CN113085838A - Parking space detection method and system based on multi-sensor fusion - Google Patents
Parking space detection method and system based on multi-sensor fusion Download PDFInfo
- Publication number
- CN113085838A CN113085838A CN202110361201.4A CN202110361201A CN113085838A CN 113085838 A CN113085838 A CN 113085838A CN 202110361201 A CN202110361201 A CN 202110361201A CN 113085838 A CN113085838 A CN 113085838A
- Authority
- CN
- China
- Prior art keywords
- parking space
- parking
- around
- image
- information
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/06—Automatic manoeuvring for parking
Abstract
The invention discloses a parking space detection method based on multi-sensor fusion, which comprises the following steps: (1) the acquired all-around view image is subjected to an all-around view image parking space detection algorithm to obtain coordinates of four corner points of the parking space; (2) mapping the obtained distance information of surrounding obstacles into coordinate points of the obstacles on the all-around image through an ultrasonic distance detection algorithm; (3) fusing the coordinate points of the barrier in the step (2) and the coordinates of the four corner points of the parking lot in the step (1) in a vehicle body coordinate system through a fusion algorithm, and judging whether parking is possible or not; the step (1) and the step (2) are carried out simultaneously. The parking space detection system comprises a panoramic image parking space detection module, an ultrasonic distance detection module and a fusion module. In the automatic parking process, the information of various vehicle-mounted sensors is fused, so that the parking space detection accuracy is improved; the system is applied to various parking lots, and the stability of the automatic parking system is improved.
Description
Technical Field
The invention relates to a parking space detection method and system, in particular to a parking space detection method and system based on multi-sensor fusion.
Background
In recent years, with the rapid increase of national economy, the rapid progress of society and the continuous enhancement of national strength, the working and living environment of people is greatly changed. Urban population is increasingly dense, families with private cars are more and more, parking spaces in parking lots are limited, car owners often spend a large amount of time on finding parking spaces to park, and the parking spaces are inconsistent with fast-paced urban life, so that a quick and effective automatic parking system is needed. The parking space detection method is an important component of an autonomous parking system and is also an important part of road intelligent traffic. At present, a uniform, effective and stable parking space detection scheme does not exist. Although a scheme for improving the parking lot to make the parking lot more intelligent is proposed recently, it is not easy to implement large-scale modification on the whole parking lot, and the scheme needs to be popularized and developed, so that the cost is huge.
Vehicle-mounted intelligence is rapidly developed, and part of results are well popularized. The existing automatic parking technology is to perform automatic parking after finding a parking space. Various intelligent parking lot efficient management schemes are provided, the parking lot map and the available parking spaces in the parking lot can be obtained, the stereoscopic vision technology is gradually mature, the functions of distance measurement, obstacle detection, road detection and the like can be achieved, and a foundation is laid for stable parking space detection. In the prior art, the parking space problem is still solved by a pure machine vision scheme, and the problems of calculation error, vision blind area and the like can exist.
Automatic parking systems are provided in many middle and high-end automobiles, but most of them are implemented based on radar. The radar is mainly used for detecting the distance between a vehicle and a surrounding obstacle, the cost is high, the acquired data are limited, and blind spots also exist in the data acquisition process in actual use. In the existing parking lot system, the information obtained based on the all-round camera can obtain the information of surrounding obstacles, but the obtained distance information is not accurate enough, and meanwhile, a vision blind area also exists.
Disclosure of Invention
The invention aims to provide a parking space detection method and system based on multi-sensor fusion, which are accurate in information acquisition and capable of reducing visual blind areas.
The technical scheme is as follows: the parking space detection method comprises the following steps:
(1) the acquired all-around view image is subjected to an all-around view image parking space detection algorithm to obtain coordinates of four corner points of the parking space;
(2) mapping the obtained distance information of surrounding obstacles into coordinate points of the obstacles on the all-around image through an ultrasonic distance detection algorithm;
(3) fusing the coordinate points of the barrier in the step (2) and the coordinates of the four corner points of the parking lot in the step (1) in a vehicle body coordinate system through a fusion algorithm, and judging whether parking is possible or not;
the step (1) and the step (2) are carried out simultaneously.
Further, in the step (1), images around the vehicle are collected through a plurality of cameras, and the images are spliced to obtain a panoramic image; processing the look-around image through a look-around image parking space detection algorithm to obtain the type of the parking space and the position point of the parking space, reasoning the four-angle-point coordinate of the complete parking space to obtain the area of the parking space, and converting the relevant coordinate point into a vehicle body coordinate system.
