CN106874842A - A kind of automobile based on digital picture and curb distance detection method - Google Patents
A kind of automobile based on digital picture and curb distance detection method Download PDFInfo
- Publication number
- CN106874842A CN106874842A CN201611261395.6A CN201611261395A CN106874842A CN 106874842 A CN106874842 A CN 106874842A CN 201611261395 A CN201611261395 A CN 201611261395A CN 106874842 A CN106874842 A CN 106874842A
- Authority
- CN
- China
- Prior art keywords
- image
- infrared
- curb
- vehicle
- pavement
- 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
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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Traffic Control Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of automobile based on digital picture and curb distance detection method, the method is using following device come the distance between collection vehicle and curb:Infrared wire generating laser, infrared area array cameras, MCU.Wherein, infrared wire generating laser is used to launch infrared linear laser, so as to project infrared batten on the road surface of vehicle both sides;Infrared area array cameras are used to shoot the image at infrared laser projection, for MCU analysis vehicles and the distance of curb;MCU is used to receive picture signal, identification curb position, and analyzes vehicle and curb distance.Automobile based on digital picture of the invention includes with curb distance detection method:Gather the view data of infrared area array cameras;Image to collecting enters row threshold division;Morphological scale-space is carried out to the image after Threshold segmentation, and extracts the center line of image;Identification curb coordinate position in the picture;Position of the curb in vehicle axis system is calculated, the distance between vehicle and curb is calculated.
Description
Technical field
The invention belongs to technical field of machine vision, more particularly to a kind of automobile based on digital picture and curb distance
Method.
Background technology
With the increase of China's car ownership, the safe driving technology of automobile is increasingly subject to people's attention.Due to driving
Limitation of the cabin to driver's seat, driver cannot generally be directly observed the object of left and right vehicle wheel side.For new hand
Driver, when vehicle travels on both sides of the road, it is easy to make vehicle be collided with curb due to sentencing inaccurate, so that
Vehicle and road are damaged.
At present, many vehicles are equipped with the Lane Departure Warning System based on digital image processing techniques.Such system is filled
Put the spatial relationship that can be detected between vehicle and road mark line, and behavior to driver's run-off-road is alerted.But
That requirement of such system to road environment is higher, especially when road mark line is not clear enough, or atmospheric visibility it is poor when,
System easily fails.And such system only detects the information of vehicle front, it is impossible to directly give vehicle both sides with curb
Distance.
The content of the invention
For problem above, it is an object of the present invention to provide a kind of automobile based on digital picture and curb distance
Detection method, realizes the direct measurement of distance between vehicle and curb.
A kind of automobile based on digital picture and curb distance detection method, comprise the following steps:
Step 1, projects infrared using the infrared wire generating laser on vehicle on the road surface of vehicle both sides
Batten, pavement image is gathered followed by the infrared area array cameras on vehicle, and infrared sample is contained in the pavement image
Bar;
Step 2, treatment is filtered using median filter to the pavement image for collecting, pavement image after being filtered
Grey scale pixel value
Step 3, under image coordinate system, row threshold division is entered by filtered pavement image, obtains binary image;Institute
The pavement image lower left corner that image coordinate system is stated to collect is origin, and horizontal direction is X-axis, and vertical direction is Y-axis;
If the gray level of the pavement image is n grades, n=0,1,2 ..., N, N are the integer more than or equal to 0;
Including:
Step 31, foreground image and Background are divided into using each gray level as initial segmentation threshold value by pavement image successively
Picture;The foreground image be pavement image in infrared batten part, the background image be pavement image in removed foreground picture
As rear remaining part;
Calculate the inter-class variance g of foreground image and background image under each gray leveln:
gn=w0(u0-u)+w1(u1-u)2
w0The ratio of pavement image, w are accounted for for the lower foreground image of current gray level level1For the lower background image of current gray level level accounts for road
The ratio of face image;0≤w0≤ 1,0≤w1≤1;
U is the average gray of pavement image, withAverage value as pavement image average gray;
