CN104850834A - Road boundary detection method based on three-dimensional laser radar - Google Patents
Road boundary detection method based on three-dimensional laser radar Download PDFInfo
- Publication number
- CN104850834A CN104850834A CN201510237014.XA CN201510237014A CN104850834A CN 104850834 A CN104850834 A CN 104850834A CN 201510237014 A CN201510237014 A CN 201510237014A CN 104850834 A CN104850834 A CN 104850834A
- Authority
- CN
- China
- Prior art keywords
- road
- value
- barrier
- point
- distance
- 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.)
- Pending
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)
Abstract
The present invention discloses a road boundary detection method based on a three-dimensional laser radar. In the process of intelligent vehicle driving, point cloud data collected by a vehicle-mounted three-dimensional laser radar is subjected to rasterizing processing to generate a binary raster graphic. The binary raster graphic is subjected to a distance conversion operation to obtain a distance grey-scale map, a filing distance is smaller than the narrow space between obstacle points of certain thresholds, the overall contour of the obstacle points is not changed, and an obstacle area contour map is obtained. A region growing method is used, with the position of an intelligent vehicle as a start point, the region growing is carried out forward, the passable area contour map of a road is obtained, and combined with the original binary raster graphic, a road area contour map is obtained. The contours of two sides of the road area contour map are extracted, the second function fitting is carried out, and a road boundary is obtained. The method is applicable to an urban road, a rural road and other roads, the influence of obstacles on a detection effect is small, the time complexity is low, the real-time processing is achieved, day and night work is achieved, and the algorithm robustness is good.
Description
Technical field:
The present invention relates generally to intelligent vehicle environment sensing field, particularly relates to a kind of intelligent vehicle that is applied to and independently travels or the road boundary real-time detection method based on three-dimensional laser radar of auxiliary travelling.
Background technology:
One of intelligent vehicle autonomous driving or auxiliary prerequisite of driving fast and effeciently will detect road area exactly.The current research major part about Road Detection is carried out based on image or radar.Picture showing be the most direct color and texture information, and having good continuity between pixel, therefore based on the research of the road edge identification of image, is carry out according to the feature of road boundary mostly.But the shortcoming of image is also clearly, Detection results is comparatively large by the interference of the factor such as light intensity, road surface material, and the limited view of camera.The data reflection of radar be the dense degree of periphery barrier, have higher precision to detection barrier, its shortcoming also clearly, only has range information, and is a kind of discrete message, the impact of the thing that is easily interfered.
By CN201110002490 " Method for Road Boundary Detection based on infrared image ", a kind of known method detecting road boundary, to the infrared image gathered, the straight-line segment that the fusion threshold value method of exhaustion and Second Order Differential Operator method obtain, complete the extraction of boundary sections, finally can accurately find out the road boundary in infrared image.
By CN201110150818 " a kind of SVM is combined the method detecting unstructured road border with laser radar ", a kind of known method detecting road boundary, the data of three-dimensional laser radar are processed into grid map, then by clustering algorithm, road barrier is on both sides of the road divided into two classes, re-use SVM training and obtain lineoid, thus determine the direction of road, finally ask for the straight-line equation of road boundary.
The method mentioned in above-mentioned two patents is all only applicable to road does not have the situation of the barriers such as vehicle, and CN201110002490 is only for structured road, and for unstructured road, this method receives certain restriction; CN201110150818 requires that the data of grid map can obviously be divided into two classes, therefore cannot be applicable to narrower backroad.
Summary of the invention:
For road existing the difficult point such as obstacle and unstructured road, the invention provides a kind of Method for Road Boundary Detection based on three-dimensional laser radar, road boundary can be detected fast and accurately, for autonomous traveling or the auxiliary travelling of intelligent vehicle.
The present invention is achieved by the following technical solutions:
Based on the Method for Road Boundary Detection of three-dimensional laser radar, it is characterized in that, include following steps:
Step 1, utilizes the cloud data of three-dimensional laser radar collection maximin method to project and generates two-value grid map;
Step 2, carries out range conversion operation to two-value grid map, and the filling distance is less than the small space between the barrier point of certain threshold value, obtains barrier zone profile diagram;
Step 3, uses region-growing method to barrier zone profile diagram, obtains pavement of road region contour figure;
Step 4, extracts the profile of pavement of road region contour figure both sides, carries out quadratic function matching, obtain final road boundary figure.
Based on the Method for Road Boundary Detection of three-dimensional laser radar, it is characterized in that, in described step 1, the concrete grammar being generated two-value grid map by projection is:
Step 1.1, the cloud data of three-dimensional laser radar collection is divided in surface level a series of squares that the length of side is 0.2m, and these squares are mapped in two-value grid map one by one, keep the position relationship of square in cloud data consistent with the position relationship in two-value grid map, and set the scope of total grid number;
Step 1.2, generates two-value grid map with the projection of maximin method.Calculate the maximum height value of the cloud data corresponding to each grid in two-value grid map and the difference of minimum height values, if this difference is greater than the threshold value of setting, just arranging this grid is barrier point, be labeled as 1, otherwise be non-barrier point, be labeled as 0, obtain two-value grid map, black color dots is barrier point, and white point is non-barrier point.
