CN103400150A - Method and device for road edge recognition based on mobile platform - Google Patents
Method and device for road edge recognition based on mobile platform Download PDFInfo
- Publication number
- CN103400150A CN103400150A CN201310351847XA CN201310351847A CN103400150A CN 103400150 A CN103400150 A CN 103400150A CN 201310351847X A CN201310351847X A CN 201310351847XA CN 201310351847 A CN201310351847 A CN 201310351847A CN 103400150 A CN103400150 A CN 103400150A
- Authority
- CN
- China
- Prior art keywords
- image
- road edge
- obtains
- mobile platform
- road
- 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
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method and a device for road edge recognition based on a mobile platform. The method comprises the following steps: using a camera module to acquire real-time pictorial information of a road; using the mobile platform to process the real-time pictorial information acquired by the camera module; converting a YUV spatial image into an RGB spatial image; converting the acquired RGB spatial image into an HSV spatial image; performing binaryzation process for the HSV spatial image; converting the acquired RGB spatial image into a grayscale image and performing edge and line detection; performing further screening for the detected lines according to the acquired zone in which the road edge is located; selecting the longest line in the road edge zone as a road edge. The method and the device solve the problems that the algorithm of the conventional road edge recognition system takes up a huge memory, is poor in real-time property, and is susceptible to interference from the outer environment, and most algorithms are only suitable for detecting ideal roads with clear edges.
Description
Technical field
The present invention relates to a kind of method and device of road edge identification, especially a kind of movement-based platform carries out method and the device of road edge identification.
Background technology
In electronic equipment, image color pattern commonly used has following a few class at present.
RGB color space: obtain color miscellaneous by the variation to red (R), green (G), blue (B) three Color Channels and their stacks each other, RGB is namely the color that represents three passages of red, green, blue, this standard almost comprised mankind eyesights can perception all colours, be to use at present one of the widest color system.The fundamental purpose of RGB color model is in electronic system, detect, represent and show image, such as TV and computer, application is also arranged simultaneously in traditional photography.
YUV color space: YUV is the same with RGB, and be used to representing color, both can transform mutually.A kind of colour coding method (belonging to PAL) that YUV is adopted by the eurovision system.YUV is mainly used in optimizing the transmission of colour-video signal, makes the old-fashioned black-and-white television of its back compatible.With the rgb video signal transmission, compare, the advantage of its maximum is only need take few bandwidth." Y " expression lightness wherein, GTG value namely, as baseband signal.What " U " and " V " represented is colourity, and effect is to describe colors of image and saturation degree, is used to specify the color of pixel.The hsv color space: the three dimensional representation of HSV model is to develop from the RGB cube, wherein: tone (H), saturation degree (S), brightness (V).Imagination is observed to the black summit on cornerwise white summit from RGB along cube, can see cubical hexagonal external feature.Hexagonal boundaries represents tone (H), and transverse axis represents saturation degree (S), and brightness (V) is measured along Z-axis.H Parametric Representation color information, the i.e. position of residing spectral color.This parameter represents with an angular metric, red, green, blue 120 degree of being separated by respectively.Complementary colors differs respectively 180 degree.Saturation degree S is a ratio value, scope from 0 to 1, and it is expressed as the ratio between the purity of the purity of selected color and this color maximum.During S=0, only has gray scale.V represents the bright degree of color, scope from 0 to 1.Because HSV is a kind of color model more intuitively, so application is more extensive in many image editing tools.
The road edge recognition device is the real-time processing by the road pavement image, warns the existence of vehicle driver's road edge in the vehicle drive path, or is provided for the device of the feasible driving region limits of route planning when autonomous driving.Road-edge detection algorithm commonly used and deficiency thereof are as follows at present.
(1) Hough change detection straight line method.
The Hough conversion utilizes the point of image space and Hough parameter space-line duality, and the test problems in image space is transformed into to parameter space.By in parameter space, carrying out simple cumulative statistics, then at the Hough parameter space, find the method detection of straight lines of totalizer peak value.
Not enough: take larger internal memory, real-time is poor, is subject to external interference, and during especially for road-edge detection, it is larger that shade, barrier etc. detect the road impact to Hough.
(2) based on the image segmentation of color space HSV.
By the image transitions by rgb color space, be the image in HSV space, can be by interested color information (as S) be further processed, method mainly contains histogram thresholding method, clustering procedure, region growing method and edge detection method etc.