u0It is the average gray of the lower foreground image of current gray level level:
u1It is the average gray of the lower background image of current gray level level:
Wherein, f (x ', y ') is the gray value of pixel in the current gray level lower foreground image of level, and f (x ", y ") is current ash
Under degree level in background image pixel gray value, NfgIt is the quantity of pixel in the lower foreground image of current gray level level, NbgIt is to work as
Under preceding gray level in background image pixel quantity, SfgIt is the set that pixel in the lower foreground image of current gray level level is constituted,
SbgFor the set that pixel in the lower background image of current gray level level is constituted;
Step 32, using gray level of inter-class variance when maximum as final segmentation threshold, two is divided into by pavement image
Value image;
Step 4, closing operation of mathematical morphology is carried out to binary image so that the infrared batten in binary image is continuous;
Step 5, is traveled through using the grating that length is 2 to the binary image that step 4 is obtained, and obtains infrared batten
Center point set (xi,f(xi)), i=1,2,3 ...;
Including:
Step 51, is traveled through, to the binary image that step 4 is obtained using the grating that length is 2 if raster content is
When 0 and 1, then the pixel that now grating is searched is the boundary point of infrared batten in binary image;
Step 52, the border point set of the infrared batten obtained by step 51 obtains the center point set of infrared batten
(xi,f(xi)), i=1,2,3 ...;
Step 6, by the center point set of infrared batten, obtains position Edge of the curb in image coordinate system:
Edge=x | x=arg max [fi' (x)], and fi″(x)≤σ}
Wherein, fi'=f (xi)-f(xi-1), fi"=f (xi)-2f(xi-1)+f(xi-2), σ → 0;
Step 7, the position Edge by curb in image coordinate system is converted to vehicle and curb under vehicle axis system
Stone apart from Dst:
Dst=ax2+by2+cx+dy+m
Wherein, x, y are respectively coordinate position of the curb under image coordinate system, and Edge is curb in image coordinate system
Under X-axis coordinate x set;A, b, c, d, m are constant;A is 6.222 × 10-4, b be 0.2409, c be 0.5568, d for-
212.1, d is 4.696 × 104;
With the center of gravity of vehicle as origin, as X-axis, the pitch axis with vehicle is the roll axis with vehicle the vehicle axis system
Y-axis, the yaw axis with vehicle is as Z axis.
Further, the use median filter described in step 2 is filtered treatment to the pavement image for collecting, filter
The grey scale pixel value of pavement image after rippleFor:
Wherein,It is the grey scale pixel value of pavement image after filtering, SxyIt is appointing for pavement image pixel (x, y)
One neighborhood of meaning, g (s, t) is the gray value of the pixel in the neighborhood.
Compared with prior art, the present invention has following technique effect:
(1) present invention produces infrared batten feature using infrared wire generating laser on road, can avoid visible
Light batten shines into other drivers and pedestrian vision interference;
(2) detection of infrared batten feature is disturbed smaller by ambient in the present invention, therefore method of the present invention exists
Day and night can be applicable;
(3) present invention can be used in detecting the curb position of different height, be that vehicle computer system enters to driver
Row early warning provides reliable basis.
Brief description of the drawings
Fig. 1 is curb distance measuring sensor installation site front schematic view of the invention;
Fig. 2 is curb distance measuring sensor installation site schematic top plan view of the invention;
Fig. 3 is vehicle of the invention and curb distance detection method flow chart;
Fig. 4 is the binary image of infrared batten after dynamic partition in the present invention;
Fig. 5 is the pavement image of infrared batten before dynamic partition in the present invention;
Fig. 6 is by the dynamic threshold segmentation method flow diagram for using of the invention;
Fig. 7 is infrared batten central line pick-up process schematic of the invention;
Fig. 8 is calibration function curve synoptic diagram of the invention.
The present invention is further elaborated with reference to the accompanying drawings and examples.
Specific embodiment
Below by drawings and Examples, the present invention is expanded on further.
In order to realize above-mentioned task, the present invention is achieved using following technical scheme, the automobile based on digital picture with
Curb distance detection device includes:Infrared wire generating laser, infrared area array cameras, MCU.
Described infrared wire generating laser is used to launch infrared linear laser, so as in the road surface upslide of vehicle both sides
Project infrared batten;
Described infrared area array cameras are used to shoot the image at infrared laser projection, and vehicle and curb are analyzed for MCU
The distance of stone;
Described MCU is used to receive picture signal, identification curb position, and analyzes vehicle and curb distance.