Based on the Method for Road Boundary Detection of three-dimensional laser radar, it is characterized in that, described step 2 comprises the following steps:
Step 2.1, generate distance gray scale figure: utilize range conversion method to obtain in two-value grid map non-barrier point to from the distance between its nearest barrier point, as the gray-scale value of these corresponding point in distance gray scale figure, and remember that the gray-scale value of barrier point corresponding point in distance gray scale figure is 0, obtain the distance gray scale figure that two-value grid map is corresponding;
Step 2.2, is less than the point of certain threshold value T as barrier point using gray-scale value in distance gray scale figure, other point obtains barrier zone profile diagram as non-barrier point.Barrier zone profile diagram is filled with the small space between barrier data that distance is less than threshold value T.
Based on the Method for Road Boundary Detection of three-dimensional laser radar, it is characterized in that, in described step 2.1, the acquisition of distance gray scale figure comprises the steps:
Step 2.1.1, chooses template: be approximately 2:1 according to the vehicle commander of intelligent vehicle and the ratio of overall width, choose the template of 3*3, wherein the center of template is 0, the top of template center be 2 below, the left side of template center and the right are 1, four angles is 100;
Step 2.1.2, the size of initialization distance gray scale figure: distance gray scale figure is consistent with two-value grid map, for each pixel in distance gray scale figure, if the value of the grid that this pixel is corresponding in two-value grid map is 1, the pixel value then arranging this pixel is 0, otherwise the pixel value arranging this pixel is 100;
Step 2.1.3, upgrades distance gray scale figure: carry out computing by each pixel in the distance gray scale figure after the template chosen and initialization, obtain final distance gray scale figure.
Based on the Method for Road Boundary Detection of three-dimensional laser radar, it is characterized in that, described step 3 is further comprising the steps:
Step 3.1, using the position of intelligent vehicle as the starting point of region growing, the terminal using barrier point as growth branch, adopts from bottom to top, from middle toward the mode of both sides growth, and what obtain road can traffic areas;
Step 3.2, asking for this can the outline of traffic areas, is preserved by profile with chain code form, forms a closed space;
Step 3.3, the barrier point extracted in initial two-value grid map in this enclosure space carries out cluster, and each barrier class of acquisition is the practical obstacle thing on road;
Step 3.4, road can all barrier classes on traffic areas and road, constitute the region, road surface of road, and finally obtain pavement of road region contour figure.
Based on the Method for Road Boundary Detection of three-dimensional laser radar, it is characterized in that, described step 4 is further comprising the steps:
Step 4.1, the selected scope needing the road boundary detected, asks for right boundary, and is revised by right boundary within the scope of this from pavement of road region contour figure, and left margin moves to left threshold value T, and right margin moves to right threshold value T, and threshold value T is defined by step 2.2;
Step 4.2, carries out quadratic function matching to right boundary respectively, obtains smooth road boundary figure.
Advantage of the present invention is:
Compared with prior art, its remarkable advantage is in the present invention: (1) this method is applicable to the various road conditions such as urban road, backroad, cross-country road; (2) effectively can filter the barriers such as the vehicle on road, Detection results affects little by barrier; (3) time complexity is low, can process in real time, and algorithm only just detects road boundary with a range conversion and a region growing; (4) can work double tides, Algorithm robustness is better.
Accompanying drawing illustrates:
Fig. 1 is the process flow diagram of the Method for Road Boundary Detection based on three-dimensional laser radar of the present invention.
Fig. 2 is two-value grid illustration of the present invention.
Fig. 3 is the barrier zone profile illustration obtained after range conversion process of the present invention.
Fig. 4 be of the present invention obtain after region-growing method process can traffic areas profile illustration.
Fig. 5 is the barrier profile illustration on the road of extraction of the present invention.
Fig. 6 is pavement of road region contour illustration of the present invention.
Fig. 7 is the smooth road boundary illustration after quadratic function matching of the present invention.
Embodiment:
Below in conjunction with embodiment, the present invention is described in further detail:
Based on the Method for Road Boundary Detection of three-dimensional laser radar, be specially:
Step 1, the cloud data projection gathered by three-dimensional laser radar generates two-value grid map;
Step 1.1, by the data transformation of three-dimensional laser radar acquisition to bodywork reference frame, the three-dimensional data points P under radar fix system
vwith the some P under bodywork reference frame
ctransforming relationship be P
c=P
vr+t, wherein R and t is the outer ginseng obtained after demarcating.
Step 1.2, first 82.4 meters of bodywork reference frame initial point, within the scope of the rectangle of rear 20 meters and each 51.2 meters of left and right, cloud data is divided into a series of little square that the length of side is 0.2m, a square is a grid, obtain 512*512 grid, wherein the initial point of bodywork reference frame is in (256,412);
Step 1.3, calculates the maximum height value of the cloud data in each grid and the difference of minimum height values, if this difference is greater than the threshold value of setting, just arranging this grid is barrier point, is labeled as 1, otherwise is non-barrier point, is labeled as 0.Fig. 2 is the two-value grid map of the barrier adopting maximin method to obtain, and black color dots is barrier point, and white point is non-barrier point.
