CN107193278B - Drivable area identification method based on positioning image and map matching - Google Patents
Drivable area identification method based on positioning image and map matching Download PDFInfo
- Publication number
- CN107193278B CN107193278B CN201710318257.5A CN201710318257A CN107193278B CN 107193278 B CN107193278 B CN 107193278B CN 201710318257 A CN201710318257 A CN 201710318257A CN 107193278 B CN107193278 B CN 107193278B
- Authority
- CN
- China
- Prior art keywords
- image
- ramp
- positioning
- camera
- map
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 239000000284 extract Substances 0.000 claims abstract description 10
- 238000002955 isolation Methods 0.000 claims abstract description 9
- 230000004927 fusion Effects 0.000 claims abstract description 3
- 230000008859 change Effects 0.000 claims description 2
- 238000005192 partition Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0251—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a travelable area identification method based on positioning image and map matching, which comprises the following steps: 1) when the autonomous vehicle enters the underground parking ramp for unmanned driving, the position of the vehicle in the ramp at the moment can be obtained by a positioning system in the autonomous vehicle. 2) The travelable area identification system extracts front ramp information of the current position from the high-precision map according to the position obtained by the positioning system; and simultaneously, the travelable region identification system extracts the image in the current vehicle camera. 3) And performing point matching on the image extracted from the high-precision map and the image obtained by the camera, and inputting the result of image matching and fusion into a travelable area identification system so as to identify the wall, the isolation facility and other vehicles in the front area. The method and the system better solve the problem of identifying the driving area in the ramp for automatic driving in the area of the underground parking lot in the future, have strong universality and have higher identification accuracy and real-time performance.
Description
Technical Field
The invention relates to the field of automatic driving, in particular to a travelable area identification method based on positioning image and map matching.
Background
More and more vehicle enterprises and internet companies are intensively equipped with automatic driving technologies, and at present, some primary automatic driving vehicles are reported by various companies.
However, to realize full-condition automatic driving, due to the complexity and unpredictability of the working conditions and the limitation of the current technology, the full-condition automatic driving in the real sense is hardly developed in a large breakthrough in the near future. Like google corporation, full autopilot is fraudulently motivated even though autopilot vehicles have been tested for long distances on actual highways.
At present, the automatic driving product is difficult to land, so that the research on the automatic driving fire heat is embarrassed, and therefore, the automatic driving product urgently needs a breakthrough, and the research on the automatic driving has a practical significance. Since the automatic driving under all conditions cannot be realized immediately, the automatic driving in a local area is not difficult to realize due to simple environmental structure. Among the local area automatic driving techniques, the parking lot autonomous parking technique is the most promising.
In view of the above, it is necessary to provide a location-based image and map matching drivable area identification method suitable for an underground parking lot ramp in a parking lot autonomous parking technology, so as to lay the foundation for future underground parking lot autonomous parking technologies.
Disclosure of Invention
The invention provides a travelable area identification method based on positioning image and map matching and suitable for an underground parking lot ramp. In the underground parking lot autonomous parking technology, the premise of enabling a vehicle to enter the underground parking lot from an entrance of the underground parking lot and finish parking is that the autonomous vehicle can automatically enter and exit a ramp of the underground parking lot, so that automatic driving of the ramp is a necessary premise for finishing autonomous parking. Since the vehicle travels on a slope in a curved room, the determination of the traveling environment in front of the vehicle is an important aspect to solve the problem of safe traveling due to the presence of both side walls and isolation facilities.
In order to achieve the purpose, the technical scheme provided by the invention is as follows:
the invention relates to a travelable area recognition method based on positioning of images and map matching of an underground parking lot ramp, which is based on the positioning of a known vehicle in the ramp, and utilizes the matching of the images shot by a camera and a high-precision map of the ramp with the known positioning to obtain the travelable area of a front ramp and prevent an autonomous vehicle from touching the wall or isolation facilities in the ramp and other vehicles in the ramp, and the method specifically comprises the following processes:
1) when the autonomous vehicle enters the underground parking ramp for unmanned driving, the position of the vehicle in the ramp at the moment can be obtained by a positioning system in the autonomous vehicle.
2) The travelable area identification system extracts front ramp information of the current position from the high-precision map according to the position obtained by the positioning system; and simultaneously, the travelable region identification system extracts the image in the current vehicle camera.
