CN106127113A - A kind of road track line detecting method based on three-dimensional laser radar - Google Patents
A kind of road track line detecting method based on three-dimensional laser radar Download PDFInfo
- Publication number
- CN106127113A CN106127113A CN201610426111.8A CN201610426111A CN106127113A CN 106127113 A CN106127113 A CN 106127113A CN 201610426111 A CN201610426111 A CN 201610426111A CN 106127113 A CN106127113 A CN 106127113A
- Authority
- CN
- China
- Prior art keywords
- grid
- data
- laser radar
- radar
- lane line
- 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)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of method for detecting lane lines based on three-dimensional laser radar, it includes step: 1) set up the radar fix system oxyz of detection vehicle；2) setting up area-of-interest under radar fix system oxy, the regions of interest data collecting laser radar carries out rasterizing process；3) filter non-floor grid according to the internal highs and lows data of grid, and utilize peak data to filter grid in non-track；4) ask for the meansigma methods of grid inner laser radar reflection intensity data, set laser radar and gather the threshold value of data reflex strength, filter the grid differed greatly with lane line reflex strength；5) the isolated or abnormal grid close to lane line Reflection intensity information is filtered；6) grid obtained above is carried out the curve matching of method of least square, obtains terrain vehicle diatom.The present invention can process in real time, work double tides, and Detection results precision is higher, highly reliable, and algorithm robustness is preferable.
Description
Technical field
The invention belongs to the traffic environment perception field in intelligent vehicle technology, being specifically related to one, to be applied to intelligent vehicle autonomous
Travel or the terrain vehicle diatom real-time detection method based on three-dimensional laser radar of auxiliary travelling.
Background technology
Three-dimensional laser radar is one of important sensor of intelligent vehicle acquisition external environmental information, has precision high, in real time
Property and the advantage such as highly reliable, laser radar is also widely used in the research of intelligent vehicle perception environment.Each laser radar
The cloud data of sensor acquisition data can use Point, and (x, y, z i) represent, x, y, z represent the environmental objects that detects
Actual range, i represents the laser radar reflex strength to this point, and size is 0-255, dimensionless. three-dimensional laser radar point cloud number
Returning data point according to about 1,300,000 per second an of cycle, renewal frequency can reach 5-20HZ.The reflex strength of laser radar is big
Little material and the smooth degree depending on being irradiated object by laser radar, and lane line typically can be different from general by brush last layer
The material of passway, the difference of its smooth degree and material determines its reflex strength can have larger difference with prevailing roadway.
And laser radar is a kind of active environment detection sensor, its little interference by environment, precision advantages of higher.
Lane detection technology is one the important technical work of intelligent vehicle environment sensing, and image technique is usual all the time
It it is the research direction of research worker first-selection.The key issue of lane detection is how to extract the feature of lane line, and makes
Which kind of model to simulate lane line with.
Chinese invention patent " a kind of method for detecting lane lines " application number 201410065412.3, publication No. is
CN103839264 A.Adaptive threshold Boundary extracting algorithm is utilized to extract the marginal information in road image.
Chinese invention patent " a kind of based on the fuzzy and method for detecting lane lines of Kalman filter " application number
201410513200.7, publication No. is CN104318258 A.Change method and introduce time domain Fuzzy Processing and Kalman filter prediction
The detecting and tracking method combined reaches detection in real time and the tracking of lane line.
Chinese invention patent " a kind of method for detecting lane lines " application number 201510117857.6, publication No. is
CN104657727 A.The method uses lane line width calibration, models lane line, draws detection region, detected edge points pair
Obtain lane line edge pair graph, maximum edge pair graph is carried out method of least square, obtains lane line matching.
Foregoing invention is all use pictorial form that method is implemented, and the acquisition quality of image is by illumination, weather
The biggest etc. extraneous factor impact.Obtaining image in said method, general consideration environment is under good situations, or uses certain
Algorithm reduce the impact that brings of environmental factors, thus bring the biggest impact to image mode detection lane line.
Summary of the invention
For the problems referred to above, it is an object of the invention to provide a kind of terrain vehicle diatom detection side based on three-dimensional laser radar
Method, it is possible to do not affected by the outside environmental elements such as weather, illumination, detects lane line, fast and accurately for intelligent vehicle
Autonomous travel or auxiliary travelling.
For achieving the above object, the present invention takes techniques below scheme: a kind of road track based on three-dimensional laser radar
Line detecting method, it comprises the following steps: 1) set up the radar fix system oxyz of detection vehicle；2) radar cloud data is located in advance
Reason, sets up the area-of-interest under radar fix system oxyz, and the regions of interest data collecting laser radar carries out grid
Change processes, and chooses grid size, and the size of grid is 0.1m × 0.1m；3) internal data of grid be divided into peak data and
Minimum point data, needing the grid filtered is non-floor grid, non-track grid, according to the inside highs and lows of grid
Data filter non-floor grid, and utilize peak data to filter non-track grid, through above-mentioned grid filter obtain pending
Raster data, be grid inner laser radar reflection intensity data；4) grid inner laser radar reflection intensity data is asked for
Meansigma methods, and set the threshold value of laser radar collection data reflex strength, filter with lane line reflex strength difference more than threshold value
Grid；5) the isolated or abnormal grid close to lane line strength information is filtered；6) the above-mentioned raster data obtained that filters is entered
The curve matching of row method of least square, obtains terrain vehicle diatom.