Not enough: after the color space conversion, need to choose suitable image processing method and detect road edge, effective method is often brought the reduction of real-time.Threshold value is chosen more difficult assurance.
(3) road stencil matching method.
With the template of mathematical model, track is mated.
Not enough: more complicated template library can bring more accurate matching degree, and is comparatively obvious but internal memory and real-time descend.Better simply template library matching speed is fast, but degree of accuracy is not high.Shade and interference are larger on the matching effect impact.
(4) based on the tracking of characteristic parameter.
Tracking based on characteristic parameter is a kind of method of parameter estimation, and it is mainly to be used on the basis of setting up the Lane Mark model to carry out, and the most representative is various filtering methods, as Kalman filtering.And the particle filter method etc. that grows up on its basis.
Not enough: because being predicts anaphase with prior probability, so in case error appears in prediction, rear period error can increase gradually, so initial survey need to have than high-accuracy.The method calculated amount is very large, needs powerful hardware platform.
Summary of the invention
For addressing the above problem, the invention provides method and device that a kind of movement-based platform carries out road edge identification, with solve existing method for the serious treatment of road surfaces weak effect of shade, required memory is large and the poor shortcoming of real-time after can't being applied to mobile platform system (as the Android system) or being applied in mobile platform.
For achieving the above object, technical scheme of the present invention is:
A kind of movement-based platform carries out the method for road edge identification, comprises the steps:
S1: with photographing module, gather the realtime graphic information that obtains road surface, described realtime graphic information is the yuv space image;
S2: use mobile platform to process the realtime graphic information that photographing module obtains, the yuv space image transitions is become to the rgb space image;
S3: the rgb space image transitions that obtains in step S2 is become to the HSV spatial image, it is carried out to the image binaryzation processing, specifically comprise the steps:
S31: the rgb space image transitions that obtains in step S2 is become to the HSV spatial image;
S32: select threshold value according to the S territory of described HSV spatial image;
S33: passing threshold carries out binary conversion treatment to the HSV spatial image;
S34: the binary image that step S33 is obtained expands successively, corrosion treatment, obtains the road edge region;
S4: be gray level image by the rgb space image transitions that obtains in step S2, it is carried out to edge and straight-line detection, specifically comprise the steps:
S41: be gray level image by the rgb space image transitions that obtains in step S2;
S42: gray level image is carried out to rim detection by arithmetic operators;
S43: the image that obtains after step S42 is detected carries out straight-line detection;
S44: the straight line that detects in step S43 is screened and optimizes;
S5: according to the road edge region that obtains in step S34, the straight line that detects in step S44 is further screened, be chosen at the longest straight line in the road edge zone as road edge.
Further, in described step S32, the selection of threshold value zone is the image geometric areas of of side or the approximate trapezoid that is comprised of a plurality of figures on the lower side.The computing method of described threshold value are: calculate respectively the S territory mean value in each geometric areas, choose the median of these mean values, described median is threshold value.
Further, described step S33 comprises: by the S territory at (a-b, a+b) point of the scope in scope is made as white, all the other are made as black color dots, wherein a is described threshold value, b is the maximal value of the S territory mean value of trying to achieve in selected several geometric areas and the difference of minimum value, and described white point compositing area is the road region that Preliminary detection goes out, and the black color dots compositing area is the road edge region that Preliminary detection goes out.
Further, in described step S42, rim detection is used Canny operator, Sobel operator.
Further, the straight-line detection of described step S43 adopts Hough change detection straight line method.
Further, described step S44 specifically comprises: by the analysis to slope and displacement, broken line segment be connected or delete, by analyzing the continuity of the detected road edge of former two field pictures in image sequence, carrying out the straight line screening.
A kind of movement-based platform carries out the device of road edge identification, comprising:
For gathering the photographing module of the realtime graphic information that obtains road surface, the realtime graphic information that described photographing module obtains is the yuv space image;
For the mobile platform that the realtime graphic information that photographing module is obtained is processed, described mobile platform becomes the rgb space image by the yuv space image transitions;
Described mobile platform becomes the HSV spatial image by the rgb space image transitions, mobile platform is selected threshold value according to the S territory of described HSV spatial image, by described threshold value, the HSV spatial image is carried out to binary conversion treatment, described binary image to acquisition expands successively, corrosion treatment, obtains the road edge region;
Described mobile platform is gray level image by the rgb space image transitions of acquisition simultaneously, mobile platform carries out rim detection to described gray level image by arithmetic operators, the image that obtains after described detection is carried out to straight-line detection, the described straight line that detects is screened and optimizes;
Described mobile platform further screens the described straight line that detects according to the described road edge zone that obtains, and is chosen at the longest straight line in the road edge zone as road edge.