3) And performing point matching on the image extracted from the high-precision map and the image obtained by the camera, and inputting the result of image matching and fusion into a travelable area identification system so as to identify the wall, the isolation facility and other vehicles in the front area.
Has the advantages that: the invention provides a travelable area identification system based on positioning image and map matching and suitable for an underground parking lot ramp, which has the following advantages compared with the existing system:
(1) the existing identification method of the front driving area comprises radar detection, camera extraction and map navigation, wherein the radar detection can accurately detect the distance of an obstacle, but when the vehicle is in a slope with a steep slope, due to the physical characteristics of the radar, the vehicle cannot completely detect the scene in the slope; the camera extracts the front road characteristics, and the limitation exists in the ramp with walls on two sides; there is non-real time in map navigation in indoor ramps. Therefore, the invention better solves the problem of identifying the driving area in the slope which is automatically driven in the area of the underground parking lot in the future.
(2) The invention has simple structure and strong universality.
(3) The method for identifying the driving area based on the positioning image and map matching has the following advantages: firstly, the disadvantage that the camera is used in a three-dimensional indoor environment with walls on two sides is avoided, and the advantage of rapidity of finding the barrier is brought into play; secondly, the non-real-time property of the digital map for establishing the travelable area identification is avoided, and the advantage of the accuracy of the digital map in a curved ramp with walls on two sides and isolation is also played.
Drawings
Fig. 1 is a schematic view of a vehicle camera mounting position.
Fig. 2 is a travelable region identification technology route diagram.
Wherein, 1-the center position of the front bumper of the autonomous vehicle.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and specific examples, which should be construed as merely illustrative of the preferred embodiments and concepts thereof, and not limitative of the remainder of the disclosure.
The invention provides a drivable area recognition method based on positioning image and map matching and suitable for an underground parking lot ramp, which is characterized in that a positioning coordinate of a current vehicle in the ramp is obtained by an autonomous vehicle positioning system, the map data in front of the current position is extracted from a ramp high-precision map based on the positioning coordinate, the recognition system extracts an image from a camera at the position right in the middle of a front bumper of an autonomous vehicle at the moment, the map data of the current position and the camera image are subjected to point matching, the drivable area of the front ramp is obtained, and walls, isolation facilities and other vehicles in the ramp are recognized, so that the recognition accuracy and the real-time performance are higher.
Fig. 1 is a schematic diagram of the installation position of a camera according to the present invention, the camera is installed at the center position 1 of the front bumper of an autonomous vehicle, and the position 1 is used as a base point for matching map data and image data.
FIG. 2 is a technical route map for location-based image and map-matching drivable area identification for an underground parking lot ramp, requiring a vehicle location system to output location coordinates of a vehicle, generate a vehicle rear axle center position and output the location coordinates to a digital map, while being inverse-transilluminated by an image of a front bumper center camera. The method comprises the following specific processes:
1) when the autonomous vehicle enters the underground parking lot ramp for unmanned driving, the central position of the rear axle of the vehicle is obtained by a positioning system in the autonomous vehicle, and the overlooking angle of the map with the front bumper of the autonomous vehicle as a base point can be obtained by combining the geometric parameters of the appearance of the vehicle.
2) The positioning data output by the positioning system is sent to the digital map, and the travelable area identification system extracts data of a wall and a partition in the digital map in front of the positioning point, so that the front slope map overlooking data with the front bumper center of the autonomous vehicle as a base point is generated.
3) At the moment, a camera at the center of the front bumper collects a front ramp image, the front ramp image output by the calibrated camera is subjected to inverse perspective change, and a front ramp top view image generated by camera data is generated.
4) And performing point matching algorithm superposition on the forward ramp map overlook data generated in the digital map and the forward ramp overlook image of the camera, inputting a result generated by image point matching into a travelable area identification system, and identifying walls, isolation facilities and other vehicles in the forward ramp area.
The travelable region identification is based on positioning, and provides a travelable region identification method based on image point matching, so that a vehicle is prevented from colliding with a wall in a ramp, an isolation facility or other vehicles.
The examples are specific illustrations of possible embodiments of the present invention, and they are not intended to limit the scope of the present invention, and equivalent embodiments or modifications without departing from the technical spirit of the present invention are intended to be included in the scope of the present invention.