Step 2, carries out range conversion operation to two-value grid map, and the filling distance is less than the small space between the barrier point of certain threshold value, obtains barrier zone profile diagram.
Step 2.1, chooses the template calculating distance gray scale figure.One is of a size of can expressing by the matrix M (k, l) of a n × n for the template calculating range conversion of n × n, and wherein k, l represent row and the row of matrix M respectively, and wherein the value of each element represents pixel p=(x
p, y
p) and its adjacent pixels q=(x
p+ k, y
p+ 1) local distance between, wherein x
pwith y
pbe respectively the transverse and longitudinal coordinate of pixel p.General template centered by pixel p, institute
With size n for odd number, subscript k and l is included in-[n/Z] ..., [n/Z] } in.Approximate according to the ratio of the vehicle commander of intelligent vehicle and overall width is 2:1, therefore chooses the template of 3*3, and wherein the center of template is 0, the top of template center be 2 below, the left side of template center and the right are 1, four angles is 100.
Step 2.2: calculate distance gray scale figure.The border set B of two-value grid map to be value be 1 set, its distance gray scale figure is one and is of a size of 512*512, is worth the matrix for DT (p).First, initialization distance gray scale figure:
then, when iterations t > 0, by template M (k, l), pixel p=(x is placed on
p, y
p) place, and with regular
<math><math display = 'block'> <mrow> <msup> <mi>DT</mi> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </msup> <mrow> <mo>(</mo> <mi>p</mi> <mo>)</mo> </mrow> <mo>=</mo> <munder> <mi>min</mi> <mrow> <mi>k</mi> <mo>,</mo> <mi>l</mi> </mrow> </munder> <mo>{</mo> <msup> <mi>DT</mi> <mrow> <mo>(</mo> <mi>t</mi> <mo>&minus;</mo> <mn>1</mn> <mo>)</mo> </mrow> </msup> <mrow> <mo>(</mo> <mi>q</mi> <mo>)</mo> </mrow> <mo>&plus;</mo> <mi>M</mi> <mrow> <mo>(</mo> <mi>k</mi> <mo>,</mo> <mi>l</mi> <mo>)</mo> </mrow> <mo>;</mo> <mi>q</mi> <mo>=</mo> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mi>p</mi> </msub> <mo>&plus;</mo> <mi>k</mi> <mo>,</mo> <msub> <mi>y</mi> <mi>p</mi> </msub> <mo>&plus;</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>}</mo> </mrow></math> By distance value from pixel q=(x
p+ k, y
p+ 1) propagate into p, this renewal process no longer changes continuing to proceed to distance gray scale figure and stops.The implication of above-mentioned each variable is identical with step 2.1.
Step 2.3, considers the width of intelligent car body, can think that between two barriers that interval is less than certain distance (under normal circumstances about 1.8 meters) be impassability, therefore can fill with barrier between these two barriers.Based on this thought, pixel value in distance gray scale figure is less than the point (be equivalent to this and be less than 1.8 meters from nearest obstacle object point) of 9 as barrier point, other point as non-barrier point, acquired disturbance areal map.Barrier zone totem culture two-value grid map middle distance is less than the small space between the barrier data of 9 pixels.Finally extract the profile of this barrier zone figure, obtain barrier zone profile diagram, as shown in Figure 3.
Step 3, uses region-growing method to barrier zone profile diagram, obtains pavement of road region contour figure.
Step 3.1, with the region-growing method improved try to achieve road can traffic areas.First, selected seed point.The coordinate points of position in barrier zone profile diagram at intelligent vehicle center is (256,412), and without other barrier in the adjacent domain of this point, namely pixel value is all 0.Therefore, can choose this point is Seed Points.Secondly, area-of-interest is chosen.Choose the region in first 70 meters of car herein.That is, the region in barrier zone profile diagram is from 412 row to 50 row.Then, up carry out by following growth step, obtain road area forward: (1) creates a stack, and sub pixel S is put into stack; (2) if stack top element is at 100 row, then give up this element, if stack is empty, then stop growing, otherwise continue step below.(3) take out stack top element, about judging it, whether upper 3 neighborhood territory pixel points have pixel value to be 0, if having, then its F are set to 1, and join in stack, then turn (2).Fig. 4 be use improve region-growing method after obtain road can traffic areas profile illustration.
Step 3.2, asking for this can the outline of traffic areas, outline is preserved with chain code form, form a closed space, and the barrier point extracted in this enclosure space carries out cluster in initial two-value grid map, each barrier class of acquisition is the barrier on road, finally extracts the profile of each barrier class, obtain barrier profile diagram, as shown in Figure 5;
Step 3.3, road can traffic areas reflection be the region that on road, unmanned vehicle can travel, namely road removes the region of barrier, therefore road all barrier classes on traffic areas and road can constitute the region, road surface of road.Fig. 6 is pavement of road region contour illustration.
Step 4, extracts the profile of pavement of road region contour figure both sides, carries out quadratic function matching.