Further, described photographing module is connected and carries out exchanges data with described mobile platform by the OTG line.
Further, described device also comprises the information processing terminal, and the described information processing terminal is for receiving the data of storing mobile platform, and the result that described mobile platform will finally be processed is undertaken by the network and information processing terminal alternately.
According to above scheme, the present invention has obtained following beneficial effect: (1) is based on the road edge feature: take straight line as main, can reach the degree of practical application fully; (2) based on the shadows on the road feature: very approaching with the non-hatched area of road in the S territory, the impact that can remove according to this shade, calculated amount is less simultaneously, reduces the requirement to internal memory; (3) based on realtime graphic: because road has continuity in the image of front and back, can consider according to this image continuity, before and after preventing, larger error appears in testing result; (4) area-of-interest: all can be limited in some area-of-interest image is cut apart, threshold value is chosen, realtime graphic detection etc., can reduce operand; (5) reduce algorithm complex: by above strategy, algorithm complex is very low, therefore can be good be applied to mobile platform; (6) be applicable to complex environment: can detect roadmarking, also can detect road edge, so more campus environment and the highway of shade all can use.
The accompanying drawing explanation
Fig. 1 is method flow schematic diagram of the present invention.
Fig. 2 is the device schematic diagram that movement-based platform of the present invention carries out road edge identification.
Embodiment
In order to make purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
As shown in Figure 1, method step of the present invention is as follows:
S1: with photographing module, gather the realtime graphic information that obtains road surface, described realtime graphic information is the yuv space image, and is specific as follows:
Directly by photographing module, obtain the data of yuv space image, it is converted to the rgb space image from yuv space, establish it and be img_src.
S2: use mobile platform to process the realtime graphic information that photographing module obtains, the yuv space image transitions is become to the rgb space image, specific as follows:
The img_src image is converted to the HSV spatial image from rgb space, is made as img_hsv.
S3: the rgb space image transitions that obtains in step S2 is become to the HSV spatial image, it is carried out to the image binaryzation processing, specific as follows:
Image space conversion: the img_src image is converted to the HSV spatial image from rgb space, is made as img_hsv.
Choose binary-state threshold: according to the S territory of img_hsv image, select optimal threshold, the zone that threshold value is selected is the image zone of of side or the approximate trapezoid that is comprised of a plurality of figures on the lower side.The optimal threshold computing method are by calculating respectively the S territory mean value in each geometric areas, choose the median of these mean values, and described median is threshold value, and the optimal threshold of establishing acquisition is a.
Passing threshold a carries out image binaryzation: by the S territory at (a-b, a+b) point in scope is made as white point, all the other are made as black color dots, wherein: a is described threshold value, b is selected neighborhood value, described neighborhood value b is the maximal value of the S territory mean value of trying to achieve in selected several geometric areas and the difference of minimum value, and described white point compositing area is the road region that Preliminary detection goes out, and the black color dots compositing area is the road edge region that Preliminary detection goes out.
To resulting binary picture expand successively, corrosion treatment.Described expansion step is that all background dots with object contact are merged in this object, makes the process of border to the outside expansion.Can be used for filling up the cavity in object.In this embodiment, the algorithm of expansion comprises: with the structural element of 3x3, each pixel of scan image is done AND-operation with the bianry image of structural element and its covering, if be all 0, this pixel of image is 0, otherwise is 1, and this step can make bianry image enlarge a circle.Corrosion is a kind of elimination frontier point, makes the process of border to internal contraction.Can be used for eliminating little and insignificant object.In this embodiment, the algorithm of corrosion comprises: with the structural element of 3x3, each pixel of scan image is done AND-operation with the bianry image of structural element and its covering, if be all 1, this pixel of image is 1, otherwise is 0.This step can make bianry image reduce a circle.The above-mentioned process that first expands post-etching is called closed operation, and described closed operation can be used to fill tiny cavity in object, connects adjacent object, smoothly when its border and its area of not obvious change.By above expansion, corrosion treatment step, can effectively get rid of the noise spot in road, and make road edge more level and smooth.