Described step 1) in, the described radar fix system setting up detection vehicle, refer to when detection vehicle is in level road
And under resting state, laser radar installed by detection vehicle, to install radar center for zero o, x, y, z axle passes initial point
O, x-axis is parallel to the ground and the headstock of direction direct detection vehicle, and y-axis is perpendicular to x-axis, parallel to the ground and direction direct detection
The left hand direction of vehicle forward direction, z-axis is perpendicular to x, y-axis, and direction is perpendicular to ground upwards.
Described step 2) in, described data preprocessing includes procedure below: 1. set up sense under radar fix system emerging
Interest region, and set the regional extent of x, y, z；
This regional extent is :-40m < x < 40m ,-10m < y < 10m ,-10m < z < 0m；
2. the cloud data of area-of-interest is divided in horizontal plane the lattice of 0.1m × 0.1m, by these little sides
Lattice are mapped in grid map one by one, keep the one_to_one corresponding of cloud data and the data in grid, and the lattice of foundation can just
Enough hold all of cloud data.
Described step 3) in, filter non-track grid, including procedure below: 1. ask for the z-axis direction of each raster data
Peak cloud data and minimum cloud data, do difference, if this difference just filters this grid point more than threshold value set in advance
And it is labeled as 0；2. for non-rice habitats and belong to planar environment, extract the z-axis bearing data of each grid, preset a threshold
Value, filters non-rice habitats raster data and is labeled as 0.
Described step 4) in, filter and lane line reflex strength larger difference grid point, to step 3) all grid of extracting
Lattice data, the cloud data in each grid is asked for average reflection intensity level, is preset reflex strength threshold value, filters and track
Grid that line reflection strength difference is bigger is also labeled as 0；
Described step 5) in, filter the isolated or abnormal grid close to lane line strength information, select filtering method, will
To grid radar cloud data in isolated or abnormity point noise filtering.
Described step 6) in, obtain lane line, including procedure below: the 1. selected terrain vehicle diatom scope needing detection,
Extraction step 5 in this range) the middle grid map obtained；The curve that 2. grid region chosen carries out method of least square is intended
Close, obtain smooth road track line chart.
The invention have the advantage that
(1) compare current most of image processing techniques, substantially reduce the car brought by the environment such as ambient weather, illumination
Diatom detection difficult；
(2) can work double tides, in real time for intelligent vehicle provide lane detection；
(3) high-precision three-dimensional laser radar provides cloud data, and reliability is high.
Accompanying drawing explanation
Fig. 1 is the overall flow schematic diagram of the present invention；
Fig. 2 is the radar fix system schematic diagram of the present invention；
Fig. 3 be the present invention filter common ground after, lane line grid schematic diagram；
Fig. 4 be the present invention filter isolated point after, lane line grid schematic diagram；
Fig. 5 is the extraction lane line schematic diagram of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawings the present invention is elaborated.
A kind of road track line detecting method based on three-dimensional laser radar, concretely comprises the following steps:
1) the radar fix system oxyz of detection vehicle is set up.
As in figure 2 it is shown, radar fix system oxyz, refer to detect stationary vehicle puts on the ground, and laser radar is installed on
Detection vehicle roof, with laser radar center for initial point o, x-axis through o and level in ground, before the direct detection vehicle of direction
Entering direction, z-axis is through o and is perpendicular to ground, and vehicle up direction is pointed in direction, and y-axis presses right-hand rule, if the direction of Fig. 2 is towards paper
The inside.
2) to radar data preprocessing.
Owing to laser radar can obtain the cloud data of environment more than hundred meters, and the cloud data of three-dimensional laser radar
About 1,300,000 cloud datas per second, and for intelligent vehicle, need not process too much cloud data, can also for intelligent vehicle
Cloud data needed for more rapid acquisition, needs radar cloud data is carried out pretreatment.
1. choosing area-of-interest (ROI) under radar fix system, the area-of-interest that this invention is chosen is :-40m < x
< < y < 10m ,-10m < z < 0m, the most neither loses useful data, also improves the operation efficiency of computer for 40m ,-10m；
Acquired area-of-interest (ROI) 2. carrying out rasterizing on horizontal plane direction process, this invention is chosen
Grid size is 0.1m × 0.1m square, and the cloud data of the cloud data inside each square and area-of-interest is one by one
Correspondence, the grid altogether obtained 800 × 200.Wherein bodywork reference frame is (400,100).
3) filter non-floor grid according to the internal highs and lows data of grid, and it is non-to utilize peak data to filter
Road grid.
In true environment, not only only have road return the cloud data of coming, the barrier being also above the ground level and non-rice habitats
Interior plane cloud data, this invention uses the methods filtering these interference information as follows.
