CN109635737A - Automobile navigation localization method is assisted based on pavement marker line visual identity - Google Patents

Automobile navigation localization method is assisted based on pavement marker line visual identity Download PDF

Info

Publication number
CN109635737A
CN109635737A CN201811523941.8A CN201811523941A CN109635737A CN 109635737 A CN109635737 A CN 109635737A CN 201811523941 A CN201811523941 A CN 201811523941A CN 109635737 A CN109635737 A CN 109635737A
Authority
CN
China
Prior art keywords
image
road
line
vehicle
pavement marker
Prior art date
Application number
CN201811523941.8A
Other languages
Chinese (zh)
Inventor
张绍成
周润楠
郭均然
Original Assignee
中国地质大学(武汉)
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中国地质大学(武汉) filed Critical 中国地质大学(武汉)
Priority to CN201811523941.8A priority Critical patent/CN109635737A/en
Publication of CN109635737A publication Critical patent/CN109635737A/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
    • G06K9/00791Recognising scenes perceived from the perspective of a land vehicle, e.g. recognising lanes, obstacles or traffic signs on road scenes
    • G06K9/00798Recognition of lanes or road borders, e.g. of lane markings, or recognition of driver's driving pattern in relation to lanes perceived from the vehicle; Analysis of car trajectory relative to detected road
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/36Input/output arrangements for on-board computers
    • G01C21/3602Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/20Image acquisition
    • G06K9/34Segmentation of touching or overlapping patterns in the image field
    • G06K9/342Cutting or merging image elements, e.g. region growing, watershed, clustering-based techniques

Abstract

The present invention provides one kind and assists automobile navigation localization method based on the visual identity of pavement marker line, this method comprises: obtaining the road color image in vehicle traveling in real time, is processed into gray level image;Binary conversion treatment is carried out to gray level image, obtains binary image;Denoising is carried out to binary image, obtains road image, the corresponding rectangle of every Road;Rectangular centre line is extracted, pavement marker line is obtained;The road information in vehicle position information and corresponding map database provided in conjunction with vehicle-mounted GNSS, determines lane where vehicle.Beneficial effects of the present invention: the present invention utilizes the algorithm of consumer level automobile data recorder image real-time perfoming road line drawing, and model is simple, be easily achieved and operation efficiency is high, is suitable for auxiliary vehicle real time navigation location data processing;Algorithm takes dynamic threshold to carry out image procossing, can have preferable Road extraction effect under the poor environment of illumination condition, to finally realize lane grade navigator fix.

Description

Automobile navigation localization method is assisted based on pavement marker line visual identity

Technical field

The present invention relates to auto navigation positioning fields, more particularly to one kind to assist vehicle based on the visual identity of pavement marker line Navigation locating method.

Background technique

Precise position information in vehicle travel process is to realize that vehicle assistant drive even develops to determining for automatic Pilot One of qualitative factor, but in vehicle travel process, trees of the individual GNSS positioning signal vulnerable to runway both sides, high level The masking of building or refracted signal interference, positioning accuracy are confined to ten meters of magnitudes, are difficult to realize lane grade by GNSS signal Navigator fix is unable to satisfy the needs of Vehicular automatic driving.

It include at present the navigation of real-time map matching assistant GPS, GNSS/ work about the research for improving vehicle positioning and navigation precision Using LED location technology, automobile navigation based on 3G technology etc. in NS integrated navigation, tunnel environment, but the above method needs to install Extras realize, higher cost, it is difficult to it promotes and applies, and it is universal with vehicle driving recorder, visual information becomes Distinguish the important observational data in lane.

Summary of the invention

Automobile navigation localization method is assisted based on the visual identity of pavement marker line in view of this, the present invention provides one kind, Using the deflection angle at any point and the Road on monocular vision information extraction Road, can be used for assisting automobile navigation fixed Position.

The present invention provides a kind of based on pavement marker line visual identity auxiliary automobile navigation localization method, including following step It is rapid:

S1, in real time the road color image in the traveling of acquisition vehicle, handle the color image, obtain grayscale image Picture;

Further, the step S1 method particularly includes:

S11, it shoots to obtain the road color image in vehicle traveling using video camera;

S12, by Color Image Processing be gray level image, for shot by camera image m row n column pixel battle array in, Any point P (x, y), gray value are denoted as g (x, y).

