CN107192994A - Multi-line laser radar mass cloud data is quickly effectively extracted and vehicle, lane line characteristic recognition method - Google Patents
Multi-line laser radar mass cloud data is quickly effectively extracted and vehicle, lane line characteristic recognition method Download PDFInfo
- Publication number
- CN107192994A CN107192994A CN201610145459.XA CN201610145459A CN107192994A CN 107192994 A CN107192994 A CN 107192994A CN 201610145459 A CN201610145459 A CN 201610145459A CN 107192994 A CN107192994 A CN 107192994A
- Authority
- CN
- China
- Prior art keywords
- laser radar
- vehicle
- cloud data
- line laser
- automatic driving
- 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
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/491—Details of non-pulse systems
- G01S7/493—Extracting wanted echo signals
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
Automatic driving car gathers three-dimensional mass cloud data by multi-line laser radar（Point cloud）It is per second up to hundreds of MB, the space of data storage, the ageing of processing require high to computing resource.The present invention proposes that a kind of multi-line laser radar three dimensional point cloud that is directed to quickly effectively extracts and do not influence vehicle, the method for lane line feature identification：R layer cloud datas in the automatic driving car area-of-interest that multi-line laser radar is gathered in vehicle multilayer cloud data are extracted by adaptive distance.In addition, it is also proposed that track line method is extracted based on distance and the light echo intensity of angle correction.Requirement present invention reduces mass cloud data processing to computer hardware, save memory space and cost, the ageing of Point Cloud Processing is accelerated, vehicle in automatic driving car area-of-interest, lane line cloud data is realized and quickly effectively extracts and feature identification.The present invention is applied to a variety of urban roads, and antijamming capability is stronger, and algorithm robustness is preferable.
Description
Technical field
The present invention is a technology for being directed to automatic driving car environment sensing field, the three of multi-line laser radar rotating acquisition
It is magnanimity to tie up cloud data amount, per second up to hundreds of MB.Therefore, the present invention can reduce the processing of magnanimity laser radar point cloud data
Requirement to computer hardware, reduces the consumption to computing resource, saves memory space and calculating time.It can realize many
Quick effective extraction of line laser radar three-dimensional mass cloud data and do not influence the feature identification of vehicle；In addition, many line lasers
It is also automatic driving car environment sensing field that radar valid data extract lane line based on distance and the light echo intensity of angle correction
Key technology.The present invention is that a kind of information is quickly effectively extracted and treatment technology.
Background technology
Real-time and accurately identification automatic driving car traveling ahead vehicle location, velocity information and lane line are vehicle anticollisions
The premise that the driving safety such as early warning, adaptive learning algorithms system is realized.The primary data information (pdi) of laser radar collection mainly includes：
Id, laser emission point range-to-go, light echo intensity where laser beam flying etc..Pass through laser emission point range-to-go
And the record of system GPS, INS calculates the 3 d space coordinate of scanned target in area-of-interest around automatic driving car,
Obtain the three dimensional point cloud of target in automatic driving car area-of-interest.These cloud datas include a large amount of influence vehicle mesh
The redundancy and noise of identification are marked, obstacle recognition is being carried out using three dimensional point cloud with being needed before classification to cloud data
Pre-processed.The pretreatment of cloud data is main including error correction and the noise data for removing point cloud etc..Many line lasers
The original each data of radar are surrounded by 12 groups of multiple lasers and are excited resulting data, and the time for obtaining a packet isMicrosecond, so each second, available point data was
It is individual.The data volume that thus laser radar data is produced during the information such as surrounding obstacles object location, speed are obtained reaches GB
Even how TB ranks, reduce requirement of the laser radar mass cloud data processing to computer hardware, reduce computing resource
How quickly consumption and effective extraction process real-time to magnanimity three dimensional point cloud to obstacle in automatic driving car area-of-interest
Thing identification is particularly important.Track line position accurately identifying and is accurately fitted, to lane departure warning, vehicle safety auxiliary etc.
System is also particularly important.At present, the detection of lane line is based primarily upon vision system, poor anti jamming capability, easily by environment etc. because
The influence of element；And not only antijamming capability is relatively strong, influenceed smaller by factors such as environment for the lane detection based on multi-thread radar
And precision is higher, real-time is stronger.