1. the cloud data in each grid is asked for the difference of the maximum on z-axis direction and minima, if this value
More than the threshold value set, with regard to labelling barrier, i.e. noise, being labeled as 0, otherwise retain and be labeled as 1, white point represents and is marked as 1,
Stain represents and is marked as 0；
2. the cloud data in each grid is extracted peak, if peak is more than the threshold value set, is labeled as 0,
Otherwise retain and be labeled as 1.
4) ask for the meansigma methods of grid inner laser radar reflection intensity data, set laser radar and gather data reflex strength
Threshold value, filter the grid differed greatly with lane line reflex strength.
The reflex strength difference utilizing laser radar to return unlike material sets a threshold value, and this threshold value is used for district
Divided lane line and prevailing roadway radar cloud data.Method particularly includes: all cloud datas in each grid are asked for reflection
Average strength, this meansigma methods and threshold value set in advance compare, and relatively filter out common ground after all raster datas
Information, as it is shown on figure 3, the brightest point in centre represents detection vehicle location.
5) the isolated or abnormal grid close to lane line strength information is filtered.
Use filtering algorithm to be filtered by the isolated noise point in radar grid cloud atlas, concretely comprise the following steps: 1. remove radar data
In a grid such as A [x] [y], the A that fetches data [x ± i] [y ± j], wherein i, j=0,1,2.2. computation grid A [x ± i] [y
± j] number m of data, if m < n, (n value is 3), then A [x] [y] is filtered, be i.e. labeled as 0.3. the value of A [x] [y]
Travel through whole grid map, it is achieved the filtering to whole laser radar raster data.As shown in Figure 4.
6) grid obtained above is carried out the curve matching of method of least square, obtains terrain vehicle diatom.
The method can also carry out multilane extraction, specifically comprises the following steps that
1. being screened by row by the area-of-interest selected, this method midrange is 200, extracts sense the most respectively
The lane line profile in interest region.
2. the alternative point of the curve matching of one group of contours extract wherein method of least square therein is chosen, due to alternative ratio
More, adjacent multiple point can be used here only to select the most alternately point, the present invention uses 3 click 1 point methods in fact
Existing, these alternative points are carried out the curve matching of method of least square, a wherein lane line can be obtained, successively to selected profile
Carry out the curve matching of method of least square, whole lane line can be extracted, as shown in Figure 5.
Claims (10)
1. a road track line detecting method based on three-dimensional laser radar, it is characterised in that: the method comprises the following steps:
1) the radar fix system oxyz of detection vehicle is set up；2) to radar data preprocessing, set up under radar fix system oxyz
Area-of-interest, the regions of interest data collecting laser radar carries out rasterizing process, and chooses grid size, grid
Size be 0.1m × 0.1m；3) internal data of grid is divided into peak data and minimum point data, needs the grid filtered
For non-floor grid, non-track grid, filter non-floor grid according to the inside highs and lows data of grid, and utilize
Peak data filter non-track grid, filter through above-mentioned grid and obtain pending raster data, are grid inner laser
Radar reflection intensity data；4) ask for the meansigma methods of grid inner laser radar reflection intensity data, and set laser radar collection
The threshold value of data reflex strength, filters with lane line reflex strength difference more than the grid of threshold value；5) filter close to lane line strong
Isolated or the abnormal grid of degree information；6) the above-mentioned raster data obtained that filters is carried out the curve matching of method of least square,
To terrain vehicle diatom.
A kind of road track line detecting method based on three-dimensional laser radar the most according to claim 1, it is characterised in that:
Described step 1) in, the described radar fix system setting up detection vehicle, refer to when detection vehicle is in level road and static shape
Under state, laser radar being installed by detection vehicle, to install radar center for zero o, x, y, z axle passes initial point o, x-axis with
Ground is parallel and the headstock of direction direct detection vehicle, and y-axis is perpendicular to x-axis, before parallel to the ground and direction direct detection vehicle
Entering the left hand direction in direction, z-axis is perpendicular to x, y-axis, and direction is perpendicular to ground upwards.
A kind of road track line detecting method based on three-dimensional laser radar the most according to claim 1, it is characterised in that:
Described step 2) in, described data preprocessing includes procedure below: 1. set up area-of-interest under radar fix system,
And set the regional extent of x, y, z；
This regional extent is :-40m < x < 40m ,-10m < y < 10m ,-10m < z < 0m；
2. the cloud data of area-of-interest is divided in horizontal plane the lattice of 0.1m × 0.1m, by these lattices one
One is mapped in grid map, keeps the one_to_one corresponding of cloud data and the data in grid, and the lattice of foundation just can hold
Under all of cloud data.
A kind of road track line detecting method based on three-dimensional laser radar the most according to claim 1, it is characterised in that:
Described step 3) in, filter non-track grid, including procedure below: 1. ask for the peak in the z-axis direction of each raster data
Cloud data and minimum cloud data, do difference, if this difference just filters this grid point more than threshold value set in advance and is labeled as
0；2. for non-rice habitats and belong to planar environment, extract the z-axis bearing data of each grid, preset a threshold value, filter
Non-rice habitats raster data is also labeled as 0.
A kind of road track line detecting method based on three-dimensional laser radar the most according to claim 1, it is characterised in that:
Described step 4) in, filter and lane line reflex strength larger difference grid point, to step 3) all raster datas of extracting, often
Cloud data in individual grid asks for average reflection intensity level, presets reflex strength threshold value, filters strong with lane line reflection
Spend the grid differed greatly and be labeled as 0.