Further, in the step (2), the distance information acquired by the single ultrasonic wave is converted into a vehicle body coordinate system and is mapped to the all-round view image, and a plurality of obstacle coordinate points corresponding to obstacles around the vehicle are acquired; complete obstacle information around the vehicle is obtained by a plurality of ultrasonic waves.
Further, in the vehicle body coordinate system, the step (3) judges as follows: if the coordinate point of the obstacle is in the parking space area, the automatic parking is considered to be dangerous; if the obstacle coordinate point is not within the parking space area, it is considered that automatic parking is possible at this time.
A parking space detection system based on multi-sensor fusion comprises a panoramic image parking space detection module, an ultrasonic distance detection module and a fusion module;
the all-around image parking space detection module processes and identifies the all-around image to obtain parking space entrance information, parking space position information, parking space type information and vertical outline information of obstacles around the vehicle;
the ultrasonic distance detection module acquires distance condition information around the vehicle by using the ultrasonic sensor to detect the vertical profile. The distance information of the obstacles around the vehicle is accurate, and the inaccuracy of the distance information caused by the distortion of the all-round looking image is compensated.
The fusion module fuses distance information and all-round looking image information obtained by the ultrasonic sensor and judges whether the barrier is in the parking space.
Compared with the prior art, the invention has the following remarkable effects: 1. in the automatic parking process, information of various vehicle-mounted sensors is fused, so that the parking space detection accuracy is improved; 2. the system is applied to various parking lots, and the stability of the automatic parking system is improved.
Drawings
FIG. 1 is a general block diagram of the present invention;
FIG. 2 is a general flow chart of the present invention;
FIG. 3 is a schematic diagram of the calculation result of the fusion algorithm module according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and the detailed description.
On the basis of the existing detection method based on the all-round-looking camera, information of multiple sensors is fused. As shown in fig. 1, the general structure of the present invention includes three parts: look around image parking stall detection module, ultrasonic wave distance detection module and fuse the module.
The all-around image parking space detection module is used for processing and identifying the all-around image (overlooking and vertical to the ground) obtained by processing to obtain parking space entrance information, parking space position information, parking space type information (a vertical parking space, a horizontal parking space and an inclined parking space) and vertical outline information of obstacles around the vehicle;
the ultrasonic distance detection module is mainly used for acquiring distance condition information around the vehicle by using an ultrasonic sensor and detecting a vertical profile. The obtained distance information of the obstacles around the vehicle is accurate, and the inaccuracy of the distance information caused by distortion of the all-round looking image is compensated.
And the fusion module is mainly used for fusing distance information and all-round view image information obtained by the ultrasonic sensor, so that the stability of the parking space detection algorithm is improved, and the stability and effectiveness of the automatic parking system are further improved.
Fig. 2 is a general flow chart of the present invention, which includes the following steps:
step 1, collecting images around a vehicle through a plurality of cameras, and splicing to obtain a panoramic image. The all-around-view image parking space detection algorithm processes the all-around-view image to obtain the parking space type and the parking space slot position point, deduces the four-angle-point coordinate of the complete parking space and converts the related coordinate point into a vehicle body coordinate system.
The above step 1 and step 2 are performed simultaneously.
And 3, in the automatic parking process, the four-corner point coordinates of the parking space, namely the parking space area, are obtained through the step 1 by looking around the image parking space detection algorithm. And 2, mapping the obtained distance information of the surrounding obstacles into obstacle coordinate points on the all-around image through an ultrasonic distance detection algorithm. The fusion algorithm fuses distance information and all-round view image information obtained by the ultrasonic sensor and judges in a vehicle body coordinate system; the judgment principle is as follows: if the coordinate point of the obstacle is in a quadrangle (parking space area) formed by four corner points of the parking space, the automatic parking is considered to be dangerous at the moment, and the parking cannot be carried out; and judging that the coordinate point of the obstacle is not in a quadrangle (parking space area) formed by the four angular points of the parking space, and automatically parking.
Fig. 3 is a schematic diagram of the calculation result of the fusion algorithm of the present invention. And two parking spaces on the right side of the vehicle are drawn by looking around the parking space area obtained by the image parking space detection algorithm. When a certain obstacle exists on the ground, the ultrasonic distance detection algorithm can detect the distance information of the obstacle and convert the distance information into an obstacle coordinate point on the all-round view image. Whether the parking space can stop or not is judged by judging whether the obstacle coordinate point is in the parking space area or not.