S4: by the rgb space image transitions that obtains in step S2, be gray level image, it is carried out to edge and straight-line detection, specific as follows:
Img_src is converted to gray-scale map, is made as img_gray.
Rim detection: img_gray is carried out to rim detection, and rim detection can be used other edge detection operators such as Canny operator, Sobel operator.
After edge detected, the gained figure carried out straight-line detection.The present invention uses Hough transform method detection of straight lines, and the straight line that detects is screened and optimizes, screening can consider that with optimization principles slope and displacement etc. are connected broken line segment or delete, also can consider the continuity of road edge at image sequence, before relying on, the detected road edge of several two field pictures carries out the straight line screening.
According to the road edge region that obtains in step S3, the straight line that detects in step S4 is further screened, be chosen at the longest straight line in the road edge zone as road edge.
As shown in Figure 2, a kind of movement-based platform carries out the device of road edge identification, comprising:
For gathering the photographing module of the realtime graphic information that obtains road surface, the realtime graphic information that described photographing module obtains is the yuv space image;
For the mobile platform that the realtime graphic information that photographing module is obtained is processed, described mobile platform becomes the rgb space image by the yuv space image transitions;
Described mobile platform becomes the HSV spatial image by the rgb space image transitions, mobile platform is selected threshold value according to the S territory of described HSV spatial image, by described threshold value, the HSV spatial image is carried out to binary conversion treatment, described binary image to acquisition expands successively, corrosion treatment, obtains the road edge region;
Described mobile platform is gray level image by the rgb space image transitions of acquisition simultaneously, mobile platform carries out rim detection to described gray level image by arithmetic operators, the image that obtains after described detection is carried out to straight-line detection, the described straight line that detects is screened and optimizes;
Described mobile platform further screens the described straight line that detects according to the described road edge zone that obtains, and is chosen at the longest straight line in the road edge zone as road edge.
Further, described photographing module is connected and carries out exchanges data with described mobile platform by the OTG line.
Further, described device also comprises the information processing terminal, and the described information processing terminal is for receiving the data of storing mobile platform, and the result that described mobile platform will finally be processed is undertaken by the network and information processing terminal alternately.
Claims (10)
1. the method that the movement-based platform carries out road edge identification, is characterized in that, comprises the steps:
S1: with photographing module, gather the realtime graphic information that obtains road surface, described realtime graphic information is the yuv space image;
S2: use mobile platform to process the realtime graphic information that photographing module obtains, the yuv space image transitions is become to the rgb space image;
S3: the rgb space image transitions that obtains in step S2 is become to the HSV spatial image, it is carried out to the image binaryzation processing, specifically comprise the steps:
S31: the rgb space image transitions that obtains in step S2 is become to the HSV spatial image;
S32: select threshold value according to the S territory of described HSV spatial image;
S33: passing threshold carries out binary conversion treatment to the HSV spatial image;
S34: the binary image that step S33 is obtained expands successively, corrosion treatment, obtains the road edge region;
S4: be gray level image by the rgb space image transitions that obtains in step S2, it is carried out to edge and straight-line detection, specifically comprise the steps:
S41: be gray level image by the rgb space image transitions that obtains in step S2;
S42: gray level image is carried out to rim detection by arithmetic operators;
S43: the image that obtains after step S42 is detected carries out straight-line detection;
S44: the straight line that detects in step S43 is screened and optimizes;
S5: according to the road edge region that obtains in step S34, the straight line that detects in step S44 is further screened, be chosen at the longest straight line in the road edge zone as road edge.
2. the movement-based platform according to claim 1 method of carrying out road edge identification, is characterized in that, in described step S32, the selection of threshold value zone is the image geometric areas of of side or the approximate trapezoid that is comprised of a plurality of figures on the lower side.
3. the movement-based platform according to claim 2 method of carrying out road edge identification, it is characterized in that, the choosing method of the threshold value in described step S32 comprises: calculate respectively the S territory mean value in each geometric areas, choose the median of these mean values, described median is threshold value.
4. the movement-based platform according to claim 1 method of carrying out road edge identification, is characterized in that, described step S33 comprises as follows:
By the S territory at (a-b, a+b) point of the scope in scope is made as white, all the other are made as black, wherein a is described threshold value, b is the maximal value of the S territory mean value of trying to achieve in selected several geometric areas and the difference of minimum value, described white point compositing area is the road region that Preliminary detection goes out, and the black color dots compositing area is the road edge region that Preliminary detection goes out.