A kind of road track line detecting method based on three-dimensional laser radar the most according to claim 1, it is characterised in that:
Described step 5) in, filter the isolated or abnormal grid close to lane line strength information, select filtering method, the grid that will obtain
Isolated or abnormity point noise filtering in radar cloud data.
A kind of road track line detecting method based on three-dimensional laser radar the most according to claim 1, its feature exists
In: described step 6) in, obtain lane line, including procedure below: the 1. selected terrain vehicle diatom scope needing detection, at this model
Enclose interior extraction step 5) the middle grid map obtained；2. the grid region chosen is carried out the curve matching of method of least square, obtains
Smooth road track line chart.
A kind of road track line detecting method based on three-dimensional laser radar the most according to claim 1, it is characterised in that:
In true environment, not only only have road return the cloud data of coming, the plane in the barrier being also above the ground level and non-rice habitats
Cloud data, this method uses the method filtering these interference information as follows；
1. the cloud data in each grid is asked for the difference of the maximum on z-axis direction and minima, if this value is more than
The threshold value set, with regard to labelling barrier, i.e. noise, is labeled as 0, otherwise retains and is labeled as 1, and white point represents and is marked as 1, stain
Represent and be marked as 0；
2. the cloud data in each grid is extracted peak, if peak is more than the threshold value set, be labeled as 0, otherwise
Retain and be labeled as 1；
1) ask for the meansigma methods of grid inner laser radar reflection intensity data, set laser radar and gather the threshold of data reflex strength
Value, filters the grid differed greatly with lane line reflex strength.
A kind of road track line detecting method based on three-dimensional laser radar the most according to claim 1, it is characterised in that:
The reflex strength difference utilizing laser radar to return unlike material sets a threshold value, and this threshold value is used for distinguishing lane line
With prevailing roadway radar cloud data；Method particularly includes: all cloud datas in each grid are asked for reflex strength average
Value, this meansigma methods and threshold value set in advance compare, and relatively filter out common ground information after all raster datas, middle
The brightest point represents detection vehicle location；
2) the isolated or abnormal grid close to lane line strength information is filtered；
Use filtering algorithm to be filtered by the isolated noise point in radar grid cloud atlas, concretely comprise the following steps: 1. go in radar data
One grid such as A [x] [y], the A that fetches data [x ± i] [y ± j], wherein i, j=0,1,2；2. computation grid A [x ± i] [y ± j]
Number m of data, if m < n, n value would be 3, then filtered by A [x] [y], be i.e. labeled as 0；3. the value traversal of A [x] [y] is whole
Individual grid map, it is achieved the filtering to whole laser radar raster data.
3) grid obtained above is carried out the curve matching of method of least square, obtains terrain vehicle diatom.
A kind of road track line detecting method based on three-dimensional laser radar the most according to claim 1, its feature exists
In: the method can also carry out multilane extraction, specifically comprises the following steps that
1. being screened by row by the area-of-interest selected, this method midrange is 200, extracts interested the most respectively
The lane line profile in region；
2. the alternative point of the curve matching of one group of contours extract wherein method of least square therein is chosen, owing to alternative point compares
Many, adjacent multiple point can be used here only to select the most alternately point, this method uses 3 click 1 point methods and realize,
These alternative points are carried out the curve matching of method of least square, a wherein lane line can be obtained, successively selected profile is entered
The curve matching of row method of least square, can extract whole lane line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610426111.8A CN106127113A (en) | 2016-06-15 | 2016-06-15 | A kind of road track line detecting method based on three-dimensional laser radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610426111.8A CN106127113A (en) | 2016-06-15 | 2016-06-15 | A kind of road track line detecting method based on three-dimensional laser radar |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106127113A true CN106127113A (en) | 2016-11-16 |