Step 4.1, extracts the profile of pavement of road region contour figure both sides.First, choose area-of-interest, choose the region (all pixels from 412 row to 100 row in corresponding pavement of road region contour figure) in first 60 meters of car herein.Then, right boundary is asked for from the region, road surface of road, concrete method for solving is, 412 row in pavement of road region contour figure are operated line by line to 100 row, Far Left and rightmost point is found out from often go, leftmost point is as the point of left margin, and rightmost point is as the point of right margin.Finally, revise right boundary, because in step 2 the profile of barrier is expanded 9 pixels, therefore, left margin needs 9 pixels that move to left, and right margin needs 9 pixels that move to right;
Step 4.2, carries out quadratic function matching to right boundary.Choose the Seed Points of right boundary, adopt the mode that dot interlace is chosen here, namely choose a point every five points, obtain the point range of right boundary respectively.Again respectively quadratic function matching is carried out to the point range of right boundary, obtain smooth road boundary, as Fig. 7.This lane boundary line indicates the direction of road, and is opened in region, road surface and non-road surface region segmentation.
Non-elaborated part of the present invention belongs to the known technology of those skilled in the art.
Claims (8)
1. based on the Method for Road Boundary Detection of three-dimensional laser radar, it is characterized in that, include following steps:
Step 1, utilizes the cloud data of three-dimensional laser radar collection maximin method to project and generates two-value grid map;
Step 2, carries out range conversion operation to two-value grid map, and the filling distance is less than the small space between the barrier point of certain threshold value, obtains barrier zone profile diagram;
Step 3, uses region-growing method to barrier zone profile diagram, obtains pavement of road region contour figure;
Step 4, extracts the profile of pavement of road region contour figure both sides, carries out quadratic function matching, obtain final road boundary figure.
2. the Method for Road Boundary Detection based on three-dimensional laser radar according to claim 1, is characterized in that, in described step 1, the concrete grammar being generated two-value grid map by projection is:
Step 1.1, the cloud data of three-dimensional laser radar collection is divided in surface level a series of squares that the length of side is 0.2m, and these squares are mapped in two-value grid map one by one, keep the position relationship of square in cloud data consistent with the position relationship in two-value grid map, and set the scope of total grid number;
Step 1.2, generates two-value grid map with the projection of maximin method.
3. calculate the maximum height value of the cloud data corresponding to each grid in two-value grid map and the difference of minimum height values, if this difference is greater than the threshold value of setting, just arranging this grid is barrier point, be labeled as 1, otherwise be non-barrier point, be labeled as 0, obtain two-value grid map, black color dots is barrier point, and white point is non-barrier point.
4. the Method for Road Boundary Detection based on three-dimensional laser radar according to claim 1, is characterized in that, described step 2 comprises the following steps:
Step 2.1, generate distance gray scale figure: utilize range conversion method to obtain in two-value grid map non-barrier point to from the distance between its nearest barrier point, as the gray-scale value of these corresponding point in distance gray scale figure, and remember that the gray-scale value of barrier point corresponding point in distance gray scale figure is 0, obtain the distance gray scale figure that two-value grid map is corresponding;
Step 2.2, is less than the point of certain threshold value T as barrier point using gray-scale value in distance gray scale figure, other point obtains barrier zone profile diagram as non-barrier point.
5. barrier zone profile diagram is filled with the small space between barrier data that distance is less than threshold value T.
6. the Method for Road Boundary Detection based on three-dimensional laser radar according to claim 3, is characterized in that, in described step 2.1, the acquisition of distance gray scale figure comprises the steps:
Step 2.1.1, chooses template: be approximately 2:1 according to the vehicle commander of intelligent vehicle and the ratio of overall width, choose the template of 3*3, wherein the center of template is 0, the top of template center be 2 below, the left side of template center and the right are 1, four angles is 100;
Step 2.1.2, the size of initialization distance gray scale figure: distance gray scale figure is consistent with two-value grid map, for each pixel in distance gray scale figure, if the value of the grid that this pixel is corresponding in two-value grid map is 1, the pixel value then arranging this pixel is 0, otherwise the pixel value arranging this pixel is 100;
Step 2.1.3, upgrades distance gray scale figure: carry out computing by each pixel in the distance gray scale figure after the template chosen and initialization, obtain final distance gray scale figure.
7. the Method for Road Boundary Detection based on three-dimensional laser radar according to claim 1, is characterized in that, described step 3 is further comprising the steps:
Step 3.1, using the position of intelligent vehicle as the starting point of region growing, the terminal using barrier point as growth branch, adopts from bottom to top, from middle toward the mode of both sides growth, and what obtain road can traffic areas;
Step 3.2, asking for this can the outline of traffic areas, is preserved by profile with chain code form, forms a closed space;
Step 3.3, the barrier point extracted in initial two-value grid map in this enclosure space carries out cluster, and each barrier class of acquisition is the practical obstacle thing on road;
Step 3.4, road can all barrier classes on traffic areas and road, constitute the region, road surface of road, and finally obtain pavement of road region contour figure.