As depicted in figs. 1 and 2:
Infrared wire generating laser and infrared area array cameras are mounted on the left surface of vehicle;
Infrared wire generating laser is installed on the center pillar position of vehicle, and its transmitting terminal is downward-sloping, on road surface
Project infrared batten feature;Infrared area array cameras are installed on vehicle left front door outside, the figure for gathering infrared SPL
As feature.
Plane where the line laser beam that infrared wire generating laser sends is vertical with the Central Symmetry face of vehicle.
As shown in figure 3, vehicle of the present invention and curb distance detection method, including:
Step 1, projects infrared using the infrared wire generating laser on vehicle on the road surface of vehicle both sides
Batten, pavement image is gathered followed by the infrared area array cameras on vehicle;During system starts, infrared wire swashs
Optical transmitting set projects an infrared batten on road surface, and the infrared batten can be fitted with the infrared area array cameras institute of polariscope
Capture.
Step 2, is origin with the pavement image lower left corner for collecting, and horizontal direction is X-axis, and vertical direction is set up for Y-axis
Image coordinate system;
Treatment is filtered to the pavement image for collecting using median filter, the pixel grey scale of pavement image after filtering
ValueFor:
Wherein,It is the grey scale pixel value of pavement image after filtering, SxyIt is appointing for pavement image pixel (x, y)
One neighborhood of meaning, g (s, t) is the gray value of the pixel in the neighborhood.
Step 3, by the light environment that vehicle is run is complex, the present invention uses the method pair of dynamic threshold segmentation
Filtered pavement image enters row threshold division, obtains binary image.Fig. 4 is the binary picture obtained after dynamic threshold segmentation
Picture, Fig. 5 is the pavement image before dynamic threshold segmentation.
If the gray level of the pavement image is n grades, n=0,1,2 ..., N, N are the integer more than or equal to 0;
Step 31, foreground image and Background are divided into using each gray level as initial segmentation threshold value by pavement image successively
Picture;N takes 255 in the present embodiment, and the foreground image is the infrared batten part in pavement image, and the background image is road surface
Remaining part after foreground image was removed in image;
Calculate the inter-class variance g of foreground image and background image under each gray leveln:
gn=w0(u0-u)+w1(u1-u)2
w0The ratio of pavement image, w are accounted for for the lower foreground image of current gray level level1For the lower background image of current gray level level accounts for road
The ratio of face image;0≤w0≤ 1,0≤w1≤1;
w0=N0/ N, w1=N1/N.Wherein, N0And N1Respectively prospect, background pixel point quantity, N are that image slices vegetarian refreshments is total
Quantity;
U is the average gray of pavement image, withAverage value as pavement image average gray;
u0It is the average gray of the lower foreground image of current gray level level:
u1It is the average gray of the lower background image of current gray level level:
Wherein, f (x ', y ') is the gray value of pixel in the current gray level lower foreground image of level, and f (x ", y ") is current ash
Under degree level in background image pixel gray value, NfgIt is the quantity of pixel in the lower foreground image of current gray level level, NbgIt is to work as
Under preceding gray level in background image pixel quantity, SfgIt is the set that pixel in the lower foreground image of current gray level level is constituted,
SbgFor the set that pixel in the lower background image of current gray level level is constituted;
Step 32, using gray level of inter-class variance when maximum as final segmentation threshold, two is divided into by pavement image
Value image;
Step 4, due to the influence of the factors such as ground relief, the image that camera is collected may be unlike shown in Fig. 4
Infrared batten as it is continuous whole, but in the infrared battens of some segmentations.In method of the present invention, form need to be used
The method for learning closed operation treatment joins together the SPL of fracture, obtains the foreground image of continuous infrared batten.
Wherein, A is the pixel set of input picture, and B is Morphological Structuring Elements, and " " is closed operation symbol,Represent
Expanded Operators,Represent erosion operator.