The content of the invention
Present invention aims at the not enough problem solved present in prior art, it is proposed that a kind of multi-line laser radar magnanimity
Three dimensional point cloud quickly effectively extracts and does not influence the method for vehicle characteristics identification and the light echo based on distance and angle correction
The method that intensity extracts lane line.Car in the automatic driving car area-of-interest that the present invention can be gathered directly to multi-line laser radar
Multi-layer three-dimension mass cloud data carries out that adaptive distance is quick effectively to be extracted and vehicle characteristics, the identification of lane line.Save
Calculating storage resource, reduces calculating carrying cost, improves that data processing is ageing, can in relatively low computer hardware
It is upper to realize.
Brief description of the drawings
Fig. 1 is the flow chart that cloud data of the present invention quickly effectively extracts implementation technology.
Fig. 2 is the flow chart of Lane detection implementation technology of the present invention.
Fig. 3 is the principle flow chart that cloud data of the present invention saves storage.
Fig. 4 is of the invention adaptive apart from effective extracting method application effect figure.
Fig. 5 present invention recognizes lane line design sketch after being corrected according to distance and angle to light echo intensity.
Embodiment
As shown in figure 1, the present invention proposes a kind of quick effective extraction of laser radar mass cloud data and does not influence car
, the method for lane line feature identification, it includes：The three-dimensional memory module of laser radar point cloud data, it is three-dimensional in cloud data
Adaptive distance calculates the r layer point clouds in vehicle multilayer cloud data in automatic driving car area-of-interest on the basis of coordinate
Data and do not influence the identification of vehicle characteristics and lane line is recognized according to distance and the light echo intensity of angle correction.Complete skill
Art flow is as follows：
Set up the three-dimensional storage matrix of laser radar point cloud data：Each laser radar point cloud data includes certain space reference
The information, wherein three-dimensional space such as three-dimensional space position coordinate (x, y, z) and light echo intensity (density), echo times under system
Between co-ordinate position information be laser radar magnanimity three dimensional point cloud more important information.First according to x, y-coordinate determines week
The distance of vehicle and automatic driving car is enclosed, then further according to automatic driving car front bumper, by surrounding vehicles in automatic driving car
Position be divided into 6 area-of-interests：It is left front, left back, just before, just after, it is right before, it is right after；Driven according to laser radar at nobody
The setting height(from bottom) of car roof is sailed, is drawn by triangle geometric knowledge, every layer of ray maximum distance formula in front of automatic driving car car body：That is, the maximum radius of radar ray annulus；It is adjacentThe distance between bar x-ray angle
Difference value equation：That is, calculate in obtained Multi Slice Mode lineLayer
Elevation where scan line.In formulaIt is the height that radar is arranged on automatic driving car,It isLayer ray and horizontal vertical
Angle.Basis firstThe scan blind spot of radar is found, blind area is filtered.Multi-line laser radar is rotation sweep detecting obstacles
Thing, scan line is into annular shape on the ground, in each scanning angle, is sorted according to vertical direction, right from top to bottom
Multi Slice Mode ray label again, is designated as respectively.The three-dimensional point cloud number obtained according to Laser Radar Scanning
According to the numerical value for projecting to X-Y plane, calculating is obtained in Multi Slice Mode lineLayer scan line, formula：
In formulaThe laser of radar is represented to the y-coordinate of scanning target,Represent adjacentLayer scan line it is vertical
Distance（TypicallyFluctuated up and down near vehicle stringcourse）, because contour of the vehicle and profile are the principal character of identification vehicle, root
The r layer cloud datas in the surrounding vehicles multi-layer three-dimension cloud data for extracting Laser Radar Scanning are calculated according to adaptive distance,
This r layers of cloud data is enough to identify the feature of vehicle（L-shaped）.The r layer cloud datas of extraction are projected into X-Y plane can be clear
It is clear to see L-shaped（The right forefoot area of automatic driving car）, but it is due to blocking L-shaped and may being divided for barrier, therefore with poly-
The method that class merges is handled, and then can improve the discrimination of vehicle characteristics.The r layers extracted according to adaptive range formula
Vehicle cloud data is exactly vehicle stringcourse position, not only can substantially represent the vehicle characteristics for projecting to X-Y plane（L-shaped）And
Even and if the defective light echo intensity that can be combined with of Cluster merging carries out integrating Cluster merging correction.
