CN115520177A - Vision-based parking method and system, vehicle and storage medium - Google Patents
Vision-based parking method and system, vehicle and storage medium Download PDFInfo
- Publication number
- CN115520177A CN115520177A CN202211111041.9A CN202211111041A CN115520177A CN 115520177 A CN115520177 A CN 115520177A CN 202211111041 A CN202211111041 A CN 202211111041A CN 115520177 A CN115520177 A CN 115520177A
- Authority
- CN
- China
- Prior art keywords
- parking space
- parking
- vehicle
- idle
- vision
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004590 computer program Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- B60W30/06—Automatic manoeuvring for parking
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vision-based parking method, which comprises the following steps: acquiring image information around a vehicle; identifying parking space angular points of idle parking spaces in the image information; generating an idle parking space frame based on the parking space angular points of the idle parking spaces; when the idle parking space frame is identified to be occupied by adjacent vehicles, acquiring the occupied position and area of the idle parking space frame; and adjusting the parking position of the vehicle in the idle parking space frame or replacing the target parking space according to the occupied position and area of the idle parking space frame. The vision-based parking method, the vision-based parking system, the vision-based parking vehicle and the vision-based parking storage medium can control the vehicle to realize automatic garage searching and parking and also improve the safety of the vehicle during parking.
Description
Technical Field
The application relates to the technical field of vehicle control, in particular to a parking method, a parking system, a vehicle and a storage medium based on vision.
Background
The traditional parking and warehousing mode is controlled by people, a driver drives a vehicle to search for an empty parking space in a parking lot, whether the parking space exists in an area range is searched through human eyes, if the vehicle speed is high, the human eyes cannot respond, the empty parking space capable of parking can be missed probably, the time for searching the parking space is increased, if the vehicle speed is slowed down to search for the empty parking space capable of parking, the time for searching the parking space can also be increased, the parking process has a great relation with the level of the driver, and the parking and warehousing mode is a low-efficiency operation mode.
Disclosure of Invention
In order to solve the problems, the invention provides a vision-based parking method which can realize automatic parking.
The invention provides a vision-based parking method, which comprises the following steps: acquiring image information around a vehicle; identifying parking space angular points of idle parking spaces in the image information; generating an idle parking space frame based on the parking space angular points of the idle parking spaces; when recognizing that the idle parking space frame is occupied by adjacent vehicles, acquiring the occupied position and area of the idle parking space frame; and adjusting the parking position of the vehicle in the idle parking space frame or replacing the target parking space according to the occupied position and area of the idle parking space frame.
In an embodiment, the step of generating an empty parking space frame based on the parking space angular point of the empty parking space includes: acquiring parking space lines of the idle parking spaces according to the plurality of parking space angular points in the idle parking spaces; and generating the idle parking space frame based on the parking space angular points and the parking space lines of the idle parking spaces.
In an embodiment, the step of acquiring the occupied position and area of the vacant parking space frame when recognizing that the vacant parking space frame is occupied by an adjacent vehicle includes: obtaining a contact point between a wheel of the adjacent vehicle positioned on one side of the idle parking space frame and the ground according to the image information; connecting the wheels of the adjacent vehicles with the contact points of the ground to obtain wheel contact connecting lines; extending the wheel contact connecting line to a side line of the idle parking space frame to obtain the occupied position and the occupied area of the adjacent vehicle on the idle parking space frame; and acquiring the occupied position and area of the idle parking space frame according to the occupied position and area of the adjacent vehicle or vehicles on the idle parking space frame.
In one embodiment, the step of adjusting the parking position of the vehicle in the vacant parking space frame or replacing the target parking space according to the occupied position and area of the vacant parking space frame includes: calculating the remaining parking positions and areas of the idle parking space frame according to the occupied positions and areas of the idle parking space frame; judging whether the remaining parking positions and areas of the free parking space frame meet parking conditions or not; if so, adjusting the parking position of the vehicle in the idle parking space frame according to the remaining parking position and area of the idle parking space frame; and if not, replacing the parking space for the vehicle.