Step 5, as shown in fig. 7, being traveled through using the grating road pavement image that length is 2, obtains infrared batten
Center point set (xi,f(xi)), i=1,2,3 ...;
Step 51, is traveled through using the grating that length is 2 to the binary image that step 4 is obtained, because grating is searched for
To be the pixel outside infrared batten when, raster content be 0 and 0, grating search for infrared batten when, raster content is 1
With 1, if so when raster content is 0 and 1, the pixel that now grating is searched is the border of infrared batten in pavement image
Point;
Step 52, the border point set of the infrared batten obtained by step 51 obtains the center point set of infrared batten
(xi,f(xi)), i=1,2,3 ...;
In the present embodiment, it is assumed that in the jth of the row of image i-th1、j2Row detects two borders up and down of SPL respectively
Point, then SPL be in the central point of the rowAfter similar treatment being carried out to each row of image, you can obtain red
Discrete point set (the x of outer batten central pointi,f(xi)), i=1,2,3 ....xiIt is coordinate of the infrared batten central point in x-axis,
f(xi) it is infrared batten central point coordinate on the y axis.
Step 6, because outer and the road surface of curb are typically at a right angle, therefore, by calculated curve center point set
First derivative and second dervative, the catastrophe point in curve can be found.
By the center point set of infrared batten, position Edge of the curb in image coordinate system is obtained:
Edge=x | x=arg max [fi' (x)], and fi″(x)≤σ}
Wherein, due to (xi,f(xi)), i=1,2,3 ... is discrete point, so fi' (x) and fi" (x) is replaced with difference, fi′
=f (xi)-f(xi-1), fi"=f (xi)-2f(xi-1)+f(xi-2), σ → 0.
Step 7, the position Edge by curb in image coordinate system is converted to vehicle and curb under vehicle axis system
Stone apart from Dst:
Dst=ax2+by2+cx+dy+m
Wherein, x, y are respectively coordinate position of the curb under image coordinate system;A, b, c, d, m are each undetermined constant.
In order to obtain a, the value of b, c, d, m, what the present invention was selected is to determine its numerical value using the method for experimental calibration, specifically
Be:
First, by testing 5 groups of data d between acquisition vehicle and curbi,xi,yi, i=1,2,3,4,5.Now this
Five groups of numbers may be constructed following linear equation:
Further, vectorial X=[a b c d m] can be obtainedTSolution:
In the present embodiment, 5 groups of different curb edges to vehicle longitudinal axis distance are respectively provided with:1800mm、
1600mm, 1500mm, 1200mm and 1000mm.In acquired image, the marginal point for recognizing is in image coordinate system
Coordinate is respectively (1175,441), (1065,448), (1019,440), (835,448), (699,431).Data are substituted into formula
In, obtaining calibrating parameters is:
Using above calibrating parameters, the image coordinate of other curb marginal points can be calculated in vehicle axis system
Position.The curve drawn out using above calibration coefficient is as shown in Figure 8.
Claims (2)
1. a kind of automobile based on digital picture and curb distance detection method, it is characterised in that comprise the following steps:
Step 1, infrared batten is projected using the infrared wire generating laser on vehicle on the road surface of vehicle both sides,
Pavement image is gathered followed by the infrared area array cameras on vehicle, infrared batten is contained in the pavement image;
Step 2, treatment is filtered using median filter to the pavement image for collecting, the picture of pavement image after being filtered
Plain gray value
Step 3, under image coordinate system, row threshold division is entered by filtered pavement image, obtains binary image;The figure
With the pavement image lower left corner for collecting it is origin as coordinate system, horizontal direction is X-axis, and vertical direction is Y-axis;
If the gray level of the pavement image is n grades, n=0,1,2 ..., N, N are the integer more than or equal to 0;
Including:
Step 31, foreground image and background image are divided into using each gray level as initial segmentation threshold value by pavement image successively;
The foreground image is the infrared batten part in pavement image, after the background image in pavement image to remove foreground image
Remaining part;
Calculate the inter-class variance g of foreground image and background image under each gray leveln:
gn=w0(u0-u)+w1(u1-u)2