8. the Method for Road Boundary Detection based on three-dimensional laser radar according to claim 1, is characterized in that, described step 4 is further comprising the steps:
Step 4.1, the selected scope needing the road boundary detected, asks for right boundary, and is revised by right boundary within the scope of this from pavement of road region contour figure, and left margin moves to left threshold value T, and right margin moves to right threshold value T, and threshold value T is defined by step 2.2;
Step 4.2, carries out quadratic function matching to right boundary respectively, obtains smooth road boundary figure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510237014.XA CN104850834A (en) | 2015-05-11 | 2015-05-11 | Road boundary detection method based on three-dimensional laser radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510237014.XA CN104850834A (en) | 2015-05-11 | 2015-05-11 | Road boundary detection method based on three-dimensional laser radar |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104850834A true CN104850834A (en) | 2015-08-19 |
Family
ID=53850469
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510237014.XA Pending CN104850834A (en) | 2015-05-11 | 2015-05-11 | Road boundary detection method based on three-dimensional laser radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104850834A (en) |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105448184A (en) * | 2015-11-13 | 2016-03-30 | 北京百度网讯科技有限公司 | Map road drawing method and map road drawing device |
| CN106127113A (en) * | 2016-06-15 | 2016-11-16 | 北京联合大学 | A kind of road track line detecting method based on three-dimensional laser radar |
| CN106485233A (en) * | 2016-10-21 | 2017-03-08 | 深圳地平线机器人科技有限公司 | Drivable region detection method, device and electronic equipment |
| CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Lane line extraction method and device |
| CN106611419A (en) * | 2016-12-19 | 2017-05-03 | 西安电子科技大学 | Extraction method for image road surface region |
| CN106646474A (en) * | 2016-12-22 | 2017-05-10 | 中国兵器装备集团自动化研究所 | Unstructured road accidented barrier detection apparatus |
| CN106709475A (en) * | 2017-01-22 | 2017-05-24 | 百度在线网络技术（北京）有限公司 | Obstacle recognition method and device, computer equipment and readable storage medium |
| CN107169464A (en) * | 2017-05-25 | 2017-09-15 | 中国农业科学院农业资源与农业区划研究所 | A kind of Method for Road Boundary Detection based on laser point cloud |
| CN108256413A (en) * | 2017-11-27 | 2018-07-06 | 科大讯飞股份有限公司 | It can traffic areas detection method and device, storage medium, electronic equipment |
| CN108961353A (en) * | 2017-05-19 | 2018-12-07 | 上海蔚来汽车有限公司 | The building of road model |
| CN109145677A (en) * | 2017-06-15 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Obstacle detection method, device, equipment and storage medium |
| CN109186624A (en) * | 2018-10-19 | 2019-01-11 | 江苏大学 | A kind of unmanned vehicle traveling right of way planing method based on friendship specification beam |
| CN109212555A (en) * | 2018-10-12 | 2019-01-15 | 合肥中科智驰科技有限公司 | Based on three-dimensional laser radar can traffic areas detection method |
| CN109615695A (en) * | 2018-11-13 | 2019-04-12 | 远景能源（南京）软件技术有限公司 | The automation conversion method of space photo outside house to roof CAD diagram paper |
| CN109726728A (en) * | 2017-10-31 | 2019-05-07 | 高德软件有限公司 | A kind of training data generation method and device |
| CN109816697A (en) * | 2019-02-02 | 2019-05-28 | 绥化学院 | A kind of unmanned model car establishes the system and method for map |
| CN109828280A (en) * | 2018-11-29 | 2019-05-31 | 亿嘉和科技股份有限公司 | A kind of localization method and autonomous charging of robots method based on three-dimensional laser grid |
| WO2019100337A1 (en) * | 2017-11-24 | 2019-05-31 | SZ DJI Technology Co., Ltd. | Navigable region recognition and topology matching, and associated systems and methods |
| CN110008921A (en) * | 2019-04-12 | 2019-07-12 | 北京百度网讯科技有限公司 | A kind of generation method of road boundary, device, electronic equipment and storage medium |
| CN110109144A (en) * | 2019-04-30 | 2019-08-09 | 北京云迹科技有限公司 | Road shoulder detection method and device based on multi-line laser radar |
| CN110222605A (en) * | 2019-05-24 | 2019-09-10 | 深兰科技（上海）有限公司 | A kind of obstacle detection method and equipment |
| CN110458854A (en) * | 2018-05-02 | 2019-11-15 | 北京图森未来科技有限公司 | A kind of road edge detection method and device |
| CN110458083A (en) * | 2019-08-05 | 2019-11-15 | 武汉中海庭数据技术有限公司 | A kind of lane line vectorization method, device and storage medium |
| CN110696826A (en) * | 2019-10-09 | 2020-01-17 | 北京百度网讯科技有限公司 | Method and device for controlling a vehicle |
| WO2020093966A1 (en) * | 2018-11-09 | 2020-05-14 | 阿里巴巴集团控股有限公司 | Positioning data generation method, apparatus, and electronic device |