In one embodiment, the step of acquiring image information of the surroundings of the vehicle includes: acquiring original image information shot by a plurality of vehicle-mounted cameras; stretching the original image information to obtain stretched image information; acquiring image coordinates of the stretched image information; and splicing the stretched image information according to the image coordinates to acquire image information.
In one embodiment, the method further comprises: when no free parking space exists in the image information, identifying whether a vehicle on the parking space is in a moving state; and waiting for the vehicle in the parking space to exit the parking space when the vehicle in the parking space is in a moving state.
In one embodiment, the step of waiting for the vehicle in the parking space to exit the parking space comprises: and sending prompt information and/or replacing the target parking space when the waiting time exceeds the preset time.
The invention also provides a vision-based parking system, which comprises a vehicle-mounted camera and a processing unit: the vehicle-mounted camera is arranged on the top of the vehicle or around the vehicle and is used for shooting original image information near the vehicle; the processing unit includes: the parking system comprises a memory and a processor, wherein the memory stores a vision-based parking program, and the vision-based parking program realizes the steps of the vision-based parking method when being executed by the processor.
The invention also provides a vehicle comprising the vision-based parking system.
The present invention also provides a storage medium, which stores a computer program that, when executed by a processor, implements the steps of the vision-based parking method as described above.
The vision-based parking method, the vision-based parking system, the vehicle and the storage medium analyze the image information shot by the vehicle-mounted camera, acquire the idle parking space in the image information, analyze whether the idle parking space is occupied by the adjacent vehicle or not, and adjust the parking position of the vehicle in the idle parking space frame according to the occupied position and area of the idle parking space frame when the idle parking space frame is identified to be occupied by the adjacent vehicle.
Drawings
FIG. 1 is a flow chart of a vision-based parking method in accordance with a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a display interface of image information according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a display interface for acquiring an idle parking space frame according to an embodiment of the present invention;
fig. 4 is a flowchart of a vision-based parking method according to a second embodiment of the present invention.
Detailed Description
The foregoing and other technical and other features, aspects and utilities of the present invention will be apparent from the following detailed description of the preferred embodiments when read in conjunction with the accompanying drawings. While the present invention has been described in connection with the preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments.
Fig. 1 is a flowchart of a vision-based parking method according to a first embodiment of the present invention.
As shown in fig. 1, the vision-based parking method provided by the present embodiment includes the following steps:
step S11: image information of the surroundings of the vehicle is acquired.
Specifically, in one embodiment, as shown in the image on the right side of fig. 2, the present invention acquires original image information captured by a front vehicle-mounted camera and a rear vehicle-mounted camera, stretches the acquired original image information to acquire stretched image information, acquires image coordinates of the stretched image information, and splices the stretched image information according to the acquired image coordinates to acquire image information shown in the image on the left side of fig. 2.
Specifically, in one embodiment, the free parking space information and the obstacle information in the image information are identified, the vehicle is controlled to drive to the free parking space according to the free parking space information, and the obstacle is controlled to be avoided in the process of driving to the free parking space according to the obstacle information.
Step S12: and identifying the parking space angular points of the idle parking spaces in the image information.
Specifically, when a plurality of free parking spaces exist in the image information, the parking space corner point of the free parking space closest to the vehicle is preferentially acquired. Wherein, the idle parking stall includes idle rhombus parking stall, idle vertical parking stall, idle horizontal parking stall.
Step S13: and generating an idle parking space frame based on the parking space angular points of the idle parking spaces.
Specifically, according to a plurality of parking space angular points in the idle parking space, parking space lines of the idle parking space are obtained, and an idle parking space frame is generated based on the parking space angular points and the parking space lines of the idle parking space. Specifically, for example, according to two parking space corner points of the same diagonal position in the idle parking space, a connection line between the two parking space corners is obtained to obtain a parking space line of the idle parking space.