Claims (5)
1. The parking space detection method based on multi-sensor fusion is characterized by comprising the following steps:
(1) the acquired all-around view image is subjected to an all-around view image parking space detection algorithm to obtain coordinates of four corner points of the parking space;
(2) mapping the obtained distance information of surrounding obstacles into coordinate points of the obstacles on the all-around image through an ultrasonic distance detection algorithm;
(3) fusing the coordinate points of the barrier in the step (2) and the coordinates of the four corner points of the parking lot in the step (1) in a vehicle body coordinate system through a fusion algorithm, and judging whether parking is possible or not;
the step (1) and the step (2) are carried out simultaneously.
2. The parking space detection method based on multi-sensor fusion of claim 1, wherein in the step (1), images around the vehicle are collected through a plurality of cameras, and the images are spliced to obtain a panoramic image; processing the look-around image through a look-around image parking space detection algorithm to obtain the type of the parking space and the position point of the parking space, reasoning the four-angle-point coordinate of the complete parking space to obtain the area of the parking space, and converting the relevant coordinate point into a vehicle body coordinate system.
3. The parking space detection method based on multi-sensor fusion of claim 1, wherein in the step (2), the distance information obtained by a single ultrasonic wave is converted into a vehicle body coordinate system and is mapped onto the all-round image, and a plurality of obstacle coordinate points corresponding to obstacles around the vehicle are obtained; complete obstacle information around the vehicle is obtained by a plurality of ultrasonic waves.
4. The parking space detection method based on multi-sensor fusion as claimed in claim 1, wherein the step (3) is implemented in a vehicle body coordinate system, and the following judgment is made: if the coordinate point of the obstacle is in the parking space area, the automatic parking is considered to be dangerous; if the obstacle coordinate point is not within the parking space area, it is considered that automatic parking is possible at this time.
5. A parking space detection system based on multi-sensor fusion is characterized by comprising a panoramic image parking space detection module, an ultrasonic distance detection module and a fusion module;
the all-around image parking space detection module processes and identifies the all-around image to obtain parking space entrance information, parking space position information, parking space type information and vertical outline information of obstacles around the vehicle;
the ultrasonic distance detection module acquires distance condition information around the vehicle by using the ultrasonic sensor and performs vertical contour detection;
the fusion module fuses distance information and all-round looking image information obtained by the ultrasonic sensor and judges whether the barrier is in the parking space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110361201.4A CN113085838A (en) | 2021-04-02 | 2021-04-02 | Parking space detection method and system based on multi-sensor fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110361201.4A CN113085838A (en) | 2021-04-02 | 2021-04-02 | Parking space detection method and system based on multi-sensor fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113085838A true CN113085838A (en) | 2021-07-09 |
Family
ID=76673308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110361201.4A Pending CN113085838A (en) | 2021-04-02 | 2021-04-02 | Parking space detection method and system based on multi-sensor fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113085838A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554882A (en) * | 2021-07-20 | 2021-10-26 | 阿波罗智联(北京)科技有限公司 | Method, apparatus, device and storage medium for outputting information |
| CN113920782A (en) * | 2021-10-08 | 2022-01-11 | 安徽江淮汽车集团股份有限公司 | Multi-sensor fusion method applied to parking space detection |
| CN114125253A (en) * | 2021-12-27 | 2022-03-01 | 上海映驰科技有限公司 | Mechanical parking space detection system and detection method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103600707A (en) * | 2013-11-06 | 2014-02-26 | 同济大学 | Parking position detecting device and method of intelligent parking system |
| KR20150027527A (en) * | 2013-09-04 | 2015-03-12 | 현대모비스 주식회사 | Parking assistance system for vehicle and parking assistant method |
| US20170039439A1 (en) * | 2015-08-03 | 2017-02-09 | Hyundai Mobis Co., Ltd. | Parking space recognition apparatus and method of controlling the same |