S2, binary conversion treatment is carried out to the gray level image, obtains binary image;

Further, the step S2 method particularly includes:

S21, solve to obtain the parallel lines that main in-line direction is parallel in image according to the internal and external orientation of video camera Project chalaza, i.e. principal vanishing point;

S22, with the principal vanishing point that step S21 is obtained be with reference to determine image lower half portion;

S23, in step S22 determine image lower half portion in any point P (x, y), gray value be denoted as g (x, Y), when the gray value meets the following conditions:

In formulaL is that projection is wide, i.e. the collection of width that projects on photograph of pavement marker line It closes, 0.025 times of picturewide is taken to be used as Lmax, ε is an additional normal number, takes ε=5 to be advisable, D is to pass through illumination condition Obtained contrast threshold,

Then the gray value of the point P (x, y) is indicated with 255, it is 0 that its gray value is enabled if being unsatisfactory for, the figure constituted in this way As being binary image;

S24, for binary image obtained in step S23, determined and schemed according to the relative position of front cover and video camera The part of front cover, rejects this parts of images as in.

S3, denoising is carried out to the binary image, obtains road line image, the corresponding square of every Road Shape;

Further, the step S3 method particularly includes:

S31, the binary image obtained to step S2 detect each piece of segment and extract its boundary;

S32, the feature modeling segment area according to extraction, the segment less than critical value is considered noise and filters out, critical Value Smin=0.00015mn, m are the corresponding number of lines of pixels of road color image, and n is the corresponding pixel of road color image Columns;

S33, adjacent white pixel point is considered as the point on same segment, is wrapped up segment with a smallest rectangle Come, replaces segment to be handled with this rectangle;

S34, straight line by mistake rectangle midpoint and along the long side direction are regarded as the projection of the center line of Road, and algorithm will meet The graphic blocks identifying that the rectangle of following two condition is replaced is Road:

(1) rectangular centre line inclination angle is between 10 to 70 degree (either between 70 to 10 degree) or vertically and in image The heart;

(2) rectangular aspect ratio is greater than 2.

The center line of S4, rectangle in extraction step S3, obtain pavement marker line;

Further, in step S4 rectangular centre line calculation formula are as follows:

Y=tan α (x-x0)+y0

α is the angle of rectangle long side and x-axis, x in formula0、y0It is rectangular centre point.

S5, according to the pavement marker line extracted in step S4, in conjunction with the vehicle-mounted GNSS vehicle position information provided and phase The road information in map data base is answered, determines lane where vehicle.

Further, the step S5 method particularly includes:

S51, the vehicle coordinate information provided by vehicle-mounted GNSS extract the road letter of corresponding position from map data base Breath, lane quantity, the quasi- transmits information in each lane including road;

S52, according to the pavement marker line extracted in step S4, the road information in step S51 is compared, where determining vehicle Specific lane information, auxiliary automobile navigation positioning.

Technical solution provided by the invention has the benefit that the present invention is real using consumer level automobile data recorder image The algorithm of Shi Jinhang road line drawing, model is simple, be easily achieved and operation efficiency is high, is suitable for auxiliary vehicle real time navigation Location data processing;Algorithm take dynamic threshold carry out image procossing, can have under the poor environment of illumination condition compared with Good Road extraction effect, the final lane grade navigator fix service realized to driving vehicle.

Detailed description of the invention

Fig. 1 is a kind of method flow schematic diagram of pavement marker line drawing provided in an embodiment of the present invention;

Fig. 2 be a vehicle driving provided in an embodiment of the present invention on highway with the photo of driver's viewing angles through locating Gray scale schematic diagram after reason;

Fig. 3 is that the relative position provided in an embodiment of the present invention according to front cover and video camera determines front cover in image Simultaneously reject the effect picture after this parts of images in part;

Fig. 4 is the schematic diagram provided in an embodiment of the present invention that figure spot is replaced using a minimum rectangle;

Fig. 5 is the projective distribution schematic diagram of Road provided in an embodiment of the present invention;

Fig. 6 is the comparison diagram of road line drawing figure provided in an embodiment of the present invention and former gray-value image;

Fig. 7 is the relation schematic diagram of Road mathematic(al) representation and corresponding rectangle provided in an embodiment of the present invention;

Road extraction process figure when Fig. 8 is certain driving at night provided in an embodiment of the present invention;

The equation parameter exemplary diagram of Fig. 9 extracted Road when being certain driving at night provided in an embodiment of the present invention;

Road line drawing exemplary diagram when Figure 10 is certain overhead driving provided in an embodiment of the present invention;

Road line drawing exemplary diagram when Figure 11 is certain highway driving provided in an embodiment of the present invention;

Figure 12 determines lane information exemplary diagram where vehicle when being certain driving at night provided in an embodiment of the present invention.