| US10670701B2 (en) | 2017-12-11 | 2020-06-02 | Automotive Research & Testing Center | Dynamic road surface detecting method based on three-dimensional sensor |
| CN111325138A (en) * | 2020-02-18 | 2020-06-23 | 中国科学院合肥物质科学研究院 | Road boundary real-time detection method based on point cloud local concave-convex characteristics |
| CN111537994A (en) * | 2020-03-24 | 2020-08-14 | 江苏徐工工程机械研究院有限公司 | Unmanned mine card obstacle detection method |
| CN111783721A (en) * | 2020-07-13 | 2020-10-16 | 湖北亿咖通科技有限公司 | Lane line extraction method of laser point cloud and electronic equipment |
| CN111860295A (en) * | 2018-09-07 | 2020-10-30 | 百度在线网络技术（北京）有限公司 | Obstacle detection method, device, equipment and storage medium based on unmanned vehicle |
| CN111932943A (en) * | 2020-10-15 | 2020-11-13 | 深圳市速腾聚创科技有限公司 | Dynamic target detection method and device, storage medium and roadbed monitoring equipment |
| CN112045654A (en) * | 2020-08-11 | 2020-12-08 | 上海有个机器人有限公司 | Detection method and device for unmanned closed space and robot |
| CN112183381A (en) * | 2020-09-30 | 2021-01-05 | 深兰人工智能(深圳)有限公司 | Method and device for detecting driving area of vehicle |
| CN112172828A (en) * | 2020-10-14 | 2021-01-05 | 斑马网络技术有限公司 | Narrow road passing method and device, electronic equipment and computer readable storage medium |
| CN112258517A (en) * | 2020-09-30 | 2021-01-22 | 无锡太机脑智能科技有限公司 | Automatic map repairing method and device for laser radar grid map |
| CN112629548A (en) * | 2020-12-28 | 2021-04-09 | 北京航空航天大学 | Three-dimensional grid map creating and updating method based on roadside laser radar |
| CN112649013A (en) * | 2020-12-29 | 2021-04-13 | 天津天瞳威势电子科技有限公司 | Method and device for determining passable area and electronic equipment |
| US11138448B2 (en) | 2018-12-29 | 2021-10-05 | Beijing Didi Infinity Technology And Development Co., Ltd. | Identifying a curb based on 3-D sensor data |
| CN113479191A (en) * | 2021-06-30 | 2021-10-08 | 重庆长安汽车股份有限公司 | Lane-line-free lane boundary detection system and method for parking and vehicle |
| US11455511B2 (en) | 2016-12-29 | 2022-09-27 | Huawei Technologies Co., Ltd. | Ground environment detection method and apparatus |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100189320A1 (en) * | 2007-06-19 | 2010-07-29 | Agfa Healthcare N.V. | Method of Segmenting Anatomic Entities in 3D Digital Medical Images |
| CN102270301A (en) * | 2011-06-07 | 2011-12-07 | 南京理工大学 | Method for detecting unstructured road boundary by combining support vector machine (SVM) and laser radar |
-
2015
- 2015-05-11 CN CN201510237014.XA patent/CN104850834A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100189320A1 (en) * | 2007-06-19 | 2010-07-29 | Agfa Healthcare N.V. | Method of Segmenting Anatomic Entities in 3D Digital Medical Images |
| CN102270301A (en) * | 2011-06-07 | 2011-12-07 | 南京理工大学 | Method for detecting unstructured road boundary by combining support vector machine (SVM) and laser radar |
Non-Patent Citations (2)
| Title |
|---|
| 史鹏波: "基于单线激光雷达的道路特征检测", 《中国优秀硕士学位论文全文数据库》 * |
| 辛煜: "无人驾驶车辆运动障碍物检测、预测和避撞方法研究", 《中国博士学位论文全文数据库》 * |
Cited By (60)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570446B (en) * | 2015-10-12 | 2019-02-01 | 腾讯科技（深圳）有限公司 | The method and apparatus of lane line drawing |
| CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Lane line extraction method and device |
| CN105448184A (en) * | 2015-11-13 | 2016-03-30 | 北京百度网讯科技有限公司 | Map road drawing method and map road drawing device |
| CN105448184B (en) * | 2015-11-13 | 2019-02-12 | 北京百度网讯科技有限公司 | The method for drafting and device of map road |
| CN106127113A (en) * | 2016-06-15 | 2016-11-16 | 北京联合大学 | A kind of road track line detecting method based on three-dimensional laser radar |
| CN106485233A (en) * | 2016-10-21 | 2017-03-08 | 深圳地平线机器人科技有限公司 | Drivable region detection method, device and electronic equipment |
| CN106485233B (en) * | 2016-10-21 | 2020-01-17 | 深圳地平线机器人科技有限公司 | Method and device for detecting travelable area and electronic equipment |
| CN106611419B (en) * | 2016-12-19 | 2019-06-21 | 西安电子科技大学 | The extracting method in image road surface region |
| CN106611419A (en) * | 2016-12-19 | 2017-05-03 | 西安电子科技大学 | Extraction method for image road surface region |
| CN106646474A (en) * | 2016-12-22 | 2017-05-10 | 中国兵器装备集团自动化研究所 | Unstructured road accidented barrier detection apparatus |
| US11455511B2 (en) | 2016-12-29 | 2022-09-27 | Huawei Technologies Co., Ltd. | Ground environment detection method and apparatus |
| CN106709475B (en) * | 2017-01-22 | 2021-01-22 | 百度在线网络技术（北京）有限公司 | Obstacle recognition method and device, computer equipment and readable storage medium |
