CN114639086A - Parking space detection method with multi-sensor fusion - Google Patents

Parking space detection method with multi-sensor fusion Download PDF

Info

Publication number
CN114639086A
CN114639086A CN202210193176.8A CN202210193176A CN114639086A CN 114639086 A CN114639086 A CN 114639086A CN 202210193176 A CN202210193176 A CN 202210193176A CN 114639086 A CN114639086 A CN 114639086A
Authority
CN
China
Prior art keywords
vehicle
parked
parking space
door
distance
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210193176.8A
Other languages
Chinese (zh)
Inventor
陈宁
刘必歆
王沁峰
邹朝圣
廖妮兰
宁静
岳鹏鑫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiamen Winjoin Technology Co ltd
Jimei University
Original Assignee
Xiamen Winjoin Technology Co ltd
Jimei University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xiamen Winjoin Technology Co ltd, Jimei University filed Critical Xiamen Winjoin Technology Co ltd
Priority to CN202210193176.8A priority Critical patent/CN114639086A/en
Publication of CN114639086A publication Critical patent/CN114639086A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to the field of parking space detection methods, in particular to a parking space detection method with multi-sensor fusion. The method comprises the following steps: a vehicle to be parked enters a garage to find a parking space, and information around the vehicle to be parked is collected through a camera; judging whether an obstacle exists in the parking space or not by acquiring information; if the obstacle exists in the parking space, the vehicle cannot be parked, and the parking space is continuously searched; if no obstacle exists in the parking space, measuring the distance between the vehicle to be parked and the parked vehicles on the two sides of the parking space through a plurality of distance measuring sensors; generating a plane image by combining information acquired by a camera; judging whether the vehicle door can be normally opened after the vehicle to be parked enters the parking space through a detection algorithm; if the vehicle door can not be opened, the vehicle can not be parked, and the parking space is continuously searched; if the door can be normally opened, the vehicle is stopped. The invention aims to provide a parking space detection method with a multi-sensor fusion, which can automatically judge whether parking is available.