Similarly, it is necessary in each scan angle before the barrier three-dimensional surface light echo intensity according to distance and angle correction
On degree, sorted, from top to bottom to Multi Slice Mode ray again label, be designated as respectively according to vertical direction.Root
According to distance and the barrier three-dimensional surface light echo strength formula of angle correction：
X, y, z represents the three-dimensional space position coordinate of the barrier of Laser Radar Scanning,
Represent certain of radarShu Jiguang to scanning target distance,Every layer of laser beam and horizontal vertical angle are represented,Represent
Certain 1 beam laser of radar to scanning target incidence angle,The light echo intensity of certain 1 beam laser scanning target of radar is represented,
、For according to multi-line laser radar three dimensional point cloud parameter to be fitted.Finally utilize K domain algorithms coupleCluster extracts car
Diatom light echo intensity.Instantiation of the present invention is as shown in Figure 4：Left figure represents the three-dimensional mass cloud data of original multi-line laser radar
Project to point cloud chart picture formed by X-Y plane；It is three-dimensional that right figure represents adaptive distance effectively extraction multi-line laser radar of the invention
Vehicle characteristics formed by X-Y plane are projected to after cloud data（L-shaped）.Comparative analysis is found：Right figure cloud data is considerably less than
Left figure original point cloud data, reduces requirement of the multi-line laser radar magnanimity initial data to computing resource, saves calculating and deposit
Store up resource space（Memory space about 16.8M or so needed for the three-dimensional mass cloud data of an original frame for left figure computer acquisition,
And right figure is by memory space needed for quick effectively extraction cloud data method a later frame three dimensional point cloud proposed by the present invention
About 1.2M or so）, calculating carrying cost is reduced, the ageing of laser radar detection of obstacles is improved（Left figure computer
About 3s or so the time required to original magnanimity three dimensional point cloud is handled, and right figure is by quick effectively extraction proposed by the present invention
The calculating time shorten to about 0.8s or so after cloud data method）；It is as shown in Figure 5 that the present invention extracts lane line example：Left figure
Represent the initial data of multi-thread radar collection and to projecting to point cloud chart picture formed by X-Y plane after data prediction（Can not be accurate
It is really clear to recognize lane line）；Right figure represents the car of light echo intensity identification of the present invention based on multi-thread distance by radar and angle correction
Diatom, red rectangle frame represents the cluster to lane line light echo intensity according to light echo intensity threshold；Dotted line represents many line laser thunders
Fitting is made up up to blind area inside lane line.
Quick effective extraction described above for laser radar mass cloud data and do not influence the feature identification of vehicle
And be described in detail according to distance and the light echo intensity of angle correction identification lane line, but those skilled in the art is
It can be appreciated that be all possible in the various improvement of the scope of the invention, addition and replacement, and all will in the right of the present invention
Ask in limited protection domain.
Claims (4)
1. quick effective extraction of multi-line laser radar magnanimity three dimensional point cloud amount and do not influence vehicle, lane line feature identification
Method, it includes：Multi-line laser radar magnanimity three dimensional point cloud memory module；Automatic driving car is based on multi-line laser radar
The extraction of r layer cloud datas in surrounding's area-of-interest of collection in vehicle multilayer cloud data；Using based on away from walk-off angle
The light echo intensity of degree correction extracts lane line.
2. according to claim 1, multi-line laser radar cloud data memory module is characterized in that：Multi-line laser radar point
Cloud data hierarchy（Multilayer）Memory module.
3. according to the method described in claim 1, vehicle multilayer in area-of-interest around multi-line laser radar automatic driving car
R layers cloud data in three dimensional point cloud, which is extracted, to be characterised by：According to multi-line laser radar automatic driving car roof peace
Holding position, adaptive distance, which is calculated, to be obtained in automatic driving car area-of-interest（Front and rear each m meters, left and right is each n meters）The R layers of vehicle
In three dimensional point cloud r layers cloud data ()；The origin of coordinates and automatic driving car sense using initialization data
The three dimensional point cloud calculating coordinate of vehicle in interest region.