Family
ID=57470245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610426111.8A Pending CN106127113A (en) | 2016-06-15 | 2016-06-15 | A kind of road track line detecting method based on three-dimensional laser radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106127113A (en) |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106772434A (en) * | 2016-11-18 | 2017-05-31 | 北京联合大学 | A kind of unmanned vehicle obstacle detection method based on TegraX1 radar datas |
| CN107272019A (en) * | 2017-05-09 | 2017-10-20 | 深圳市速腾聚创科技有限公司 | Curb detection method based on Laser Radar Scanning |
| CN107798305A (en) * | 2012-03-23 | 2018-03-13 | 伟摩有限责任公司 | Detect lane markings |
| CN108345008A (en) * | 2017-01-23 | 2018-07-31 | 郑州宇通客车股份有限公司 | A kind of target object detecting method, point cloud data extracting method and device |
| WO2018195742A1 (en) * | 2017-04-24 | 2018-11-01 | 李卓希 | Vehicle driving control method and system |
| WO2018210303A1 (en) * | 2017-05-19 | 2018-11-22 | 上海蔚来汽车有限公司 | Road model construction |
| CN108873896A (en) * | 2018-06-15 | 2018-11-23 | 驭势科技（北京）有限公司 | A kind of lane line analogy method, device and storage medium |
| CN108985230A (en) * | 2018-07-17 | 2018-12-11 | 深圳市易成自动驾驶技术有限公司 | Method for detecting lane lines, device and computer readable storage medium |
| CN109017780A (en) * | 2018-04-12 | 2018-12-18 | 深圳市布谷鸟科技有限公司 | A kind of Vehicular intelligent driving control method |
| CN109753982A (en) * | 2017-11-07 | 2019-05-14 | 北京京东尚科信息技术有限公司 | Obstacle point detecting method, device and computer readable storage medium |
| CN109840463A (en) * | 2017-11-27 | 2019-06-04 | 北京图森未来科技有限公司 | A kind of Lane detection method and apparatus |
| CN109858460A (en) * | 2019-02-20 | 2019-06-07 | 重庆邮电大学 | A kind of method for detecting lane lines based on three-dimensional laser radar |
| CN109916416A (en) * | 2019-01-29 | 2019-06-21 | 腾讯科技（深圳）有限公司 | Lane line data processing and update method, device and equipment |
| CN109946708A (en) * | 2017-12-21 | 2019-06-28 | 北京万集科技股份有限公司 | A kind of method for detecting lane lines and device based on laser radar scanning |
| CN110008851A (en) * | 2019-03-15 | 2019-07-12 | 深兰科技（上海）有限公司 | A kind of method and apparatus of lane detection |
| CN110595492A (en) * | 2019-09-25 | 2019-12-20 | 上海交通大学 | Vehicle self-positioning system and method in park environment |
| CN110609268A (en) * | 2018-11-01 | 2019-12-24 | 驭势科技（北京）有限公司 | Laser radar calibration method, device and system and storage medium |
| CN110632617A (en) * | 2019-09-29 | 2019-12-31 | 北京邮电大学 | Laser radar point cloud data processing method and device |
| CN110736999A (en) * | 2019-10-24 | 2020-01-31 | 北京交通大学 | Railway turnout detection method based on laser radar |
| CN110865388A (en) * | 2019-11-28 | 2020-03-06 | 芜湖汽车前瞻技术研究院有限公司 | Combined calibration method and device for camera and laser radar and storage medium |
| TWI690439B (en) * | 2018-11-01 | 2020-04-11 | 財團法人車輛研究測試中心 | Lane stripe detecting method based on three-dimensional lidar and system thereof |
| WO2020083349A1 (en) * | 2018-10-24 | 2020-04-30 | 长沙智能驾驶研究院有限公司 | Method and device for data processing for use in intelligent driving equipment, and storage medium |
| CN111126114A (en) * | 2018-11-01 | 2020-05-08 | 财团法人车辆研究测试中心 | Method and system for detecting light of road marking |
| CN111256707A (en) * | 2019-08-27 | 2020-06-09 | 北京纵目安驰智能科技有限公司 | Congestion car following system and terminal based on look around |
| CN111273305A (en) * | 2020-02-18 | 2020-06-12 | 中国科学院合肥物质科学研究院 | Multi-sensor fusion road extraction and indexing method based on global and local grid maps |
| CN111275075A (en) * | 2020-01-10 | 2020-06-12 | 山东超越数控电子股份有限公司 | Vehicle detection and tracking method based on 3D laser radar |
| CN111402160A (en) * | 2020-03-13 | 2020-07-10 | 北京百度网讯科技有限公司 | Point cloud data denoising method, device, equipment and storage medium |
| CN111491845A (en) * | 2017-10-16 | 2020-08-04 | 康蒂-特米克微电子有限公司 | Method for radar classification of road surfaces |
| CN111699407A (en) * | 2019-03-29 | 2020-09-22 | 深圳市大疆创新科技有限公司 | Method for detecting stationary object near fence by microwave radar and millimeter wave radar |
| CN111999741A (en) * | 2020-01-17 | 2020-11-27 | 青岛慧拓智能机器有限公司 | Method and device for detecting roadside laser radar target |
| CN112215144A (en) * | 2020-10-12 | 2021-01-12 | 北京四维智联科技有限公司 | Method and system for processing lane line |
| US10901421B2 (en) | 2018-06-26 | 2021-01-26 | Neusoft Reach Automotive Technology (Shanghai) Co., Ltd. | Method and device for detecting road boundary |
| CN112327308A (en) * | 2019-07-19 | 2021-02-05 | 阿里巴巴集团控股有限公司 | Object detection method, device, system and equipment |