Description

Parking space detection method with multi-sensor fusion
Technical Field
The invention relates to the field of parking space detection methods, in particular to a parking space detection method with 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 is a very important link in an automatic parking system, the current parking space detection method has strict requirements on a parking environment and a parking space line of a parking space, the current parking space detection method can only obtain image information around a vehicle, and the current parking space detection method does not have a function of automatically judging whether the vehicle can be parked, and has certain limitations.
Disclosure of Invention
The invention aims to provide a parking space detection method with a plurality of sensors fused, which can automatically judge whether parking is available.
The technical scheme adopted by the invention is as follows: the utility model provides a parking stall detection method of multisensor integration which characterized in that: the method comprises the following steps:
the method comprises the following steps: a vehicle to be parked enters a garage to find a vertical parking space, and information around the vehicle to be parked is acquired through a plurality of cameras;
step two: judging whether obstacles exist in the parking space or not according to the acquired information around the vehicle to be parked;
step three: if the obstacle exists in the parking space, the vehicle cannot be parked, and the vertical parking space is continuously searched;
step four: if no obstacle exists in the parking space, measuring the distance between the vehicle to be parked and the parked vehicles on the two sides of the parking space through a plurality of distance measuring sensors;
step five: generating a plane image by combining the information around the vehicle to be parked, which is acquired by the camera in the first step;
step six: judging whether the vehicle door can be normally opened after the vehicle to be parked enters the parking space through a detection algorithm;
step seven: if the vehicle door can not be opened, the vehicle can not be parked, and the vertical parking space is continuously searched; if the door can be normally opened, the vehicle is stopped.
The cameras are respectively arranged on two sides of the vehicle to be parked; the plurality of distance measuring sensors are respectively arranged at four corners of the vehicle to be parked.
The plane images are images of a vehicle to be parked and two parked vehicle positions.
The detection algorithm is used for calculating the distance between two vehicles to be parked, and comprises an algorithm A and an algorithm B.
The algorithm A is used for calculating the distance between two vehicles to be parked under the condition that the vehicles to be parked are in front of two parked vehicles: lx ═ LLong and long+Lc11+Lc12(ii) a Judging the size between Lx and Lt:
if Lx is larger than Lt, the vehicle door can be normally opened after the vehicle to be parked enters the parking space, and then the vehicle can be parked and the parking operation is carried out; if Lx < Lt, the vehicle door of the vehicle to be parked can not be opened after the vehicle enters the parking space, namely the vehicle can not be parked, and the parking space is continuously searched.
The algorithm B is used for calculating the distance between two vehicles to be parked when the vehicles to be parked are in front of one parked vehicle: ly ═ LLong and long+Lc21-Lc22(ii) a Judging the size between Ly and Lt:
if Ly is greater than Lt, the vehicle can be parked and the parking operation can be carried out by normally opening the door of the vehicle to be parked after the vehicle enters the parking space; if Ly < Lt, the vehicle door of the vehicle to be parked cannot be opened after the vehicle enters the parking space, namely the vehicle cannot be parked, and the parking space is continuously searched.
Wherein Lx is the distance between two vehicles to be parked, LLong and longIs the length of the vehicle to be parked; and Lt is the sum of the width of the vehicle to be parked and the lengths of the two vehicle doors: l is LWidth of+2LDoor with a door panelWherein L isWidth ofFor the width, L, of the vehicle to be parkedDoor with a door panelIs the length of the door of the vehicle to be parked;
lc in the algorithm A11Is the transverse distance, Lc, between the vehicle head and one of the parked vehicles12Is the transverse distance between the tail of the vehicle and another parked vehicle;
lc in the algorithm B21Is the transverse distance, Lc, between the vehicle head and one of the parked vehicles22The lateral distance between the slot and the side door of another parked vehicle.
Said Lc11、Lc12、Lc21、Lc22The distance can be measured by the distance measuring sensor.
The invention has the beneficial effects that: according to the invention, through the mutual cooperation of the plurality of distance measuring sensors and the combination of the parking space detection algorithm, whether the parking space can be parked or not can be judged, so that a great amount of judgment time of a vehicle owner is saved, the vehicle owner is prevented from parking the wrong parking space, and the lost time is reduced. The invention automatically judges whether the vehicle to be parked can be parked or not through the parking space detection algorithm, saves the time of the vehicle owner and has great application value and popularization value.
Drawings
FIG. 1 is an overall flow chart of a parking space detection method with multi-sensor integration according to the present invention;
FIG. 2 is a schematic diagram of a vehicle to be parked according to the multi-sensor integrated parking space detection method of the present invention;
FIG. 3 is an algorithm A representation of the multi-sensor fusion parking space detection method of the present invention;
fig. 4 is an algorithm B demonstration diagram of the parking space detection method with multi-sensor fusion according to the present invention.
Detailed Description
The present invention is not limited by the following examples, and specific embodiments may be determined according to the technical solutions and practical situations of the present invention.
The utility model provides a parking stall detection method of multisensor integration which characterized in that: the method comprises the following steps:
the method comprises the following steps: a vehicle to be parked enters a garage to find a vertical parking space, and information around the vehicle to be parked is collected through a plurality of cameras;
step two: judging whether obstacles exist in the parking space or not according to the acquired information around the vehicle to be parked;
step three: if the obstacle exists in the parking space, the vehicle cannot be parked, and the vertical parking space is continuously searched;
step four: if no obstacle exists in the parking space, measuring the distance between the vehicle to be parked and the parked vehicles on the two sides of the parking space through a plurality of distance measuring sensors;
step five: generating a plane image by combining the information around the vehicle to be parked, which is acquired by the camera in the first step;
step six: judging whether the vehicle door can be normally opened after the vehicle to be parked enters the parking space through a detection algorithm;
step seven: if the vehicle door cannot be opened, the vehicle cannot be parked, and the vertical parking space is continuously searched; if the door can be normally opened, the vehicle is stopped.
The cameras are respectively arranged on two sides of the vehicle to be parked; the plurality of distance measuring sensors are respectively arranged at four corners of the vehicle to be parked.
The plane images are images of a vehicle to be parked and two parked vehicle positions.
The detection algorithm is used for calculating the distance between two vehicles to be parked, and comprises an algorithm A and an algorithm B.
The algorithm A is used for calculating the distance between two vehicles to be parked under the condition that the vehicles to be parked are in front of two parked vehicles: lx ═ LLong and long+Lc11+Lc12(ii) a Judging the size between Lx and Lt:
if Lx is larger than Lt, the vehicle door can be normally opened after the vehicle to be parked enters the parking space, and then the vehicle can be parked and the parking operation is carried out; if Lx is less than Lt, the vehicle to be parked cannot open the vehicle door after entering the parking space, namely, the vehicle cannot be parked, and the parking space is continuously searched.
The algorithm B is used for calculating the distance between two vehicles to be parked under the condition that the vehicles to be parked are in front of one parked vehicle: ly ═ LIs long and long+Lc21-Lc22(ii) a Judging the size between Ly and Lt:
if Ly is greater than Lt, the vehicle can be parked and the parking operation can be carried out by normally opening the door of the vehicle to be parked after the vehicle enters the parking space; if Ly < Lt, the vehicle door of the vehicle to be parked cannot be opened after the vehicle enters the parking space, namely the vehicle cannot be parked, and the parking space is continuously searched.
Wherein Lx is the distance between two vehicles to be parked, LLong and longIs the length of the vehicle to be parked; and Lt is the sum of the width of the vehicle to be parked and the lengths of the two vehicle doors: l is LWidth of+2LDoor with a door panelWherein L isWidth ofFor the width, L, of the vehicle to be parkedDoor with a door panelIs the length of the door of the vehicle to be parked;
lc in the algorithm A11Is the transverse distance, Lc, between the vehicle head and one of the parked vehicles12Is the lateral distance between the tail of the vehicle and another parked vehicle;
lc in the algorithm B21Is the transverse distance, Lc, between the vehicle head and one of the parked vehicles22The lateral distance between the slot and the side door of another parked vehicle.
Said Lc11、Lc12、Lc21、Lc22The distance can be measured by the distance measuring sensor.
The method comprises the following steps that a vehicle to be parked enters a garage to find a vertical parking space, information around the vehicle to be parked is collected through a plurality of cameras, and whether obstacles exist in the parking space is judged through the collected information around the vehicle to be parked; if the obstacles exist in the parking space, the vehicle cannot be parked, the vertical parking space is continuously searched, and if the obstacles do not exist in the parking space, the distance between the vehicle to be parked and the parked vehicles on the two sides of the parking space is measured through a plurality of distance measuring sensors; and generating a plane image by combining the information around the vehicle to be parked, which is acquired by the camera, and judging whether the vehicle door can be normally opened after the vehicle to be parked enters the parking space through a detection algorithm.
Example 1:
referring to FIG. 3 in conjunction with the drawings, Lc can be measured by a distance measuring sensor when a parked vehicle is parked at a position as shown in FIG. 311And Lc12By Lx ═ LIs long and long+Lc11+Lc12Calculating the length of Lx; if Lx>Lt, after the vehicle to be parked enters the parking space, the door of the vehicle can be normally opened, and then the vehicle can be parked and the parking operation is carried out; if Lx<And Lt, the vehicle door cannot be opened after the vehicle to be parked enters the parking space, namely the vehicle cannot be parked, and the parking space is continuously searched.
Example 2:
referring to fig. 4 in conjunction with the drawings, Lc can be measured by the distance measuring sensor when the parked vehicle is parked at the position shown in fig. 421And Lc22By Ly ═ LIs long and long+Lc21-Lc22Calculating the length of the Ly; if Ly>Lt, after the vehicle to be parked enters the parking space, the door of the vehicle can be normally opened, and then the vehicle can be parked and the parking operation is carried out; if Ly<And Lt, the vehicle door cannot be opened after the vehicle to be parked enters the parking space, namely the vehicle cannot be parked, and the parking space is continuously searched.
Through the embodiment 1 and the embodiment 2, the parking space detection algorithm can be popularized to automatically judge whether the vehicle to be parked can park, so that a great amount of judgment time of a vehicle owner is saved, the vehicle owner is prevented from parking the wrong parking space, the lost time is reduced, and the parking space detection method has a great application prospect.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (8)