5. the method that according to claim 1 to 4, arbitrary described movement-based platform carries out road edge identification, is characterized in that, in described step S42, rim detection is used Canny operator, Sobel operator.
6. the movement-based platform according to claim 5 method of carrying out road edge identification, is characterized in that, the straight-line detection of described step S43 adopts Hough change detection straight line method.
7. the movement-based platform according to claim 6 method of carrying out road edge identification, it is characterized in that, described step S44 specifically comprises: by the analysis to slope and displacement, broken line segment be connected or delete, by analyzing the continuity of the detected road edge of former two field pictures in image sequence, carrying out the straight line screening.
8. the device that the movement-based platform carries out road edge identification, is characterized in that, comprising:
For gathering the photographing module of the realtime graphic information that obtains road surface, the realtime graphic information that described photographing module obtains is the yuv space image;
For the mobile platform that the realtime graphic information that photographing module is obtained is processed, described mobile platform becomes the rgb space image by the yuv space image transitions;
Described mobile platform becomes the HSV spatial image by the rgb space image transitions, mobile platform is selected threshold value according to the S territory of described HSV spatial image, by described threshold value, the HSV spatial image is carried out to binary conversion treatment, binary image to acquisition expands successively, corrosion treatment, obtains the road edge region;
Described mobile platform is gray level image by the rgb space image transitions of acquisition simultaneously, mobile platform carries out rim detection to described gray level image by arithmetic operators, the image that obtains after described detection is carried out to straight-line detection, the straight line that detects is screened and optimizes;
Described mobile platform further screens the described straight line that detects according to the described road edge zone that obtains, and is chosen at the longest straight line in the road edge zone as road edge.
9. the movement-based platform according to claim 8 device that carries out road edge identification, is characterized in that, described photographing module is connected and carries out exchanges data with described mobile platform by the OTG line.
10. the movement-based platform according to claim 9 device that carries out road edge identification, it is characterized in that, described device also comprises the information processing terminal, the described information processing terminal is for receiving the data of storing mobile platform, and the result that described mobile platform will finally be processed is undertaken by the network and information processing terminal alternately.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310351847.XA CN103400150B (en) | 2013-08-14 | 2013-08-14 | A kind of method and device that road edge identification is carried out based on mobile platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310351847.XA CN103400150B (en) | 2013-08-14 | 2013-08-14 | A kind of method and device that road edge identification is carried out based on mobile platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103400150A true CN103400150A (en) | 2013-11-20 |
| CN103400150B CN103400150B (en) | 2017-07-07 |
Family
ID=49563768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310351847.XA Active CN103400150B (en) | 2013-08-14 | 2013-08-14 | A kind of method and device that road edge identification is carried out based on mobile platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103400150B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714538A (en) * | 2013-12-20 | 2014-04-09 | 中联重科股份有限公司 | Road edge detection method, device and vehicle |
| CN104680519A (en) * | 2015-02-06 | 2015-06-03 | 四川长虹电器股份有限公司 | Seven-piece puzzle identification method based on contours and colors |
| CN105488492A (en) * | 2015-12-25 | 2016-04-13 | 北京大学深圳研究生院 | Color image preprocessing method, road identification method and related device |
| CN105549603A (en) * | 2015-12-07 | 2016-05-04 | 北京航空航天大学 | Intelligent road tour inspection control method for multi-rotor-wing unmanned aerial vehicle |
| CN105809149A (en) * | 2016-03-31 | 2016-07-27 | 电子科技大学 | Lane line detection method based on straight lines with maximum length |