| CN112560800A (en) * | 2021-01-12 | 2021-03-26 | 知行汽车科技（苏州）有限公司 | Road edge detection method, device and storage medium |
| CN113221241A (en) * | 2021-04-30 | 2021-08-06 | 北京京东乾石科技有限公司 | Data processing method of unmanned vehicle and related equipment |
| CN113255404A (en) * | 2020-02-11 | 2021-08-13 | 北京百度网讯科技有限公司 | Lane line recognition method and device, electronic device and computer-readable storage medium |
| CN113281782A (en) * | 2021-05-08 | 2021-08-20 | 北京联合大学 | Laser radar snow point filtering method based on unmanned vehicle |
| CN113298910A (en) * | 2021-05-14 | 2021-08-24 | 阿波罗智能技术(北京)有限公司 | Method, apparatus and storage medium for generating traffic sign line map |
| CN113607185A (en) * | 2021-10-08 | 2021-11-05 | 禾多科技（北京）有限公司 | Lane line information display method, lane line information display device, electronic device, and computer-readable medium |
| CN113758501A (en) * | 2021-09-08 | 2021-12-07 | 广州小鹏自动驾驶科技有限公司 | Method for detecting abnormal lane line in map and readable storage medium |
| CN115079152A (en) * | 2021-03-10 | 2022-09-20 | 广达电脑股份有限公司 | Electronic device and method for positioning, imaging, detecting and distinguishing |
| CN116047537A (en) * | 2022-12-05 | 2023-05-02 | 北京中科东信科技有限公司 | Road information generation method and system based on laser radar |
| WO2023124231A1 (en) * | 2021-12-31 | 2023-07-06 | 中国第一汽车股份有限公司 | Lidar-based road boundary detection method and apparatus |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8332134B2 (en) * | 2008-04-24 | 2012-12-11 | GM Global Technology Operations LLC | Three-dimensional LIDAR-based clear path detection |
| CN103226833A (en) * | 2013-05-08 | 2013-07-31 | 清华大学 | Point cloud data partitioning method based on three-dimensional laser radar |
| CN104850834A (en) * | 2015-05-11 | 2015-08-19 | 中国科学院合肥物质科学研究院 | Road boundary detection method based on three-dimensional laser radar |
| CN105488498A (en) * | 2016-01-15 | 2016-04-13 | 武汉光庭信息技术股份有限公司 | Lane sideline automatic extraction method and lane sideline automatic extraction system based on laser point cloud |
-
2016
- 2016-06-15 CN CN201610426111.8A patent/CN106127113A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8332134B2 (en) * | 2008-04-24 | 2012-12-11 | GM Global Technology Operations LLC | Three-dimensional LIDAR-based clear path detection |
| CN103226833A (en) * | 2013-05-08 | 2013-07-31 | 清华大学 | Point cloud data partitioning method based on three-dimensional laser radar |
| CN104850834A (en) * | 2015-05-11 | 2015-08-19 | 中国科学院合肥物质科学研究院 | Road boundary detection method based on three-dimensional laser radar |
| CN105488498A (en) * | 2016-01-15 | 2016-04-13 | 武汉光庭信息技术股份有限公司 | Lane sideline automatic extraction method and lane sideline automatic extraction system based on laser point cloud |
Non-Patent Citations (1)
| Title |
|---|
| 吴毅华: "基于激光雷达回波信号的车道线检测方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (64)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798305A (en) * | 2012-03-23 | 2018-03-13 | 伟摩有限责任公司 | Detect lane markings |
| CN107798305B (en) * | 2012-03-23 | 2021-12-07 | 伟摩有限责任公司 | Detecting lane markings |
| CN106772434A (en) * | 2016-11-18 | 2017-05-31 | 北京联合大学 | A kind of unmanned vehicle obstacle detection method based on TegraX1 radar datas |
| CN108345008A (en) * | 2017-01-23 | 2018-07-31 | 郑州宇通客车股份有限公司 | A kind of target object detecting method, point cloud data extracting method and device |
| WO2018195742A1 (en) * | 2017-04-24 | 2018-11-01 | 李卓希 | Vehicle driving control method and system |
| CN107272019A (en) * | 2017-05-09 | 2017-10-20 | 深圳市速腾聚创科技有限公司 | Curb detection method based on Laser Radar Scanning |
| WO2018210303A1 (en) * | 2017-05-19 | 2018-11-22 | 上海蔚来汽车有限公司 | Road model construction |
| CN108961353B (en) * | 2017-05-19 | 2023-12-08 | 上海蔚来汽车有限公司 | Construction of road model |
| CN108961353A (en) * | 2017-05-19 | 2018-12-07 | 上海蔚来汽车有限公司 | The building of road model |
| CN111491845B (en) * | 2017-10-16 | 2024-04-16 | 德国大陆自动驾驶有限公司 | Method for radar classification of road surfaces |
| CN111491845A (en) * | 2017-10-16 | 2020-08-04 | 康蒂-特米克微电子有限公司 | Method for radar classification of road surfaces |
| CN109753982A (en) * | 2017-11-07 | 2019-05-14 | 北京京东尚科信息技术有限公司 | Obstacle point detecting method, device and computer readable storage medium |
| CN109753982B (en) * | 2017-11-07 | 2021-09-03 | 北京京东乾石科技有限公司 | Obstacle point detection method, obstacle point detection device, and computer-readable storage medium |
| CN109840463B (en) * | 2017-11-27 | 2021-03-30 | 北京图森未来科技有限公司 | Lane line identification method and device |