Specific embodiment

To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention Formula is further described.It should be appreciated that described herein, specific examples are only used to explain the present invention, is not used to limit The present invention.

The embodiment of the present invention selects vehicle photo captured by consumer level automobile data recorder in driving process on highway, Its process is as shown in Figure 1, include the following steps:

S1, obtained in real time using consumer level automobile data recorder vehicle advance in road color image, to the cromogram As being handled, gray level image is obtained;

The reason is that grayscale image can take into account the image recognition under day and night different illumination conditions, treated Gray level image as shown in Fig. 2, for image captured by automobile data recorder m row n column pixel battle array in any point P (x, y), Gray value is denoted as g (x, y).

S2, binary conversion treatment is carried out to the gray level image, obtains binary image;

Solve to obtain the projection that the parallel lines of main in-line direction are parallel in image according to the internal and external orientation of video camera Chalaza, i.e. principal vanishing point.It is with reference to the lower half portion for determining image with the principal vanishing point;

The reason is that principal vanishing point is principal point, and the point on all ground for the image perpendicular to floor Projection all should be in the point hereinafter, it is known that the projection of Road on all ground is all in the lower half portion of image.

The lane of vehicle driving is usually dark (gray value is small), and the Road on road surface is usually white or yellow (gray value is big) of color, therefore all darker and intermediate brighter lines in two sides that meets are likely to be Road.Thereby determine that into The threshold condition of row binaryzation: for any point P (x, y) in image lower half portion, gray value is denoted as g (x, y), when the point Gray value meets the following conditions:

In formulaL is that projection is wide, i.e. the collection of width that projects on photograph of pavement marker line It closes, 0.025 times of picturewide is taken to be used as L after testedmax, ε is an additional normal number, takes ε=5 to be advisable after tested, D is The contrast threshold obtained by illumination condition,It should be noted that using 5 as D most The limitation of small value, its object is in order to guarantee therefore the bad region of illumination condition will not generate much noise;

Then the gray value is indicated with 255, otherwise its gray value is indicated with 0, thus exports binary image.

It should be noted that finding that generation is reflective at front cover, since glistening intensity is excessively high when handling single image It is and related with weather at that time, it is difficult to be effectively removed by denoising means.Therefore to above-mentioned binary image, according to front cover with take the photograph The relative position of camera determines the part of front cover in image, skips over the image procossing of this part, and effect is as shown in Figure 3.

S3, denoising is carried out to the binary image, obtains road line image, the corresponding square of every Road Shape;

For the binary image that step S2 is obtained, detects each piece of segment and extract its boundary;

Noise exists in the form of fleck under normal conditions, and Road is then the regular figure of strip, and approximate In rectangle.According to the feature modeling segment area of extraction, the segment less than critical value is considered noise and filters out, critical value Smin =0.00015.mn, m are the corresponding number of lines of pixels of road color image, and n is the columns of the corresponding pixel of road color image;

There is the shade of roadside tress or railing on road surface, Road also will appear the place covered by shade, will lead to There is black dot in the white segment of the binary image of Road, is unfavorable for the direction interpretation of Road.Therefore it needs to extract Segment boundary node, is considered as the point on same segment for adjacent white pixel point, is wrapped up segment with a smallest rectangle Get up, replace segment to be handled with this rectangle, as shown in figure 4, white segment is the segment after binaryzation, white rectangle is The minimum rectangle that may include entire segment replaces the segment with the rectangle, can accurately and easily obtain the several several of segment What parameter;

By rectangle midpoint excessively and straight line along the long side direction is regarded as the projection of the center line of Road, by the base of central projection Present principles it is found that the projection of Road will not be horizontal, and only can be in the Road of image center it is vertical, such as Fig. 5 It is shown.Therefore, by inclination angle between 10 to 70 degree the line of (or 70 to 10 degree between) and vertical and in picture centre Line is identified as Road;

It should be noted that also needing to limit the length of segment, Road has elongated characteristic, can be different from water The noises such as pool, road sign, therefore the length-width ratio for representing the rectangle of Road should also be greater than 2;

Image after above-mentioned denoising process is the extracted road line image of the present embodiment, as shown in fig. 6, being road The comparison for extracting figure with former gray-value image, it can be found that the Road within the scope of pilot's line of vision is accurately extracted.