Specifically, in an embodiment, as shown in fig. 3, after the image information shown on the left side is obtained according to the original image information on the right side, the invention identifies the free parking space in the image information through the deep learning neural network technology, obtains a plurality of parking space angular points and parking space lines in the free parking space, and generates a complete free parking space frame based on the obtained parking space angular points and parking space lines.
Specifically, step S13 is followed by: and identifying whether the vacant parking space frame is occupied by the adjacent vehicle, if so, entering the step S14: when the idle parking space frame is identified to be occupied by adjacent vehicles, acquiring the occupied position and area of the idle parking space frame; if not, controlling the vehicle to park in the idle parking space frame.
Specifically, when the idle parking space frame is occupied by adjacent vehicles, the contact point between the wheel of the adjacent vehicle on one side of the idle parking space frame and the ground is obtained according to the image information, the wheel of the adjacent vehicle is connected with the contact point on the ground, a wheel contact connecting line is obtained, the wheel contact connecting line is extended to the side line of the idle parking space frame to obtain the occupied position and area of the adjacent vehicle on the idle parking space frame, and the occupied position and area of the idle parking space frame are obtained according to the occupied position and area of a single or a plurality of adjacent vehicles on the idle parking space frame.
Step S15: and adjusting the parking position of the vehicle in the idle parking space frame or replacing the target parking space according to the occupied position and area of the idle parking space frame.
Specifically, the remaining parking position and area of the free parking space frame are calculated according to the occupied position and area of the free parking space frame, and whether the remaining parking position and area of the free parking space frame meet preset safe parking conditions or not is judged; if so, adjusting the parking position of the vehicle in the idle parking space frame according to the remaining parking position and area of the idle parking space frame; and if not, replacing the target parking space for the vehicle.
Specifically, in one embodiment, when it is determined that the remaining parking position and area of the free parking space frame satisfy the preset safe parking condition, the garage entering angle when the vehicle parks is adjusted according to the remaining parking position and area of the free parking space frame and the position of the adjacent vehicle.
According to the vision-based parking method, the image information shot by the vehicle-mounted camera is analyzed, the free parking space in the image information is obtained, whether the free parking space is occupied by the adjacent vehicle is analyzed, and when the fact that the free parking space frame is occupied by the adjacent vehicle is recognized, the parking position of the vehicle in the free parking space frame is adjusted according to the occupied position and area of the free parking space frame, so that the vehicle can be controlled to automatically find a parking garage for parking, and the safety of the vehicle during parking is improved.
Fig. 4 is a flowchart of a vision-based parking method according to a second embodiment of the present invention.
As shown in fig. 4, the vision-based parking method provided by the embodiment includes the following steps:
step S41: and when no free parking space exists in the image information, identifying whether the vehicle on the parking space is in a moving state.
Specifically, when it is recognized that the vehicle in the parking space is in the moving state, the process proceeds to step S43: waiting for the vehicle on the parking space to exit the parking space; if it is recognized that the vehicle in the parking space is not in the moving state, the process proceeds to step S42: and replacing the target parking space.
Step S44: and judging whether the waiting time exceeds the preset time.
Specifically, when it is determined that the time for waiting for the vehicle in the parking space to exit the parking space exceeds the preset time, the process proceeds to step S46: sending prompt information and/or replacing a target parking space; and (5) judging that the time for waiting for the vehicle on the parking space to leave the parking space does not exceed the preset time, and entering the step S45: and identifying the parking space angle point of the parking space to obtain an idle parking space frame, calculating the remaining parking position and area of the idle parking space frame, and controlling the vehicle to park according to the remaining parking position and area of the idle parking space frame.