| CN109840463A (en) * | 2017-11-27 | 2019-06-04 | 北京图森未来科技有限公司 | A kind of Lane detection method and apparatus |
| CN109946708A (en) * | 2017-12-21 | 2019-06-28 | 北京万集科技股份有限公司 | A kind of method for detecting lane lines and device based on laser radar scanning |
| CN109017780A (en) * | 2018-04-12 | 2018-12-18 | 深圳市布谷鸟科技有限公司 | A kind of Vehicular intelligent driving control method |
| CN108873896B (en) * | 2018-06-15 | 2021-07-02 | 驭势科技（北京）有限公司 | Lane line simulation method and device and storage medium |
| CN108873896A (en) * | 2018-06-15 | 2018-11-23 | 驭势科技（北京）有限公司 | A kind of lane line analogy method, device and storage medium |
| US10901421B2 (en) | 2018-06-26 | 2021-01-26 | Neusoft Reach Automotive Technology (Shanghai) Co., Ltd. | Method and device for detecting road boundary |
| CN108985230A (en) * | 2018-07-17 | 2018-12-11 | 深圳市易成自动驾驶技术有限公司 | Method for detecting lane lines, device and computer readable storage medium |
| WO2020083349A1 (en) * | 2018-10-24 | 2020-04-30 | 长沙智能驾驶研究院有限公司 | Method and device for data processing for use in intelligent driving equipment, and storage medium |
| TWI690439B (en) * | 2018-11-01 | 2020-04-11 | 財團法人車輛研究測試中心 | Lane stripe detecting method based on three-dimensional lidar and system thereof |
| CN111126114A (en) * | 2018-11-01 | 2020-05-08 | 财团法人车辆研究测试中心 | Method and system for detecting light of road marking |
| US11474242B2 (en) | 2018-11-01 | 2022-10-18 | Automotive Research & Testing Center | Lane stripe detecting method based on three-dimensional lidar and system thereof |
| CN111126114B (en) * | 2018-11-01 | 2023-03-31 | 财团法人车辆研究测试中心 | Method and system for detecting light of road marking |
| CN110609268A (en) * | 2018-11-01 | 2019-12-24 | 驭势科技（北京）有限公司 | Laser radar calibration method, device and system and storage medium |
| CN109916416A (en) * | 2019-01-29 | 2019-06-21 | 腾讯科技（深圳）有限公司 | Lane line data processing and update method, device and equipment |
| CN109858460B (en) * | 2019-02-20 | 2022-06-10 | 重庆邮电大学 | Lane line detection method based on three-dimensional laser radar |
| CN109858460A (en) * | 2019-02-20 | 2019-06-07 | 重庆邮电大学 | A kind of method for detecting lane lines based on three-dimensional laser radar |
| CN110008851B (en) * | 2019-03-15 | 2021-11-19 | 深兰科技（上海）有限公司 | Method and equipment for detecting lane line |
| CN110008851A (en) * | 2019-03-15 | 2019-07-12 | 深兰科技（上海）有限公司 | A kind of method and apparatus of lane detection |
| CN111699407A (en) * | 2019-03-29 | 2020-09-22 | 深圳市大疆创新科技有限公司 | Method for detecting stationary object near fence by microwave radar and millimeter wave radar |
| CN112327308A (en) * | 2019-07-19 | 2021-02-05 | 阿里巴巴集团控股有限公司 | Object detection method, device, system and equipment |
| CN111256707A (en) * | 2019-08-27 | 2020-06-09 | 北京纵目安驰智能科技有限公司 | Congestion car following system and terminal based on look around |
| CN110595492A (en) * | 2019-09-25 | 2019-12-20 | 上海交通大学 | Vehicle self-positioning system and method in park environment |
| CN110632617A (en) * | 2019-09-29 | 2019-12-31 | 北京邮电大学 | Laser radar point cloud data processing method and device |
| CN110736999A (en) * | 2019-10-24 | 2020-01-31 | 北京交通大学 | Railway turnout detection method based on laser radar |
| CN110736999B (en) * | 2019-10-24 | 2021-11-02 | 北京交通大学 | Railway turnout detection method based on laser radar |
| CN110865388A (en) * | 2019-11-28 | 2020-03-06 | 芜湖汽车前瞻技术研究院有限公司 | Combined calibration method and device for camera and laser radar and storage medium |
| CN110865388B (en) * | 2019-11-28 | 2023-10-31 | 芜湖汽车前瞻技术研究院有限公司 | Combined calibration method and device for camera and laser radar and storage medium |
| CN111275075B (en) * | 2020-01-10 | 2023-05-02 | 超越科技股份有限公司 | Vehicle detection and tracking method based on 3D laser radar |
| CN111275075A (en) * | 2020-01-10 | 2020-06-12 | 山东超越数控电子股份有限公司 | Vehicle detection and tracking method based on 3D laser radar |
| CN111999741B (en) * | 2020-01-17 | 2023-03-14 | 青岛慧拓智能机器有限公司 | Method and device for detecting roadside laser radar target |
| CN111999741A (en) * | 2020-01-17 | 2020-11-27 | 青岛慧拓智能机器有限公司 | Method and device for detecting roadside laser radar target |
| CN113255404A (en) * | 2020-02-11 | 2021-08-13 | 北京百度网讯科技有限公司 | Lane line recognition method and device, electronic device and computer-readable storage medium |
| CN111273305A (en) * | 2020-02-18 | 2020-06-12 | 中国科学院合肥物质科学研究院 | Multi-sensor fusion road extraction and indexing method based on global and local grid maps |
| CN111402160A (en) * | 2020-03-13 | 2020-07-10 | 北京百度网讯科技有限公司 | Point cloud data denoising method, device, equipment and storage medium |
| CN111402160B (en) * | 2020-03-13 | 2023-09-05 | 北京百度网讯科技有限公司 | Point cloud data denoising method, device, equipment and storage medium |