w0The ratio of pavement image, w are accounted for for the lower foreground image of current gray level level1For the lower background image of current gray level level accounts for road surface figure
The ratio of picture;0≤w0≤ 1,0≤w1≤1;
U is the average gray of pavement image, withAverage value as pavement image average gray;
u0It is the average gray of the lower foreground image of current gray level level:
u1It is the average gray of the lower background image of current gray level level:
Wherein, f (x ', y ') is the gray value of pixel in the current gray level lower foreground image of level, and f (x ", y ") is current gray level level
The gray value of pixel, N in lower background imagefgIt is the quantity of pixel in the lower foreground image of current gray level level, NbgIt is current ash
Under degree level in background image pixel quantity, SfgIt is the set that pixel in the lower foreground image of current gray level level is constituted, SbgFor
The set that pixel is constituted in the lower background image of current gray level level;
Step 32, using gray level of inter-class variance when maximum as final segmentation threshold, binaryzation is divided into by pavement image
Image;
Step 4, closing operation of mathematical morphology is carried out to binary image so that the infrared batten in binary image is continuous;
Step 5, is traveled through using the grating that length is 2 to the binary image that step 4 is obtained, in obtaining infrared batten
Heart point set (xi,f(xi)), i=1,2,3 ...;
Including:
Step 51, is traveled through using the grating that length is 2 to the binary image that step 4 is obtained, if raster content is 0 and 1
When, then the pixel that now grating is searched is the boundary point of infrared batten in binary image;
Step 52, the border point set of the infrared batten obtained by step 51 obtains the center point set (x of infrared batteni,f
(xi)), i=1,2,3 ...;
Step 6, by the center point set of infrared batten, obtains position Edge of the curb in image coordinate system:
Edge=x | x=argmax [fi' (x)], and fi″(x)≤σ}
Wherein, fi'=f (xi)-f(xi-1), fi"=f (xi)-2f(xi-1)+f(xi-2), σ → 0;
Step 7, the position Edge by curb in image coordinate system is converted to vehicle and curb under vehicle axis system
Apart from Dst:
Dst=ax2+by2+cx+dy+m
Wherein, x, y are respectively coordinate position of the curb under image coordinate system, and Edge is curb under image coordinate system
The set of X-axis coordinate x;A, b, c, d, m are constant;A is 6.222 × 10-4, b is that 0.2409, c is that 0.5568, d is -212.1, d
It is 4.696 × 104;
The vehicle axis system with the center of gravity of vehicle as origin, the roll axis with vehicle as X-axis, the pitch axis with vehicle as Y-axis,
Yaw axis with vehicle is as Z axis.
2. the automobile and curb distance detection method of digital picture are based on as claimed in claim 1, it is characterised in that step
Use median filter described in 2 is filtered treatment to the pavement image for collecting, the pixel ash of pavement image after filtering
Angle valueFor:
Wherein,It is the grey scale pixel value of pavement image after filtering, SxyFor pavement image pixel (x, y) any one
Neighborhood, g (s, t) is the gray value of the pixel in the neighborhood.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611261395.6A CN106874842B (en) | 2016-12-30 | 2016-12-30 | Digital image-based automobile and road edge stone distance detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611261395.6A CN106874842B (en) | 2016-12-30 | 2016-12-30 | Digital image-based automobile and road edge stone distance detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106874842A true CN106874842A (en) | 2017-06-20 |
CN106874842B CN106874842B (en) | 2020-07-03 |
Family
ID=59165293
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611261395.6A Expired - Fee Related CN106874842B (en) | 2016-12-30 | 2016-12-30 | Digital image-based automobile and road edge stone distance detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106874842B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109359632A (en) * | 2018-11-30 | 2019-02-19 | 重庆昂布瑞拉科技有限公司 | Highway sideline detection method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101789123A (en) * | 2010-01-27 | 2010-07-28 | 中国科学院半导体研究所 | Method for creating distance map based on monocular camera machine vision |
EP2257458A1 (en) * | 2008-04-03 | 2010-12-08 | Valeo Schalter und Sensoren GmbH | Method and device for supporting a driver of a vehicle during the process of leaving a parking space |