The invention also provides a vision-based parking system, which comprises a vehicle-mounted camera and a processing unit: the vehicle-mounted camera is arranged on the top of the vehicle or around the vehicle and is used for shooting original image information near the vehicle; the processing unit includes: the vision-based parking method comprises a memory and a processor, wherein the memory stores a vision-based parking program, and the vision-based parking program realizes the steps of the vision-based parking method when executed by the processor.
The invention also provides a vehicle comprising the vision-based parking system.
The present invention also provides a storage medium, which stores a computer program that, when executed by a processor, implements the steps of the vision-based parking method as described above.
The vision-based parking method, the vision-based parking system, the vehicle and the storage medium analyze the image information shot by the vehicle-mounted camera, acquire the idle parking space in the image information, analyze whether the idle parking space is occupied by the adjacent vehicle or not, and adjust the parking position of the vehicle in the idle parking space frame according to the occupied position and area of the idle parking space frame when the idle parking space frame is identified to be occupied by the adjacent vehicle.
Although the present invention has been described with reference to the preferred embodiments, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A vision-based parking method, comprising:
acquiring image information around a vehicle;
identifying parking space angular points of idle parking spaces in the image information;
generating an idle parking space frame based on the parking space angular points of the idle parking spaces;
when recognizing that the idle parking space frame is occupied by adjacent vehicles, acquiring the occupied position and area of the idle parking space frame;
and adjusting the parking position of the vehicle in the idle parking space frame or replacing the target parking space according to the occupied position and area of the idle parking space frame.
2. The vision-based parking method of claim 1 wherein the step of generating an empty parking space frame based on the corner points of the empty parking spaces comprises:
acquiring parking space lines of the idle parking spaces according to the angular points of the parking spaces in the idle parking spaces;
and generating the free parking space frame based on the parking space angular points and the parking space lines of the free parking spaces.
3. The vision-based parking method according to claim 1, wherein the step of acquiring an occupied position and area of the vacant parking space frame upon recognizing that the vacant parking space frame is occupied by an adjacent vehicle includes:
obtaining a contact point between a wheel of the adjacent vehicle positioned on one side of the idle parking space frame and the ground according to the image information;
connecting the wheels of the adjacent vehicles with the contact points of the ground to obtain wheel contact connecting lines;
extending the wheel contact connecting line to a side line of the idle parking space frame to obtain the occupied position and the occupied area of the adjacent vehicle on the idle parking space frame;
and acquiring the occupied position and area of the idle parking space frame according to the occupied position and area of the adjacent vehicle or vehicles on the idle parking space frame.
4. The vision-based parking method according to claim 1, wherein the step of adjusting the parking position of the vehicle in the vacant parking space frame or replacing the target parking space according to the occupied position and area of the vacant parking space frame comprises:
calculating the remaining parking positions and areas of the idle parking space frame according to the occupied positions and areas of the idle parking space frame;
judging whether the remaining parking positions and areas of the free parking space frame meet parking conditions or not;
if so, adjusting the parking position of the vehicle in the idle parking space frame according to the remaining parking position and area of the idle parking space frame;
and if not, replacing the parking space for the vehicle.
5. The vision-based parking method according to claim 1, wherein the step of acquiring image information of the surroundings of the vehicle includes:
acquiring original image information shot by a plurality of vehicle-mounted cameras;
stretching the original image information to obtain stretched image information;
acquiring image coordinates of the stretched image information;
and splicing the stretched image information according to the image coordinates to acquire image information.
6. The vision-based parking method of claim 1 further comprising:
when no free parking space exists in the image information, identifying whether a vehicle on the parking space is in a moving state;
and waiting for the vehicle in the parking space to exit the parking space when the vehicle in the parking space is in a moving state.
7. The vision-based parking method of claim 6 wherein said step of waiting for a vehicle in said parking space to exit the parking space, thereafter comprises:
and sending prompt information and/or replacing the target parking space when the waiting time exceeds the preset time.