4. according to claim 1, the span of light echo intensity is 0 ~ 255, the light echo intensity model of different classes of barrier
It is different to enclose, but also has cross-coincidence each other；Even if similar barrier due to laser radar by distance, atmospheric attenuation,
Still there is relatively large deviation in the influence light echo intensity level for scanning the factors such as the geometrical property of body surface；Therefore need according to distance
Target's feature-extraction is carried out with the threshold value determined after angle correction, the light echo strength range of lane line finally can be more accurately extracted
It is。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610145459.XA CN107192994A (en) | 2016-03-15 | 2016-03-15 | Multi-line laser radar mass cloud data is quickly effectively extracted and vehicle, lane line characteristic recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610145459.XA CN107192994A (en) | 2016-03-15 | 2016-03-15 | Multi-line laser radar mass cloud data is quickly effectively extracted and vehicle, lane line characteristic recognition method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107192994A true CN107192994A (en) | 2017-09-22 |
Family
ID=59871743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610145459.XA Pending CN107192994A (en) | 2016-03-15 | 2016-03-15 | Multi-line laser radar mass cloud data is quickly effectively extracted and vehicle, lane line characteristic recognition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107192994A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610524A (en) * | 2017-11-02 | 2018-01-19 | 济南浪潮高新科技投资发展有限公司 | A kind of method and device that parking position Intelligent Recognition is carried out using laser radar |
| CN108198241A (en) * | 2018-02-02 | 2018-06-22 | 北京卡雷尔机器人技术有限公司 | A kind of method and apparatus of 3-D view structure |
| CN108459319A (en) * | 2018-03-13 | 2018-08-28 | 燕山大学 | A kind of quick scanning system of vehicle running region Terrain Elevation |
| CN108647646A (en) * | 2018-05-11 | 2018-10-12 | 北京理工大学 | The optimizing detection method and device of low obstructions based on low harness radar |
| CN108732586A (en) * | 2018-05-31 | 2018-11-02 | 山东理工大学 | A kind of super large Three Dimensional Ground laser scanning original point cloud Spatial Rules method |
| CN109100741A (en) * | 2018-06-11 | 2018-12-28 | 长安大学 | A kind of object detection method based on 3D laser radar and image data |
| CN109613553A (en) * | 2018-12-18 | 2019-04-12 | 歌尔股份有限公司 | The method, apparatus and system of physical quantities in scene are determined based on laser radar |
| CN110109138A (en) * | 2019-01-31 | 2019-08-09 | 浙江工业大学 | A kind of vehicle gabarit View Drawing method based on laser radar point cloud data |
| CN110363058A (en) * | 2018-03-26 | 2019-10-22 | 国际商业机器公司 | It is positioned using the three dimensional object for avoidance of one shot convolutional neural networks |
| CN110632617A (en) * | 2019-09-29 | 2019-12-31 | 北京邮电大学 | Laser radar point cloud data processing method and device |
| CN110645910A (en) * | 2019-09-02 | 2020-01-03 | 北京控制工程研究所 | Automatic workpiece three-dimensional size detection system and method based on laser scanning |
| 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 |
| US10769948B2 (en) | 2018-12-27 | 2020-09-08 | Industrial Technology Research Institute | Parking spot detection system and method thereof |
| CN112433198A (en) * | 2019-08-24 | 2021-03-02 | 苏州寻迹智行机器人技术有限公司 | Method for extracting plane from three-dimensional point cloud data of laser radar |
| CN113343835A (en) * | 2021-06-02 | 2021-09-03 | 合肥泰瑞数创科技有限公司 | Object identification method and system suitable for emergency rescue and storage medium |
| CN113534170A (en) * | 2020-04-20 | 2021-10-22 | 上海禾赛科技有限公司 | Lane line detection method, data processing unit and vehicle-mounted laser radar system |
| CN113635864A (en) * | 2021-07-27 | 2021-11-12 | 际络科技(上海)有限公司 | Cleaning method and device for vehicle-mounted laser radar, electronic equipment and storage medium |
| CN113734046A (en) * | 2021-08-17 | 2021-12-03 | 厦门星图安达科技有限公司 | Method, device and equipment for detecting personnel in vehicle location partition based on radar |
| CN113859228A (en) * | 2020-06-30 | 2021-12-31 | 上海商汤智能科技有限公司 | Vehicle control method and device, electronic equipment and storage medium |
| CN115038990A (en) * | 2020-01-31 | 2022-09-09 | 日产自动车株式会社 | Object recognition method and object recognition device |