The center line of S4, rectangle in extraction step S3, obtain pavement marker line;

Since the accuracy requirement of automobile navigation positioning does not reach Centimeter Level, the width in lane can be ignored not Meter, is regarded as the straight line of not width, can directly calculate rectangular centre line as Road projection image expression formula:

Y=tan α (x-x0)+y0

α is the angle of rectangle long side and x-axis, x in formula0、y0It is rectangular centre point, as shown in fig. 7, Road mathematical expression The relation schematic diagram of formula and corresponding rectangle.

The present embodiment is using automobile data recorder institute's recorded video under multiple and different road conditions, different illumination conditions as research Data are tested, and consider that the resolution ratio of different brands automobile data recorder institute recorded video is different, difference regards when to ensure to test Frequency extracted data are comparable, and video resolution is unified for 320*480,29.97 frame of video number of pictures per second.

The scene that the present embodiment chooses three inclement conditions common in daily driving carries out road road sign using above-mentioned steps Remember line drawing test:

(1) when certain driving at night Road extraction process image as shown in figure 8, current driving lane be 4 lane roads, should Driving direction is two lanes, has 3 Roads, and road conditions are good, and no a large amount of vehicles stop.The upper left corner is automobile data recorder in figure The grayscale image of video pictures after processing is shot, the lower left corner is binary image, and the lower right corner is that the Road after being disposed mentions It wins the confidence breath, the upper right corner is the Road extracted and the comparison of original image.As can be seen that algorithm extracts 3 Roads altogether, it will be current Road in video camera coverage all extracts, and the equation parameter of extracted Road is as shown in figure 9, with Road center The orientation for indicating Road is put with inclination angle;

(2) road line drawing image is as shown in Figure 10 when certain overhead driving, and current crossing is more broad, land mark line by It is darker in abrasion color.As can be seen that algorithm is extracted Road, but the Road in lane farther out can not be identified, due to algorithm The limitation of binarization method, or abrasion more serious region darker for color, Road identification have difficulties;

(3) road line drawing image is as shown in figure 11 when certain highway driving, and present road line is clear but has vehicle interference.It can To find out that algorithm is extracted 3 Roads in right side, not missing because of vehicle interference by vehicle discriminating is Road.

S5, according to the pavement marker line extracted in step S4, in conjunction with the vehicle-mounted GNSS vehicle position information provided and phase The road information in map data base is answered, determines lane where vehicle.

Specifically, the vehicle coordinate information provided according to vehicle-mounted GNSS extracts the road of corresponding position from map data base Road information, lane quantity, the quasi- transmits information in each lane including road.According to the pavement marker line extracted in step S4, The road information is compared again, as shown in figure 12, the exemplary diagram of the specific lane information where vehicle is determined when being driving at night, Finally automobile navigation is assisted to position using determining specific lane information.

The present embodiment is by testing the road surface Road identification under different situations, it can be seen that this method adapts to The illumination condition on daytime and night has a higher resistance for the interference of the factors such as vehicle, but Road is shallower or ground When being printed on text homochromy with Road, the road line drawing of this method will receive interference.

The monocular video using vehicle travel process middle rolling car recorder is present embodiments provided, Road is extracted Algorithm, algorithm is fast and effective, has a real-time resolving ability, and the quantitative information for the pavement marker line that algorithm extracts is in follow-up work In, it can be applied to carry out in data fusion positioning resolving with GNSS observation signal.

It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program Program product.Therefore, hardware embodiment, software implementation or embodiment combining software and hardware aspects can be used in the present invention Form.It can be used moreover, the present invention can be used in the computer that one or more wherein includes computer usable program code The form for the computer program product implemented on storage medium (including but not limited to magnetic disk storage and optical memory etc.).

The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.

These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.

The foregoing is only a preferred embodiment of the present invention, is not intended to limit the scope of the present invention.