| CN105956511A (en) * | 2016-04-18 | 2016-09-21 | 江苏大学 | Lane line detecting and combining method based on Hough transform |
| CN106153634A (en) * | 2016-09-22 | 2016-11-23 | 武汉科技大学 | A kind of image acquisition for test refractory brick thermal shock resistance automatically and processing system |
| CN106444765A (en) * | 2016-10-21 | 2017-02-22 | 广东工业大学 | AGV (automatic guided vehicle), AGV navigation method based on vision and AGV navigation system based on vision |
| CN107358224A (en) * | 2017-08-18 | 2017-11-17 | 北京工业大学 | A kind of method that iris outline detects in cataract operation |
| CN105046260B (en) * | 2015-07-31 | 2019-01-04 | 小米科技有限责任公司 | Image pre-processing method and device |
| CN109592342A (en) * | 2018-11-15 | 2019-04-09 | 华南智能机器人创新研究院 | A kind of vision cylindrical material material delivery method and system |
| CN109934128A (en) * | 2019-02-27 | 2019-06-25 | 长安大学 | A kind of Aerial Images pavement identification method for road disease detection |
| CN110795994A (en) * | 2019-09-16 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Intersection image selection method and device |
| CN111043485A (en) * | 2020-01-08 | 2020-04-21 | 南京航空航天大学 | Two-axis full-automatic tracking cradle head and tracking method thereof |
| CN111163575A (en) * | 2020-01-02 | 2020-05-15 | 杭州涂鸦信息技术有限公司 | Method and system for supporting remote control of five-way colored lamp |
| CN112183554A (en) * | 2020-09-01 | 2021-01-05 | 国交空间信息技术（北京）有限公司 | Automatic road boundary contour extraction method |
| CN112529922A (en) * | 2020-11-18 | 2021-03-19 | 南京农业大学 | Method for accurately separating RGB image backgrounds of multicolor blades in open environment |
| CN112613523A (en) * | 2020-12-15 | 2021-04-06 | 中冶赛迪重庆信息技术有限公司 | Method, system, medium and electronic terminal for identifying steel flow at converter steel tapping hole |
| TWI729898B (en) * | 2020-08-04 | 2021-06-01 | 國立勤益科技大學 | Lane image analysis method |
| CN113392704A (en) * | 2021-05-12 | 2021-09-14 | 重庆大学 | Mountain road sideline position detection method |
| CN113642372A (en) * | 2020-04-27 | 2021-11-12 | 百度（美国）有限责任公司 | Method and system for recognizing object based on gray-scale image in operation of autonomous driving vehicle |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682292A (en) * | 2012-05-10 | 2012-09-19 | 清华大学 | Method based on monocular vision for detecting and roughly positioning edge of road |
-
2013
- 2013-08-14 CN CN201310351847.XA patent/CN103400150B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682292A (en) * | 2012-05-10 | 2012-09-19 | 清华大学 | Method based on monocular vision for detecting and roughly positioning edge of road |
Non-Patent Citations (1)
| Title |
|---|
| 张凤珍等: "基于数学形态学与Hough变换的道路边缘提取", 《太原科技大学学报》 * |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714538B (en) * | 2013-12-20 | 2016-12-28 | 中联重科股份有限公司 | road edge detection method, device and vehicle |
| CN103714538A (en) * | 2013-12-20 | 2014-04-09 | 中联重科股份有限公司 | Road edge detection method, device and vehicle |
| CN104680519A (en) * | 2015-02-06 | 2015-06-03 | 四川长虹电器股份有限公司 | Seven-piece puzzle identification method based on contours and colors |
| CN104680519B (en) * | 2015-02-06 | 2017-06-23 | 四川长虹电器股份有限公司 | Seven-piece puzzle recognition methods based on profile and color |
| CN105046260B (en) * | 2015-07-31 | 2019-01-04 | 小米科技有限责任公司 | Image pre-processing method and device |
| CN105549603A (en) * | 2015-12-07 | 2016-05-04 | 北京航空航天大学 | Intelligent road tour inspection control method for multi-rotor-wing unmanned aerial vehicle |
| CN105488492A (en) * | 2015-12-25 | 2016-04-13 | 北京大学深圳研究生院 | Color image preprocessing method, road identification method and related device |
| CN105809149A (en) * | 2016-03-31 | 2016-07-27 | 电子科技大学 | Lane line detection method based on straight lines with maximum length |
| CN105956511A (en) * | 2016-04-18 | 2016-09-21 | 江苏大学 | Lane line detecting and combining method based on Hough transform |
| CN105956511B (en) * | 2016-04-18 | 2019-04-02 | 江苏大学 | A method of lane straight-line detection based on Hough transform with merge |
| CN106153634A (en) * | 2016-09-22 | 2016-11-23 | 武汉科技大学 | A kind of image acquisition for test refractory brick thermal shock resistance automatically and processing system |
| CN106444765A (en) * | 2016-10-21 | 2017-02-22 | 广东工业大学 | AGV (automatic guided vehicle), AGV navigation method based on vision and AGV navigation system based on vision |
| CN106444765B (en) * | 2016-10-21 | 2019-07-09 | 广东工业大学 | A kind of AGV air navigation aid of view-based access control model |