| CN115985109A (en) * | 2022-10-17 | 2023-04-18 | 上海伯镭智能科技有限公司 | Unmanned mine car environment sensing method and system |
| CN117636135A (en) * | 2023-10-26 | 2024-03-01 | 内蒙古电力(集团)有限责任公司航检分公司 | Laser radar point cloud online data classification method and device based on edge calculation |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021954A (en) * | 2007-03-23 | 2007-08-22 | 东南大学 | Three-dimensional scanning point cloud compressing method |
| CN101914890A (en) * | 2010-08-31 | 2010-12-15 | 中交第二公路勘察设计研究院有限公司 | Airborne laser measurement-based highway reconstruction and expansion investigation method |
| CN102693319A (en) * | 2012-05-31 | 2012-09-26 | 北京拓维思科技有限公司 | Pyramid-based mass airborne laser radar point cloud storage method |
| CN102779280A (en) * | 2012-06-19 | 2012-11-14 | 武汉大学 | Traffic information extraction method based on laser sensor |
| CN105184852A (en) * | 2015-08-04 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Laser-point-cloud-based urban road identification method and apparatus |
-
2016
- 2016-03-15 CN CN201610145459.XA patent/CN107192994A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021954A (en) * | 2007-03-23 | 2007-08-22 | 东南大学 | Three-dimensional scanning point cloud compressing method |
| CN101914890A (en) * | 2010-08-31 | 2010-12-15 | 中交第二公路勘察设计研究院有限公司 | Airborne laser measurement-based highway reconstruction and expansion investigation method |
| CN102693319A (en) * | 2012-05-31 | 2012-09-26 | 北京拓维思科技有限公司 | Pyramid-based mass airborne laser radar point cloud storage method |
| CN102779280A (en) * | 2012-06-19 | 2012-11-14 | 武汉大学 | Traffic information extraction method based on laser sensor |
| CN105184852A (en) * | 2015-08-04 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Laser-point-cloud-based urban road identification method and apparatus |
Non-Patent Citations (1)
| Title |
|---|
| 骆社周 等: ""机载激光雷达森林叶面积指数反演研究"", 《地球物理学报》 * |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610524A (en) * | 2017-11-02 | 2018-01-19 | 济南浪潮高新科技投资发展有限公司 | A kind of method and device that parking position Intelligent Recognition is carried out using laser radar |
| CN108198241A (en) * | 2018-02-02 | 2018-06-22 | 北京卡雷尔机器人技术有限公司 | A kind of method and apparatus of 3-D view structure |
| CN108459319A (en) * | 2018-03-13 | 2018-08-28 | 燕山大学 | A kind of quick scanning system of vehicle running region Terrain Elevation |
| CN110363058B (en) * | 2018-03-26 | 2023-06-27 | 国际商业机器公司 | Three-dimensional object localization for obstacle avoidance using one-shot convolutional neural networks |
| CN110363058A (en) * | 2018-03-26 | 2019-10-22 | 国际商业机器公司 | It is positioned using the three dimensional object for avoidance of one shot convolutional neural networks |
| CN108647646B (en) * | 2018-05-11 | 2019-12-13 | 北京理工大学 | Low-beam radar-based short obstacle optimized detection method and device |
| CN108647646A (en) * | 2018-05-11 | 2018-10-12 | 北京理工大学 | The optimizing detection method and device of low obstructions based on low harness radar |
| CN108732586A (en) * | 2018-05-31 | 2018-11-02 | 山东理工大学 | A kind of super large Three Dimensional Ground laser scanning original point cloud Spatial Rules method |
| CN109100741A (en) * | 2018-06-11 | 2018-12-28 | 长安大学 | A kind of object detection method based on 3D laser radar and image data |
| CN109100741B (en) * | 2018-06-11 | 2020-11-20 | 长安大学 | Target detection method based on 3D laser radar and image data |
| CN109613553A (en) * | 2018-12-18 | 2019-04-12 | 歌尔股份有限公司 | The method, apparatus and system of physical quantities in scene are determined based on laser radar |
| US10769948B2 (en) | 2018-12-27 | 2020-09-08 | Industrial Technology Research Institute | Parking spot detection system and method thereof |
| CN110109138A (en) * | 2019-01-31 | 2019-08-09 | 浙江工业大学 | A kind of vehicle gabarit View Drawing method based on laser radar point cloud data |
| CN112433198A (en) * | 2019-08-24 | 2021-03-02 | 苏州寻迹智行机器人技术有限公司 | Method for extracting plane from three-dimensional point cloud data of laser radar |
| CN112433198B (en) * | 2019-08-24 | 2022-04-12 | 苏州寻迹智行机器人技术有限公司 | Method for extracting plane from three-dimensional point cloud data of laser radar |
| CN110645910A (en) * | 2019-09-02 | 2020-01-03 | 北京控制工程研究所 | Automatic workpiece three-dimensional size detection system and method based on laser scanning |
| CN110632617B (en) * | 2019-09-29 | 2021-11-02 | 北京邮电大学 | Laser radar point cloud data processing method and device |
| CN110632617A (en) * | 2019-09-29 | 2019-12-31 | 北京邮电大学 | Laser radar point cloud data processing method and device |