1. The utility model provides a parking stall detection method of multisensor integration which characterized in that: the method comprises the following steps:
the method comprises the following steps: a vehicle to be parked enters a garage to find a vertical parking space, and information around the vehicle to be parked is collected through a plurality of cameras;
step two: judging whether obstacles exist in the parking space or not according to the acquired information around the vehicle to be parked;
step three: if the obstacle exists in the parking space, the vehicle cannot be parked, and the vertical parking space is continuously searched;
step four: if no obstacle exists in the parking space, measuring the distance between the vehicle to be parked and the parked vehicles on the two sides of the parking space through a plurality of distance measuring sensors;
step five: generating a plane image by combining the information around the vehicle to be parked, which is acquired by the camera in the first step;
step six: judging whether the vehicle door can be normally opened after the vehicle to be parked enters the parking space through a detection algorithm;
step seven: if the vehicle door can not be opened, the vehicle can not be parked, and the vertical parking space is continuously searched; if the door can be normally opened, the vehicle is stopped.
2. The parking space detection method based on multi-sensor fusion as claimed in claim 1, characterized in that: the cameras are respectively arranged on two sides of the vehicle to be parked; the plurality of distance measuring sensors are respectively arranged at four corners of the vehicle to be parked.
3. The parking space detection method based on multi-sensor fusion as claimed in claim 1, characterized in that: the plane images are images of a vehicle to be parked and two parked vehicle positions.
4. The parking space detection method based on multi-sensor fusion as claimed in claim 1, characterized in that: the detection algorithm is used for calculating the distance between two vehicles to be parked, and comprises an algorithm A and an algorithm B.
5. The parking space detection method based on multi-sensor fusion as claimed in claim 1, characterized in that: the algorithm A is used for calculating the distance between two vehicles to be parked under the condition that the vehicles to be parked are in front of two parked vehicles: lx ═ LLong and long+Lc11+Lc12(ii) a Judging the size between Lx and Lt:
if Lx is larger than Lt, the vehicle can normally open the door after the vehicle to be parked enters the parking space, and then the vehicle can be parked and the parking operation is carried out; if Lx < Lt, the vehicle door of the vehicle to be parked can not be opened after the vehicle enters the parking space, namely the vehicle can not be parked, and the parking space is continuously searched.
6. The parking space detection method based on multi-sensor fusion as claimed in claim 1, characterized in that: the algorithm B is used for calculating the distance between two vehicles to be parked under the condition that the vehicles to be parked are in front of one parked vehicle: ly ═ LLong and long+Lc21-Lc22(ii) a Judging the size between Ly and Lt:
if Ly is greater than Lt, the vehicle can be parked and the parking operation can be carried out by normally opening the door of the vehicle after the vehicle to be parked enters the parking space; if Ly < Lt, the vehicle door of the vehicle to be parked cannot be opened after the vehicle enters the parking space, namely the vehicle cannot be parked, and the parking space is continuously searched.
7. The parking space detection method with the multi-sensor integration according to claims 5 and 6, characterized in that: wherein Lx is the distance between two vehicles to be parked, LLong and longIs the length of the vehicle to be parked; and Lt is the sum of the width of the vehicle to be parked and the lengths of the two vehicle doors: l is LWidth of+2LDoor with a door panelWherein L isWidth ofFor the width, L, of the vehicle to be parkedDoor with a door panelIs the length of the door of the vehicle to be parked;
lc in the algorithm A11Is the transverse distance, Lc, between the vehicle head and one of the parked vehicles12Is the lateral distance between the tail of the vehicle and another parked vehicle;
lc in the algorithm B21For crossing between the head and one of the parked vehiclesDistance, Lc22The lateral distance between the slot and the side door of another parked vehicle.
8. The method for detecting the parking space through multi-sensor fusion according to claims 5, 6 and 7, characterized in that: said Lc11、Lc12、Lc21、Lc22The distance can be measured by the distance measuring sensor.
CN202210193176.8A 2022-03-01 2022-03-01 Parking space detection method with multi-sensor fusion Pending CN114639086A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210193176.8A CN114639086A (en) 2022-03-01 2022-03-01 Parking space detection method with multi-sensor fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210193176.8A CN114639086A (en) 2022-03-01 2022-03-01 Parking space detection method with multi-sensor fusion