| CN107358224A (en) * | 2017-08-18 | 2017-11-17 | 北京工业大学 | A kind of method that iris outline detects in cataract operation |
| CN109592342A (en) * | 2018-11-15 | 2019-04-09 | 华南智能机器人创新研究院 | A kind of vision cylindrical material material delivery method and system |
| CN109934128A (en) * | 2019-02-27 | 2019-06-25 | 长安大学 | A kind of Aerial Images pavement identification method for road disease detection |
| CN110795994A (en) * | 2019-09-16 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Intersection image selection method and device |
| CN111163575A (en) * | 2020-01-02 | 2020-05-15 | 杭州涂鸦信息技术有限公司 | Method and system for supporting remote control of five-way colored lamp |
| CN111043485A (en) * | 2020-01-08 | 2020-04-21 | 南京航空航天大学 | Two-axis full-automatic tracking cradle head and tracking method thereof |
| CN111043485B (en) * | 2020-01-08 | 2024-03-19 | 南京航空航天大学 | Two-axis full-automatic tracking holder and tracking method thereof |
| CN113642372A (en) * | 2020-04-27 | 2021-11-12 | 百度（美国）有限责任公司 | Method and system for recognizing object based on gray-scale image in operation of autonomous driving vehicle |
| CN113642372B (en) * | 2020-04-27 | 2024-02-20 | 百度（美国）有限责任公司 | Method and system for recognizing object based on gray image in operation of autonomous driving vehicle |
| TWI729898B (en) * | 2020-08-04 | 2021-06-01 | 國立勤益科技大學 | Lane image analysis method |
| CN112183554A (en) * | 2020-09-01 | 2021-01-05 | 国交空间信息技术（北京）有限公司 | Automatic road boundary contour extraction method |
| CN112529922A (en) * | 2020-11-18 | 2021-03-19 | 南京农业大学 | Method for accurately separating RGB image backgrounds of multicolor blades in open environment |
| CN112613523A (en) * | 2020-12-15 | 2021-04-06 | 中冶赛迪重庆信息技术有限公司 | Method, system, medium and electronic terminal for identifying steel flow at converter steel tapping hole |
| CN113392704A (en) * | 2021-05-12 | 2021-09-14 | 重庆大学 | Mountain road sideline position detection method |
| CN113392704B (en) * | 2021-05-12 | 2022-06-10 | 重庆大学 | Mountain road sideline position detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103400150B (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103400150B (en) | A kind of method and device that road edge identification is carried out based on mobile platform | |
| US10592754B2 (en) | Shadow removing method for color image and application | |
| CN109886896B (en) | Blue license plate segmentation and correction method | |
| CN106709436B (en) | Track traffic panoramic monitoring-oriented cross-camera suspicious pedestrian target tracking system | |
| US8660349B2 (en) | Screen area detection method and screen area detection system | |
| CN102682292B (en) | Method based on monocular vision for detecting and roughly positioning edge of road | |
| CN110516550B (en) | FPGA-based lane line real-time detection method | |
| US20060153450A1 (en) | Integrated image processor | |
| CN104376548A (en) | Fast image splicing method based on improved SURF algorithm | |
| CN111462503B (en) | Vehicle speed measuring method and device and computer readable storage medium | |
| CN104766071B (en) | A kind of traffic lights fast algorithm of detecting applied to pilotless automobile | |
| CN105069801A (en) | Method for preprocessing video image based on image quality diagnosis | |
| CN110414385B (en) | Lane line detection method and system based on homography transformation and characteristic window | |
| CN110163039B (en) | Method, apparatus, storage medium, and processor for determining vehicle driving state | |
| CN112017445B (en) | Pedestrian violation prediction and motion trail tracking system and method | |
| CN112200742A (en) | Filtering and denoising method applied to edge detection | |
| CN104504703A (en) | Welding spot color image segmentation method based on chip element SMT (surface mounting technology) | |
| CN104700405A (en) | Foreground detection method and system | |
| Xiang et al. | Exemplar-based depth inpainting with arbitrary-shape patches and cross-modal matching | |
| CN110188640B (en) | Face recognition method, face recognition device, server and computer readable medium | |
| CN111652033A (en) | Lane line detection method based on OpenCV | |
| CN114241436A (en) | Lane line detection method and system for improving color space and search window | |
| CN111241911A (en) | Self-adaptive lane line detection method | |
| CN112926365A (en) | Lane line detection method and system | |
| JP2020095621A (en) | Image processing device and image processing method |
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 |