| CN115038990A (en) * | 2020-01-31 | 2022-09-09 | 日产自动车株式会社 | Object recognition method and object recognition device |
| 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 |
| CN113534170A (en) * | 2020-04-20 | 2021-10-22 | 上海禾赛科技有限公司 | Lane line detection method, data processing unit and vehicle-mounted laser radar system |
| CN113859228A (en) * | 2020-06-30 | 2021-12-31 | 上海商汤智能科技有限公司 | Vehicle control method and device, electronic equipment and storage medium |
| CN113343835B (en) * | 2021-06-02 | 2022-04-15 | 合肥泰瑞数创科技有限公司 | Object identification method and system suitable for emergency rescue and storage medium |
| CN113343835A (en) * | 2021-06-02 | 2021-09-03 | 合肥泰瑞数创科技有限公司 | Object identification method and system suitable for emergency rescue and storage medium |
| CN113635864A (en) * | 2021-07-27 | 2021-11-12 | 际络科技(上海)有限公司 | Cleaning method and device for vehicle-mounted laser radar, electronic equipment and storage medium |
| CN113635864B (en) * | 2021-07-27 | 2023-08-15 | 际络科技(上海)有限公司 | Vehicle-mounted laser radar cleaning method and device, electronic equipment and storage medium |
| CN113734046A (en) * | 2021-08-17 | 2021-12-03 | 厦门星图安达科技有限公司 | Method, device and equipment for detecting personnel in vehicle location partition based on radar |
| CN113734046B (en) * | 2021-08-17 | 2023-09-19 | 江苏星图智能科技有限公司 | Method, device and equipment for detecting personnel in vehicle position partition based on radar |
| CN115985109A (en) * | 2022-10-17 | 2023-04-18 | 上海伯镭智能科技有限公司 | Unmanned mine car environment sensing method and system |
| CN115985109B (en) * | 2022-10-17 | 2023-11-07 | 上海伯镭智能科技有限公司 | Unmanned mine car environment sensing method and system |
| CN117636135A (en) * | 2023-10-26 | 2024-03-01 | 内蒙古电力(集团)有限责任公司航检分公司 | Laser radar point cloud online data classification method and device based on edge calculation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107192994A (en) | Multi-line laser radar mass cloud data is quickly effectively extracted and vehicle, lane line characteristic recognition method | |
| US11854272B2 (en) | Hazard detection from a camera in a scene with moving shadows | |
| TWI722355B (en) | Systems and methods for correcting a high-definition map based on detection of obstructing objects | |
| CN108363065B (en) | Object detection system | |
| CN110531376B (en) | Obstacle detection and tracking method for port unmanned vehicle | |
| CN110443225B (en) | Virtual and real lane line identification method and device based on feature pixel statistics | |
| US11195028B2 (en) | Real-time simultaneous detection of lane marker and raised pavement marker for optimal estimation of multiple lane boundaries | |
| US8818702B2 (en) | System and method for tracking objects | |
| JP4246766B2 (en) | Method and apparatus for locating and tracking an object from a vehicle | |
| CN109583280A (en) | Lane detection method, apparatus, equipment and storage medium | |
| CN115049700A (en) | Target detection method and device | |
| US11295521B2 (en) | Ground map generation | |
| CN110674705A (en) | Small-sized obstacle detection method and device based on multi-line laser radar | |
| CN107796373A (en) | A kind of distance-finding method of the front vehicles monocular vision based on track plane geometry model-driven | |
| WO2023207845A1 (en) | Parking space detection method and apparatus, and electronic device and machine-readable storage medium | |
| US20190213427A1 (en) | Detection and Validation of Objects from Sequential Images of a Camera | |
| CN115327572A (en) | Method for detecting obstacle in front of vehicle | |
| CN107220632B (en) | Road surface image segmentation method based on normal characteristic | |
| CN116311127A (en) | Road boundary detection method, computer equipment, readable storage medium and motor vehicle | |
| CN114384492B (en) | Point cloud processing method and device for laser radar and storage medium | |
| US20220171975A1 (en) | Method for Determining a Semantic Free Space | |
| CN114084129A (en) | Fusion-based vehicle automatic driving control method and system | |
| US20230264938A1 (en) | Obstacle detector and obstacle detection method | |
| Álvarez et al. | Perception advances in outdoor vehicle detection for automatic cruise control | |
| CN118501859B (en) | Laser radar ground extraction method based on wire harness iteration |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170922 |
|
| WD01 | Invention patent application deemed withdrawn after publication |