| CN112215144A (en) * | 2020-10-12 | 2021-01-12 | 北京四维智联科技有限公司 | Method and system for processing lane line |
| CN112215144B (en) * | 2020-10-12 | 2024-05-14 | 北京四维智联科技有限公司 | Method and system for processing lane lines |
| CN112560800B (en) * | 2021-01-12 | 2024-05-28 | 知行汽车科技(苏州)股份有限公司 | Road edge detection method, device and storage medium |
| CN112560800A (en) * | 2021-01-12 | 2021-03-26 | 知行汽车科技（苏州）有限公司 | Road edge detection method, device and storage medium |
| CN115079152A (en) * | 2021-03-10 | 2022-09-20 | 广达电脑股份有限公司 | Electronic device and method for positioning, imaging, detecting and distinguishing |
| CN113221241A (en) * | 2021-04-30 | 2021-08-06 | 北京京东乾石科技有限公司 | Data processing method of unmanned vehicle and related equipment |
| CN113281782A (en) * | 2021-05-08 | 2021-08-20 | 北京联合大学 | Laser radar snow point filtering method based on unmanned vehicle |
| CN113298910A (en) * | 2021-05-14 | 2021-08-24 | 阿波罗智能技术(北京)有限公司 | Method, apparatus and storage medium for generating traffic sign line map |
| CN113758501A (en) * | 2021-09-08 | 2021-12-07 | 广州小鹏自动驾驶科技有限公司 | Method for detecting abnormal lane line in map and readable storage medium |
| CN113758501B (en) * | 2021-09-08 | 2024-06-04 | 广州小鹏自动驾驶科技有限公司 | Method for detecting abnormal lane line in map and readable storage medium |
| CN113607185B (en) * | 2021-10-08 | 2022-01-04 | 禾多科技（北京）有限公司 | Lane line information display method, lane line information display device, electronic device, and computer-readable medium |
| CN113607185A (en) * | 2021-10-08 | 2021-11-05 | 禾多科技（北京）有限公司 | Lane line information display method, lane line information display device, electronic device, and computer-readable medium |
| WO2023124231A1 (en) * | 2021-12-31 | 2023-07-06 | 中国第一汽车股份有限公司 | Lidar-based road boundary detection method and apparatus |
| CN116047537B (en) * | 2022-12-05 | 2023-12-26 | 北京中科东信科技有限公司 | Road information generation method and system based on laser radar |
| CN116047537A (en) * | 2022-12-05 | 2023-05-02 | 北京中科东信科技有限公司 | Road information generation method and system based on laser radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106127113A (en) | A kind of road track line detecting method based on three-dimensional laser radar | |
| CN111079611B (en) | Automatic extraction method for road surface and marking line thereof | |
| CN105160309B (en) | Three lanes detection method based on morphological image segmentation and region growing | |
| CN101807352B (en) | Method for detecting parking stalls on basis of fuzzy pattern recognition | |
| CN104792792A (en) | Stepwise-refinement pavement crack detection method | |
| CN106199558A (en) | Barrier method for quick | |
| CN106951879A (en) | Multiple features fusion vehicle checking method based on camera and millimetre-wave radar | |
| CN103854320A (en) | Automatic vehicle type identification device and method based on laser radar | |
| CN104392212A (en) | Method for detecting road information and identifying forward vehicles based on vision | |
| CN105260699A (en) | Lane line data processing method and lane line data processing device | |
| CN102693423A (en) | Method for precise positioning of license plate in strong light conditions | |
| CN102073852A (en) | Multiple vehicle segmentation method based on optimum threshold values and random labeling method for multiple vehicles | |
| CN110197173B (en) | Road edge detection method based on binocular vision | |
| CN103136528A (en) | Double-edge detection based vehicle license plate identification method | |
| CN105719283A (en) | Road surface crack image detection method based on Hessian matrix multi-scale filtering | |
| CN103077387B (en) | Carriage of freight train automatic testing method in video | |
| CN204895461U (en) | Skew early warning system in lane | |
| CN114359876B (en) | Vehicle target identification method and storage medium | |
| CN109870458B (en) | Pavement crack detection and classification method based on three-dimensional laser sensor and bounding box | |
| Zhang et al. | Rapid inspection of pavement markings using mobile LiDAR point clouds | |
| CN202134079U (en) | Unmanned vehicle lane marker line identification and alarm device | |
| CN102393902A (en) | Vehicle color detection method based on H_S two-dimensional histogram and regional color matching | |
| CN113569915A (en) | Multi-strategy rail transit obstacle identification method based on laser radar | |
| CN106529404A (en) | Imaging principle-based recognition method for pilotless automobile to recognize road marker line | |
| CN105718964A (en) | Transmission line vibration damper visual detection 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161116 |