| CN106709475A (en) * | 2017-01-22 | 2017-05-24 | 百度在线网络技术（北京）有限公司 | Obstacle recognition method and device, computer equipment and readable storage medium |
| CN108961353A (en) * | 2017-05-19 | 2018-12-07 | 上海蔚来汽车有限公司 | The building of road model |
| CN108961353B (en) * | 2017-05-19 | 2023-12-08 | 上海蔚来汽车有限公司 | Construction of road model |
| CN107169464A (en) * | 2017-05-25 | 2017-09-15 | 中国农业科学院农业资源与农业区划研究所 | A kind of Method for Road Boundary Detection based on laser point cloud |
| CN107169464B (en) * | 2017-05-25 | 2019-04-09 | 中国农业科学院农业资源与农业区划研究所 | A kind of Method for Road Boundary Detection based on laser point cloud |
| CN109145677A (en) * | 2017-06-15 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Obstacle detection method, device, equipment and storage medium |
| CN109726728A (en) * | 2017-10-31 | 2019-05-07 | 高德软件有限公司 | A kind of training data generation method and device |
| CN111279154A (en) * | 2017-11-24 | 2020-06-12 | 深圳市大疆创新科技有限公司 | Navigation area identification and topology matching and associated systems and methods |
| WO2019100337A1 (en) * | 2017-11-24 | 2019-05-31 | SZ DJI Technology Co., Ltd. | Navigable region recognition and topology matching, and associated systems and methods |
| CN111279154B (en) * | 2017-11-24 | 2021-08-31 | 深圳市大疆创新科技有限公司 | Navigation area identification and topology matching and associated systems and methods |
| CN108256413A (en) * | 2017-11-27 | 2018-07-06 | 科大讯飞股份有限公司 | It can traffic areas detection method and device, storage medium, electronic equipment |
| US10670701B2 (en) | 2017-12-11 | 2020-06-02 | Automotive Research & Testing Center | Dynamic road surface detecting method based on three-dimensional sensor |
| US11500101B2 (en) | 2018-05-02 | 2022-11-15 | Tusimple, Inc. | Curb detection by analysis of reflection images |
| CN110458854A (en) * | 2018-05-02 | 2019-11-15 | 北京图森未来科技有限公司 | A kind of road edge detection method and device |
| CN111860295B (en) * | 2018-09-07 | 2023-08-25 | 百度在线网络技术（北京）有限公司 | Obstacle detection method, device and equipment based on unmanned vehicle and storage medium |
| CN111860295A (en) * | 2018-09-07 | 2020-10-30 | 百度在线网络技术（北京）有限公司 | Obstacle detection method, device, equipment and storage medium based on unmanned vehicle |
| CN109212555A (en) * | 2018-10-12 | 2019-01-15 | 合肥中科智驰科技有限公司 | Based on three-dimensional laser radar can traffic areas detection method |
| CN109186624B (en) * | 2018-10-19 | 2021-11-12 | 江苏大学 | Unmanned vehicle driving right-of-way planning method based on traffic rule constraint |
| CN109186624A (en) * | 2018-10-19 | 2019-01-11 | 江苏大学 | A kind of unmanned vehicle traveling right of way planing method based on friendship specification beam |
| WO2020093966A1 (en) * | 2018-11-09 | 2020-05-14 | 阿里巴巴集团控股有限公司 | Positioning data generation method, apparatus, and electronic device |
| CN109615695A (en) * | 2018-11-13 | 2019-04-12 | 远景能源（南京）软件技术有限公司 | The automation conversion method of space photo outside house to roof CAD diagram paper |
| CN109828280A (en) * | 2018-11-29 | 2019-05-31 | 亿嘉和科技股份有限公司 | A kind of localization method and autonomous charging of robots method based on three-dimensional laser grid |
| US11138448B2 (en) | 2018-12-29 | 2021-10-05 | Beijing Didi Infinity Technology And Development Co., Ltd. | Identifying a curb based on 3-D sensor data |
| CN109816697A (en) * | 2019-02-02 | 2019-05-28 | 绥化学院 | A kind of unmanned model car establishes the system and method for map |
| CN109816697B (en) * | 2019-02-02 | 2019-12-10 | 绥化学院 | System and method for establishing map by unmanned model vehicle |
| CN110008921A (en) * | 2019-04-12 | 2019-07-12 | 北京百度网讯科技有限公司 | A kind of generation method of road boundary, device, electronic equipment and storage medium |
| CN110008921B (en) * | 2019-04-12 | 2021-12-28 | 北京百度网讯科技有限公司 | Road boundary generation method and device, electronic equipment and storage medium |
| CN110109144A (en) * | 2019-04-30 | 2019-08-09 | 北京云迹科技有限公司 | Road shoulder detection method and device based on multi-line laser radar |
| CN110222605B (en) * | 2019-05-24 | 2021-11-19 | 深兰科技（上海）有限公司 | Obstacle detection method and equipment |
| CN110222605A (en) * | 2019-05-24 | 2019-09-10 | 深兰科技（上海）有限公司 | A kind of obstacle detection method and equipment |
| CN110458083A (en) * | 2019-08-05 | 2019-11-15 | 武汉中海庭数据技术有限公司 | A kind of lane line vectorization method, device and storage medium |
| CN110696826A (en) * | 2019-10-09 | 2020-01-17 | 北京百度网讯科技有限公司 | Method and device for controlling a vehicle |
| CN111325138B (en) * | 2020-02-18 | 2023-04-07 | 中国科学院合肥物质科学研究院 | Road boundary real-time detection method based on point cloud local concave-convex characteristics |
| CN111325138A (en) * | 2020-02-18 | 2020-06-23 | 中国科学院合肥物质科学研究院 | Road boundary real-time detection method based on point cloud local concave-convex characteristics |