Publications (1)

Publication Number Publication Date
CN114639086A true CN114639086A (en) 2022-06-17

Family

ID=81947231

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210193176.8A Pending CN114639086A (en) 2022-03-01 2022-03-01 Parking space detection method with multi-sensor fusion

Country Status (1)

Country Link
CN (1) CN114639086A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105869432A (en) * 2016-03-29 2016-08-17 江苏大学 Method for identifying parking lot scene based on multiple-sensor fusion
JP2019137169A (en) * 2018-02-08 2019-08-22 三菱電機株式会社 Guidance device, guidance system, and program
CN113085838A (en) * 2021-04-02 2021-07-09 的卢技术有限公司 Parking space detection method and system based on multi-sensor fusion
DE102020117770A1 (en) * 2020-07-06 2022-01-13 Valeo Schalter Und Sensoren Gmbh METHOD OF OPERATING A VEHICLE, PARKING ASSISTANCE SYSTEM AND VEHICLE

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105869432A (en) * 2016-03-29 2016-08-17 江苏大学 Method for identifying parking lot scene based on multiple-sensor fusion
JP2019137169A (en) * 2018-02-08 2019-08-22 三菱電機株式会社 Guidance device, guidance system, and program
DE102020117770A1 (en) * 2020-07-06 2022-01-13 Valeo Schalter Und Sensoren Gmbh METHOD OF OPERATING A VEHICLE, PARKING ASSISTANCE SYSTEM AND VEHICLE
CN113085838A (en) * 2021-04-02 2021-07-09 的卢技术有限公司 Parking space detection method and system based on multi-sensor fusion

Similar Documents

Publication Publication Date Title
CN109435942B (en) Information fusion-based parking space line and parking space recognition method and device
CN102390370B (en) Stereoscopic vision based emergency treatment device and method for running vehicles
CN111476169B (en) Complex scene road side parking behavior identification method based on video frame
CN101916383B (en) Vehicle detecting, tracking and identifying system based on multi-camera
CN105185123A (en) Fake plate vehicle recognition system and method
CN104933409A (en) Parking space identification method based on point and line features of panoramic image
CN105744232A (en) Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology
CN106203272B (en) The method and apparatus for determining the movement of movable objects
CN113033479B (en) Berth event identification method and system based on multilayer perception
CN102897086A (en) Back car driving information detecting and prompting method and system
CN110458050B (en) Vehicle cut-in detection method and device based on vehicle-mounted video
WO2022213523A1 (en) Method and system for determining roadside parking entrance event on basis of a plurality of dimensions
CN105741589A (en) Parking spot detection method and device based on vehicle-to-vehicle communication
CN110610153A (en) Lane recognition method and system for automatic driving
CN113085838A (en) Parking space detection method and system based on multi-sensor fusion
CN116118719B (en) Automatic driving parking speed measuring system based on obstacle judgment vehicle speed
CN115116012A (en) Method and system for detecting parking state of vehicle parking space based on target detection algorithm
CN115775378A (en) Vehicle-road cooperative target detection method based on multi-sensor fusion
CN111105619A (en) Method and device for judging road side reverse parking
CN111223303B (en) Charging pile parking space management method, device and system
CN114495066A (en) Method for assisting backing
CN112669615B (en) Parking space detection method and system based on camera
CN113879211A (en) Reminding method and system for preventing conflict between muck vehicle and non-motor vehicle in right turning process
CN117372950B (en) Detection device and detection method for new energy parking space occupied by non-energy vehicle
CN114639086A (en) Parking space detection method with multi-sensor fusion

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