Claims (8)

1. one kind assists automobile navigation localization method based on the visual identity of pavement marker line, which comprises the steps of:
S1, in real time the road color image in the traveling of acquisition vehicle, handle the color image, obtain gray level image;
S2, binary conversion treatment is carried out to the gray level image, obtains binary image;
S3, denoising is carried out to the binary image, obtains road line image, the corresponding rectangle of every Road;
The center line of S4, rectangle in extraction step S3, obtain pavement marker line.
S5, according to the pavement marker line extracted in step S4, in conjunction with the vehicle-mounted GNSS vehicle position information provided and correspondingly Road information in chart database determines lane where vehicle.
2. according to claim 1 assist automobile navigation localization method based on the visual identity of pavement marker line, feature exists In, in step S1, using video camera shoot to obtain vehicle advance in road color image.
3. according to claim 1 assist automobile navigation localization method based on the visual identity of pavement marker line, feature exists In solving to obtain the parallel lines for being parallel to main in-line direction in image according to the internal and external orientation of video camera in step S2 Chalaza is projected, is with reference to the lower half portion for determining image with the projection chalaza.
4. according to claim 1 assist automobile navigation localization method based on the visual identity of pavement marker line, feature exists In in step S2, to the process of gray level image progress binaryzation are as follows: set the gray value of any point P (x, y) in gray level image For g (x, y), point P (x, y) is in the lower half portion of image and gray value g (x, y) meets the following conditions:
In formula,M is the line number of the corresponding pixel of road color image, and L is that projection is wide, and ε takes 5, D It is the contrast threshold obtained by illumination condition,
The image that then point P (x, y) is constituted is binary image.
5. according to claim 1 assist automobile navigation localization method based on the visual identity of pavement marker line, feature exists In in step S2, according to the relative position of front cover and video camera, determining the part of front cover in binary image, reject institute State the image of Chinese herbaceous peony cover.
6. according to claim 1 assist automobile navigation localization method based on the visual identity of pavement marker line, feature exists In in step S3, by screening segment area and segment shape to binary image progress denoising, detailed process are as follows:
S31, screening segment area, the critical value of segment area are as follows: Smin=0.00015mn, in formula, SminFor segment area Minimum value, m is the corresponding number of lines of pixels of road color image, and n is the columns of the corresponding pixel of road color image, and area is small In critical value segment as noise filtering;
S32, segment boundary node is extracted, segment is wrapped up with a rectangle, replaces segment to be handled with this rectangle;
S33, straight line by mistake rectangle midpoint and along the long side direction are regarded as the projection of the center line of Road, and algorithm will meet following The graphic blocks identifying that the rectangle of two conditions is replaced is Road:
(1) rectangular centre line inclination angle is between 10 to 70 degree (either between -70 to -10 degree) or vertically and in image The heart;
(2) rectangular aspect ratio is greater than 2.
7. according to claim 1 assist automobile navigation localization method based on the visual identity of pavement marker line, feature exists In, in step S4, the calculation formula of rectangular centre line are as follows:
Y=tan α (x-x0)+y0
α is the angle of rectangle long side and x-axis, x in formula0、y0It is rectangular centre point.
8. according to claim 1 assist automobile navigation localization method based on the visual identity of pavement marker line, feature exists In the detailed process of step S5 are as follows:
S51, the vehicle coordinate information provided according to vehicle-mounted GNSS, extract the road information of corresponding position from map data base, Lane quantity, the quasi- transmits information in each lane including road;
S52, according to the pavement marker line extracted in step S4, compare the road information in step S51, determine the tool where vehicle Body lane information, auxiliary automobile navigation positioning.
CN201811523941.8A 2018-12-12 2018-12-12 Automobile navigation localization method is assisted based on pavement marker line visual identity CN109635737A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811523941.8A CN109635737A (en) 2018-12-12 2018-12-12 Automobile navigation localization method is assisted based on pavement marker line visual identity

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811523941.8A CN109635737A (en) 2018-12-12 2018-12-12 Automobile navigation localization method is assisted based on pavement marker line visual identity

Publications (1)

Publication Number Publication Date
CN109635737A true CN109635737A (en) 2019-04-16

Family

ID=66073454

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811523941.8A CN109635737A (en) 2018-12-12 2018-12-12 Automobile navigation localization method is assisted based on pavement marker line visual identity

Country Status (1)