Claims (2)
1. The travelable area identification method based on the positioning image and map matching is characterized by comprising the following steps of:
1) when the autonomous vehicle enters the ramp of the underground parking lot for unmanned driving, a positioning system in the autonomous vehicle is used for positioning, and the position of the vehicle in the ramp at the moment can be obtained;
the positioning system in the step 1) is used for positioning specifically the central position of the rear axle of the vehicle, and further the overlooking angle of a map with the front bumper of the autonomous vehicle as a base point is obtained by combining the geometric parameters of the appearance of the vehicle;
2) according to the position obtained by the positioning system, the travelable area identification system extracts front ramp information of the current position from the high-precision map; meanwhile, the travelable area identification system extracts the image in the current vehicle camera;
the concrete realization of the step 2) comprises the following steps: the positioning data output by the positioning system is sent to a digital map, and the travelable area identification system extracts data of a wall and a partition in the digital map in front of a positioning point and generates forward slope map overlooking data with a front bumper center of the autonomous vehicle as a base point;
the concrete implementation of step 2) also includes: collecting a front ramp image by a camera, carrying out inverse perspective change on the front ramp image output by the calibrated camera, and generating a front ramp top view image generated by camera data;
3) and superposing the image extracted from the high-precision map and the image obtained by the camera by using a point matching algorithm, and inputting the result of image matching fusion into a travelable area identification system so as to identify the wall, the isolation facility and other vehicles in the front area.
2. The method of claim 1, wherein the camera is mounted in a front bumper center location.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710318257.5A CN107193278B (en) | 2017-05-08 | 2017-05-08 | Drivable area identification method based on positioning image and map matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710318257.5A CN107193278B (en) | 2017-05-08 | 2017-05-08 | Drivable area identification method based on positioning image and map matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107193278A CN107193278A (en) | 2017-09-22 |
| CN107193278B true CN107193278B (en) | 2021-06-18 |
Family
ID=59873836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710318257.5A Active CN107193278B (en) | 2017-05-08 | 2017-05-08 | Drivable area identification method based on positioning image and map matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107193278B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109556615B (en) * | 2018-10-10 | 2022-10-04 | 吉林大学 | Driving map generation method based on multi-sensor fusion cognition of automatic driving |
| CN109765903B (en) * | 2019-02-28 | 2022-03-08 | 北京智行者科技有限公司 | Automatic driving planning method |
| CN110377029A (en) * | 2019-06-27 | 2019-10-25 | 北京汽车集团有限公司 | The control method and device of Vehicular automatic driving |
| CN110631598A (en) * | 2019-08-06 | 2019-12-31 | 北京百度网讯科技有限公司 | Method, device and equipment for evaluating vehicle positioning accuracy and computer readable storage medium |
| CN111559259B (en) * | 2020-04-16 | 2022-07-22 | 江苏大学 | ROS-based high-efficiency wireless charging intelligent trolley with laser navigation function and control method |
| CN113335306A (en) * | 2021-06-02 | 2021-09-03 | 上海追势科技有限公司 | Automatic driving method for vehicles at parking lot entrance and exit and cross-floor entrance and exit |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408771A (en) * | 2014-11-12 | 2015-03-11 | 东北大学 | Underground mine ramp constructing method based on three-dimensional model |
| CN105073542A (en) * | 2013-04-01 | 2015-11-18 | 朴秀旼 | Automatic driving system for vehicle |
| CN105698812A (en) * | 2016-01-15 | 2016-06-22 | 武汉光庭科技有限公司 | Lane line detecting system and method based on safe driving map and cameras on two sides during automatic driving |
| CN106527427A (en) * | 2016-10-19 | 2017-03-22 | 东风汽车公司 | Automatic driving sensing system based on highway |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102015206144B4 (en) * | 2015-04-07 | 2022-10-06 | Volkswagen Aktiengesellschaft | Method and device for safely parking a vehicle |
| KR101714185B1 (en) * | 2015-08-05 | 2017-03-22 | 엘지전자 주식회사 | Driver Assistance Apparatus and Vehicle Having The Same |
| CN105718865A (en) * | 2016-01-15 | 2016-06-29 | 武汉光庭科技有限公司 | System and method for road safety detection based on binocular cameras for automatic driving |