| US20170036695A1 (en) * | 2015-08-03 | 2017-02-09 | Hyundai Mobis Co., Ltd. | Parking assistance apparatus and method of controlling the same |
| CN109606354A (en) * | 2018-10-18 | 2019-04-12 | 同济大学 | A kind of automatic parking method and auxiliary system based on hierarchical planning |
| CN110490172A (en) * | 2019-08-27 | 2019-11-22 | 北京茵沃汽车科技有限公司 | Information merges parking stall position compensation method, the system, device, medium parked |
| CN110861639A (en) * | 2019-11-28 | 2020-03-06 | 安徽江淮汽车集团股份有限公司 | Parking information fusion method and device, electronic equipment and storage medium |
| CN111845723A (en) * | 2020-08-05 | 2020-10-30 | 北京四维智联科技有限公司 | Full-automatic parking method and system |
-
2021
- 2021-04-02 CN CN202110361201.4A patent/CN113085838A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150027527A (en) * | 2013-09-04 | 2015-03-12 | 현대모비스 주식회사 | Parking assistance system for vehicle and parking assistant method |
| CN103600707A (en) * | 2013-11-06 | 2014-02-26 | 同济大学 | Parking position detecting device and method of intelligent parking system |
| US20170039439A1 (en) * | 2015-08-03 | 2017-02-09 | Hyundai Mobis Co., Ltd. | Parking space recognition apparatus and method of controlling the same |
| US20170036695A1 (en) * | 2015-08-03 | 2017-02-09 | Hyundai Mobis Co., Ltd. | Parking assistance apparatus and method of controlling the same |
| CN109606354A (en) * | 2018-10-18 | 2019-04-12 | 同济大学 | A kind of automatic parking method and auxiliary system based on hierarchical planning |
| CN110490172A (en) * | 2019-08-27 | 2019-11-22 | 北京茵沃汽车科技有限公司 | Information merges parking stall position compensation method, the system, device, medium parked |
| CN110861639A (en) * | 2019-11-28 | 2020-03-06 | 安徽江淮汽车集团股份有限公司 | Parking information fusion method and device, electronic equipment and storage medium |
| CN111845723A (en) * | 2020-08-05 | 2020-10-30 | 北京四维智联科技有限公司 | Full-automatic parking method and system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554882A (en) * | 2021-07-20 | 2021-10-26 | 阿波罗智联(北京)科技有限公司 | Method, apparatus, device and storage medium for outputting information |
| CN113920782A (en) * | 2021-10-08 | 2022-01-11 | 安徽江淮汽车集团股份有限公司 | Multi-sensor fusion method applied to parking space detection |
| CN114125253A (en) * | 2021-12-27 | 2022-03-01 | 上海映驰科技有限公司 | Mechanical parking space detection system and detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113085838A (en) | Parking space detection method and system based on multi-sensor fusion | |
| CN107665603B (en) | Real-time detection method for judging parking space occupation | |
| CN102944224B (en) | Work method for automatic environmental perception systemfor remotely piloted vehicle | |
| US6370261B1 (en) | Vehicle surroundings monitoring apparatus | |
| US5937079A (en) | Method for stereo image object detection | |
| CN102435174B (en) | Method and device for detecting barrier based on hybrid binocular vision | |
| Labayrade et al. | In-vehicle obstacles detection and characterization by stereovision | |
| CN102390370A (en) | Stereoscopic vision based emergency treatment device and method for running vehicles | |
| WO2015024407A1 (en) | Power robot based binocular vision navigation system and method based on | |
| CN107767687B (en) | Free parking space detection method and system based on binocular stereoscopic vision | |
| CN111413983A (en) | Environment sensing method and control end of unmanned vehicle | |
| CN111796299A (en) | Obstacle sensing method and device and unmanned sweeper | |
| CN104902261A (en) | Device and method for road surface identification in low-definition video streaming | |
| CN102538766A (en) | Obstacle test method for active intelligent vehicle | |
| CN113420687A (en) | Method and device for acquiring travelable area and vehicle | |
| CN112622885B (en) | Method and system for constructing inclined parking spaces based on ultrasonic radar | |
| CN114821526A (en) | Obstacle three-dimensional frame detection method based on 4D millimeter wave radar point cloud | |
| JP4956099B2 (en) | Wall detector | |
| CN202608712U (en) | Stereoscopic vision based active grating projection sensor system | |
| CN114495066A (en) | Method for assisting backing | |
| CN112578405B (en) | Method and system for removing ground based on laser radar point cloud data | |
| CN113658240B (en) | Main obstacle detection method and device and automatic driving system | |
| CN115424468A (en) | Parking stall detecting system based on many cameras fuse | |
| CN113345118B (en) | Parking charge management method, system and storage medium | |
| CN115409965A (en) | Mining area map automatic generation method for unstructured roads |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210709 |