| CN111537994A (en) * | 2020-03-24 | 2020-08-14 | 江苏徐工工程机械研究院有限公司 | Unmanned mine card obstacle detection method |
| CN111783721A (en) * | 2020-07-13 | 2020-10-16 | 湖北亿咖通科技有限公司 | Lane line extraction method of laser point cloud and electronic equipment |
| CN112045654B (en) * | 2020-08-11 | 2022-01-28 | 上海有个机器人有限公司 | Detection method and device for unmanned closed space and robot |
| CN112045654A (en) * | 2020-08-11 | 2020-12-08 | 上海有个机器人有限公司 | Detection method and device for unmanned closed space and robot |
| CN112183381A (en) * | 2020-09-30 | 2021-01-05 | 深兰人工智能(深圳)有限公司 | Method and device for detecting driving area of vehicle |
| CN112258517A (en) * | 2020-09-30 | 2021-01-22 | 无锡太机脑智能科技有限公司 | Automatic map repairing method and device for laser radar grid map |
| CN112172828B (en) * | 2020-10-14 | 2022-03-08 | 斑马网络技术有限公司 | Narrow road passing method and device, electronic equipment and computer readable storage medium |
| CN112172828A (en) * | 2020-10-14 | 2021-01-05 | 斑马网络技术有限公司 | Narrow road passing method and device, electronic equipment and computer readable storage medium |
| CN111932943B (en) * | 2020-10-15 | 2021-05-14 | 深圳市速腾聚创科技有限公司 | Dynamic target detection method and device, storage medium and roadbed monitoring equipment |
| CN111932943A (en) * | 2020-10-15 | 2020-11-13 | 深圳市速腾聚创科技有限公司 | Dynamic target detection method and device, storage medium and roadbed monitoring equipment |
| CN112629548A (en) * | 2020-12-28 | 2021-04-09 | 北京航空航天大学 | Three-dimensional grid map creating and updating method based on roadside laser radar |
| CN112629548B (en) * | 2020-12-28 | 2023-01-24 | 北京航空航天大学 | Three-dimensional grid map creating and updating method based on roadside laser radar |
| CN112649013A (en) * | 2020-12-29 | 2021-04-13 | 天津天瞳威势电子科技有限公司 | Method and device for determining passable area and electronic equipment |
| CN113479191A (en) * | 2021-06-30 | 2021-10-08 | 重庆长安汽车股份有限公司 | Lane-line-free lane boundary detection system and method for parking and vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104850834A (en) | Road boundary detection method based on three-dimensional laser radar | |
| Kühnl et al. | Spatial ray features for real-time ego-lane extraction | |
| CN107169464B (en) | A kind of Method for Road Boundary Detection based on laser point cloud | |
| CN103714538B (en) | road edge detection method, device and vehicle | |
| CN101750049B (en) | Monocular vision vehicle distance measuring method based on road and vehicle information | |
| CN107066986A (en) | A kind of lane line based on monocular vision and preceding object object detecting method | |
| CN103177246B (en) | Based on the dual model Lane detection method of dynami c block division | |
| CN104392212A (en) | Method for detecting road information and identifying forward vehicles based on vision | |
| Daigavane et al. | Road lane detection with improved canny edges using ant colony optimization | |
| CN105740782A (en) | Monocular vision based driver lane-changing process quantization method | |
| CN104573627A (en) | Lane line reservation and detection algorithm based on binary image | |
| CN103927526A (en) | Vehicle detecting method based on Gauss difference multi-scale edge fusion | |
| DE102009050504A1 (en) | Clear path of travel detecting method for motor vehicle i.e. car, involves combining clear path of travel and determined flat surface to describe enhanced clear path of travel, and utilizing enhanced clear path of travel to navigate vehicle | |
| EP2821980A1 (en) | Three-dimensional object detection device | |
| CN105005771A (en) | Method for detecting full line of lane based on optical flow point locus statistics | |
| CN105678285A (en) | Adaptive road aerial view transformation method and road lane detection method | |
| CN104008377A (en) | Ground traffic sign real-time detection and recognition method based on space-time correlation | |
| CN104700072A (en) | Lane line historical frame recognition method | |
| CN105206109A (en) | Infrared CCD based foggy day identifying early-warning system and method for vehicle | |
| EP2821982B1 (en) | Three-dimensional object detection device | |
| CN105005778A (en) | Expressway vehicle detection method based on visual background extraction | |
| CN105488492A (en) | Color image preprocessing method, road identification method and related device | |
| CN202134079U (en) | Unmanned vehicle lane marker line identification and alarm device | |
| CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
| CN104700071A (en) | Method for extracting panorama road profile |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150819 |
|
| RJ01 | Rejection of invention patent application after publication |