| CN105783936B (en) * | 2016-03-08 | 2019-09-24 | 武汉中海庭数据技术有限公司 | For the road markings drawing and vehicle positioning method and system in automatic Pilot |
| CN105761533B (en) * | 2016-03-28 | 2018-06-29 | 江苏大学 | A kind of pilotless automobile parking stall planing method |
| CN105946853B (en) * | 2016-04-28 | 2018-05-29 | 中山大学 | The system and method for long range automatic parking based on Multi-sensor Fusion |
-
2017
- 2017-05-08 CN CN201710318257.5A patent/CN107193278B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105073542A (en) * | 2013-04-01 | 2015-11-18 | 朴秀旼 | Automatic driving system for vehicle |
| CN104408771A (en) * | 2014-11-12 | 2015-03-11 | 东北大学 | Underground mine ramp constructing method based on three-dimensional model |
| CN105698812A (en) * | 2016-01-15 | 2016-06-22 | 武汉光庭科技有限公司 | Lane line detecting system and method based on safe driving map and cameras on two sides during automatic driving |
| CN106527427A (en) * | 2016-10-19 | 2017-03-22 | 东风汽车公司 | Automatic driving sensing system based on highway |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107193278A (en) | 2017-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107193278B (en) | Drivable area identification method based on positioning image and map matching | |
| CN105946853B (en) | The system and method for long range automatic parking based on Multi-sensor Fusion | |
| US10024965B2 (en) | Generating 3-dimensional maps of a scene using passive and active measurements | |
| Laugier et al. | Probabilistic analysis of dynamic scenes and collision risks assessment to improve driving safety | |
| US11250697B2 (en) | Missing traffic face detector | |
| JP2022106924A (en) | Device and method for autonomous self-position estimation | |
| US20190278273A1 (en) | Odometry system and method for tracking traffic lights | |
| CN109443369A (en) | The method for constructing sound state grating map using laser radar and visual sensor | |
| US20200333466A1 (en) | Ground intensity lidar localizer | |
| CN107422730A (en) | The AGV transportation systems of view-based access control model guiding and its driving control method | |
| Yoneda et al. | Urban road localization by using multiple layer map matching and line segment matching | |
| CN108628324A (en) | Unmanned vehicle navigation method, device, equipment based on map vector and storage medium | |
| CN112518739A (en) | Intelligent self-navigation method for reconnaissance of tracked chassis robot | |
| Aldibaja et al. | LIDAR-data accumulation strategy to generate high definition maps for autonomous vehicles | |
| Revilloud et al. | An improved approach for robust road marking detection and tracking applied to multi-lane estimation | |
| CN112572431A (en) | Parking lot driving assistance method, system, equipment and storage medium | |
| Gustafsson et al. | Navigation and tracking of road-bound vehicles | |
| Hara et al. | Vehicle localization based on the detection of line segments from multi-camera images | |
| US20190293444A1 (en) | Lane level accuracy using vision of roadway lights and particle filter | |
| CN111539305B (en) | Map construction method and system, vehicle and storage medium | |
| Jiang et al. | Precise vehicle ego-localization using feature matching of pavement images | |
| Chipka et al. | Estimation and navigation methods with limited information for autonomous urban driving | |
| CN115424468A (en) | Parking stall detecting system based on many cameras fuse | |
| Chipka et al. | Autonomous urban localization and navigation with limited information | |
| TW202115616A (en) | Map data positioning system and method using roadside feature recognition having the advantages of low data volume, low computational complexity, high reliability |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231008 Address after: 230000 Room 203, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee after: Hefei Jiuzhou Longteng scientific and technological achievement transformation Co.,Ltd. Address before: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee before: Dragon totem Technology (Hefei) Co.,Ltd. Effective date of registration: 20231008 Address after: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee after: Dragon totem Technology (Hefei) Co.,Ltd. Address before: Zhenjiang City, Jiangsu Province, 212013 Jingkou District Road No. 301 Patentee before: JIANGSU University |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231117 Address after: Building A1, Bainiaohe Digital Town, Haohuahong Town, Huishui County, Qiannan Buyi and Miao Autonomous Prefecture, Guizhou Province, 550600 Patentee after: Guizhou Mengdong Technology Co.,Ltd. Address before: 230000 Room 203, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee before: Hefei Jiuzhou Longteng scientific and technological achievement transformation Co.,Ltd. |
|
| TR01 | Transfer of patent right |