8. A vision-based parking system, comprising an onboard camera and a processing unit:
the vehicle-mounted camera is arranged on the top of the vehicle or around the vehicle and is used for shooting original image information near the vehicle;
the processing unit includes: a memory and a processor, wherein the memory stores a vision-based parking program, and the vision-based parking program implements the steps of the vision-based parking method according to any one of claims 1 to 7 when executed by the processor.
9. A vehicle comprising the vision-based parking system of claim 8.
10. A storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the vision-based parking method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211111041.9A CN115520177A (en) | 2022-09-13 | 2022-09-13 | Vision-based parking method and system, vehicle and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211111041.9A CN115520177A (en) | 2022-09-13 | 2022-09-13 | Vision-based parking method and system, vehicle and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115520177A true CN115520177A (en) | 2022-12-27 |
Family
ID=84697878
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211111041.9A Pending CN115520177A (en) | 2022-09-13 | 2022-09-13 | Vision-based parking method and system, vehicle and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115520177A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116206482A (en) * | 2023-03-08 | 2023-06-02 | 重庆赛力斯新能源汽车设计院有限公司 | Parking space release method, electronic equipment and storage medium |
CN116758775A (en) * | 2023-04-13 | 2023-09-15 | 浙江小虎科技有限公司 | Parking space state judging method and system |
-
2022
- 2022-09-13 CN CN202211111041.9A patent/CN115520177A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116206482A (en) * | 2023-03-08 | 2023-06-02 | 重庆赛力斯新能源汽车设计院有限公司 | Parking space release method, electronic equipment and storage medium |
CN116206482B (en) * | 2023-03-08 | 2024-05-24 | 重庆赛力斯新能源汽车设计院有限公司 | Parking space release method, electronic equipment and storage medium |
CN116758775A (en) * | 2023-04-13 | 2023-09-15 | 浙江小虎科技有限公司 | Parking space state judging method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115520177A (en) | Vision-based parking method and system, vehicle and storage medium | |
US20190075255A1 (en) | Display control apparatus, display control method, and program | |
US20090192686A1 (en) | Method and Driver Assistance System for Sensor-Based Drive-Off Control of a Motor Vehicle | |
CN111028534B (en) | Parking space detection method and device | |
CN107187436B (en) | The method and apparatus for preventing mis-accelerator pressing | |
CN108482367B (en) | Method, device and system for assisting driving based on intelligent rearview mirror | |
CN112509354B (en) | Parking space detection method and device, vehicle and readable medium | |
CN112771858A (en) | Camera assessment techniques for automated vehicles | |
CN112158197B (en) | Vehicle blind area obstacle avoiding method, device and system | |
CN109664889B (en) | Vehicle control method, device and system and storage medium | |
CN110351491A (en) | A kind of low light compensation method according under environment, apparatus and system | |
CN112009462A (en) | Forward automatic parking method and device | |
CN208789584U (en) | Driving support device | |
CN111814657A (en) | Unmanned vehicle parking method and system based on image recognition and storage medium | |
US11580695B2 (en) | Method for a sensor-based and memory-based representation of a surroundings, display device and vehicle having the display device | |
CN114407928A (en) | Vehicle avoidance control method and vehicle avoidance control device | |
CN116022126A (en) | Autonomous learning parking method, electronic device and storage medium | |
US20190266416A1 (en) | Vehicle image system and method for positioning vehicle using vehicle image | |
KR102565897B1 (en) | System guiding with the acknowledged information of the speciality vehicles to the parking booth | |
CN113370970B (en) | Automatic parking method and device for parking in adjacent parking space | |
CN112172670B (en) | Image recognition-based rear view image display method and device | |
CN109849795B (en) | Method and system for controlling turning of rearview mirror | |
CN114103812A (en) | Backing-up and warehousing guide system and method | |
KR102565883B1 (en) | System for offering the information of the vehicles near to the parked vehicles with the artificial intelligence recognition | |
KR102685379B1 (en) | Intelligent parking method and device |
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 |