traffic lane offset warning method fast | |
CN103593981A (en) | Vehicle model identification method based on video | |
CN116030662B (en) | Intelligent safety detection system and method based on big data | |
CN103927548A (en) | Novel vehicle collision avoiding brake behavior detection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100324 Termination date: 20100626 |