Country Link
CN (1) CN109635737A (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101032405A (en) * 2007-03-21 2007-09-12 汤一平 Safe driving auxiliary device based on omnidirectional computer vision
JP2009240683A (en) * 2008-03-31 2009-10-22 Electronic Navigation Research Institute Driver sleepiness detector
CN102314599A (en) * 2011-10-11 2012-01-11 东华大学 Identification and deviation-detection method for lane
CN103389733A (en) * 2013-08-02 2013-11-13 重庆市科学技术研究院 Vehicle line walking method and system based on machine vision
CN104392212A (en) * 2014-11-14 2015-03-04 北京工业大学 Method for detecting road information and identifying forward vehicles based on vision
CN105674992A (en) * 2014-11-20 2016-06-15 高德软件有限公司 Navigation method and apparatus
CN105678285A (en) * 2016-02-18 2016-06-15 北京大学深圳研究生院 Adaptive road aerial view transformation method and road lane detection method
US20170052031A1 (en) * 2012-06-08 2017-02-23 Apple Inc. Determining Location and Direction of Travel Using Map Vector Constraints
CN106919915A (en) * 2017-02-22 2017-07-04 武汉极目智能技术有限公司 Map road mark and road quality harvester and method based on ADAS systems
CN107862290A (en) * 2017-11-10 2018-03-30 智车优行科技(北京)有限公司 Method for detecting lane lines and system
CN108205667A (en) * 2018-03-14 2018-06-26 海信集团有限公司 Method for detecting lane lines and device, lane detection terminal, storage medium

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101032405A (en) * 2007-03-21 2007-09-12 汤一平 Safe driving auxiliary device based on omnidirectional computer vision
JP2009240683A (en) * 2008-03-31 2009-10-22 Electronic Navigation Research Institute Driver sleepiness detector
CN102314599A (en) * 2011-10-11 2012-01-11 东华大学 Identification and deviation-detection method for lane
US20170052031A1 (en) * 2012-06-08 2017-02-23 Apple Inc. Determining Location and Direction of Travel Using Map Vector Constraints
CN103389733A (en) * 2013-08-02 2013-11-13 重庆市科学技术研究院 Vehicle line walking method and system based on machine vision
CN104392212A (en) * 2014-11-14 2015-03-04 北京工业大学 Method for detecting road information and identifying forward vehicles based on vision
CN105674992A (en) * 2014-11-20 2016-06-15 高德软件有限公司 Navigation method and apparatus
CN105678285A (en) * 2016-02-18 2016-06-15 北京大学深圳研究生院 Adaptive road aerial view transformation method and road lane detection method
CN106919915A (en) * 2017-02-22 2017-07-04 武汉极目智能技术有限公司 Map road mark and road quality harvester and method based on ADAS systems
CN107862290A (en) * 2017-11-10 2018-03-30 智车优行科技(北京)有限公司 Method for detecting lane lines and system
CN108205667A (en) * 2018-03-14 2018-06-26 海信集团有限公司 Method for detecting lane lines and device, lane detection terminal, storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
XINXIN DU.ET.: "Vision-based approach towards lane line detection and vehicle localization", 《MACHINE VISION AND APPLICATIONS》 *
詹海浪: "基于计算机视觉的车道线检测与交通路标识别", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Similar Documents

Publication Publication Date Title
CN105260699B (en) A kind of processing method and processing device of lane line data
US20200173803A1 (en) Vision augmented navigation
Son et al. Real-time illumination invariant lane detection for lane departure warning system
Yoo et al. Gradient-enhancing conversion for illumination-robust lane detection
Guan et al. Automated road information extraction from mobile laser scanning data
Borkar et al. A novel lane detection system with efficient ground truth generation
JP5892876B2 (en) In-vehicle environment recognition system
CN104318258B (en) Time domain fuzzy and kalman filter-based lane detection method
Borkar et al. Robust lane detection and tracking with ransac and kalman filter
EP2879110B1 (en) Three-dimensional object detection device, and three-dimensional object detection method
US10776635B2 (en) Monocular cued detection of three-dimensional structures from depth images
CN103714538B (en) road edge detection method, device and vehicle
US8750567B2 (en) Road structure detection and tracking
Li et al. Springrobot: A prototype autonomous vehicle and its algorithms for lane detection
US8818026B2 (en) Object recognition device and object recognition method
US9384401B2 (en) Method for fog detection
JP5867596B2 (en) Three-dimensional object detection apparatus and three-dimensional object detection method
US8121350B2 (en) Apparatus, method and computer program for determining a position on the basis of a camera image from a camera
CN101334836B (en) License plate positioning method incorporating color, size and texture characteristic
Guo et al. Robust road detection and tracking in challenging scenarios based on Markov random fields with unsupervised learning
US20140236463A1 (en) Enhanced clear path detection in the presence of traffic infrastructure indicator
CN102682292B (en) Method based on monocular vision for detecting and roughly positioning edge of road
US7957559B2 (en) Apparatus and system for recognizing environment surrounding vehicle
KR100317790B1 (en) Lane area extractor and method thereof
US9269001B2 (en) Illumination invariant and robust apparatus and method for detecting and recognizing various traffic signs

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