CN102804239A (en) * | 2010-03-24 | 2012-11-28 | 株式会社东芝 | Processing device for assisting driving of vehicle, vehicle driving assisting device, and vehicle device |
CN104554256A (en) * | 2013-10-16 | 2015-04-29 | 福特全球技术公司 | Method and device for assisting automobile parking onto road edge stone |
CN105292085A (en) * | 2015-11-02 | 2016-02-03 | 清华大学苏州汽车研究院(吴江) | Vehicle forward collision avoidance system based on infrared laser aid |
-
2016
- 2016-12-30 CN CN201611261395.6A patent/CN106874842B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2257458A1 (en) * | 2008-04-03 | 2010-12-08 | Valeo Schalter und Sensoren GmbH | Method and device for supporting a driver of a vehicle during the process of leaving a parking space |
CN101789123A (en) * | 2010-01-27 | 2010-07-28 | 中国科学院半导体研究所 | Method for creating distance map based on monocular camera machine vision |
CN102804239A (en) * | 2010-03-24 | 2012-11-28 | 株式会社东芝 | Processing device for assisting driving of vehicle, vehicle driving assisting device, and vehicle device |
CN104554256A (en) * | 2013-10-16 | 2015-04-29 | 福特全球技术公司 | Method and device for assisting automobile parking onto road edge stone |
CN105292085A (en) * | 2015-11-02 | 2016-02-03 | 清华大学苏州汽车研究院(吴江) | Vehicle forward collision avoidance system based on infrared laser aid |
Non-Patent Citations (4)
Title |
---|
JIANN-DER LEE ET AL.: ""A Warning System for Obstacle Detection at Vehicle Lateral Blind Spot Area"", 《2013 7TH ASIA MODELLING SYMPOSIUM》 * |
宋宏勋 等: ""基于双相机立体摄影测量的路面裂缝识别方法"", 《中国公路学报》 * |
梁宗宇 等: ""基于激光测距的汽车防撞警示系统设计"", 《电脑知识与技术》 * |
王建锋 等: ""路面三维检测技术研究"", 《武汉理工大学学报(交通科学与工程版)》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109359632A (en) * | 2018-11-30 | 2019-02-19 | 重庆昂布瑞拉科技有限公司 | Highway sideline detection method and device |
CN109359632B (en) * | 2018-11-30 | 2021-08-10 | 重庆子粒科技有限公司 | Road sideline detection method and device |
Also Published As
Publication number | Publication date |
---|---|
CN106874842B (en) | 2020-07-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105260699B (en) | A kind of processing method and processing device of lane line data | |
Assidiq et al. | Real time lane detection for autonomous vehicles | |
CN107025432B (en) | A kind of efficient lane detection tracking and system | |
US20200041284A1 (en) | Map road marking and road quality collecting apparatus and method based on adas system | |
CN109190523B (en) | Vehicle detection tracking early warning method based on vision | |
CN104916163B (en) | Parking space detection method | |
EP1796043B1 (en) | Object detection | |
CN105835880B (en) | Lane following system | |
US7046822B1 (en) | Method of detecting objects within a wide range of a road vehicle | |
JP4930046B2 (en) | Road surface discrimination method and road surface discrimination device | |
CN101030256B (en) | Method and apparatus for cutting vehicle image | |
CN105206109B (en) | A kind of vehicle greasy weather identification early warning system and method based on infrared CCD | |
CN108596058A (en) | Running disorder object distance measuring method based on computer vision | |
CN110647850A (en) | Automatic lane deviation measuring method based on inverse perspective principle | |
AU2015352462B2 (en) | Method of controlling a traffic surveillance system | |
CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
US20150015384A1 (en) | Object Detection Device | |
KR101478258B1 (en) | Lane detection method and system | |
CN107274678B (en) | A kind of night vehicle flowrate and model recognizing method based on Kinect | |
CN107886034B (en) | Driving reminding method and device and vehicle | |
EP2741234B1 (en) | Object localization using vertical symmetry | |
CN105303844B (en) | Night expressway fog automatic detection device and its detection method based on laser | |
Meshram et al. | Traffic surveillance by counting and classification of vehicles from video using image processing | |
CN114639078A (en) | Vehicle type recognition method, device and system | |
CN108108680A (en) | A kind of front vehicle identification and distance measuring method based on binocular vision |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210521 Address after: Room 502, 5th floor, bishuiyunxuan, No.9, Xingqing South Road, Beilin District, Xi'an City, Shaanxi Province, 710000 Patentee after: Shaanxi shuoxuan Information Technology Co.,Ltd. Address before: 710064 No. 126 central section of South Ring Road, Yanta District, Xi'an, Shaanxi Patentee before: CHANG'AN University |
|
TR01 | Transfer of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200703 Termination date: 20211230 |
|
CF01 | Termination of patent right due to non-payment of annual fee |