# US 2021/0342606 A1 · Parking Detection Method, System, Processing Device and Storage Medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0342606 A1
- Document ID: US20210342606A1
- Status: Published application
- Kind: A1
- Application number: 17/263,537
- Filed: 2020-04-30
- Published: 2021-11-04
- Earliest claimed: 2020-04-30
- Assignees: Boe Technology Group Co., Ltd.
- Applicants: BOE Technology Group Co., Ltd.
- Inventors: Tong LIU
- Web page: https://patentgrep.com/patent/US20210342606A1

## CPC

- G06V 20/586: {of parking space}
- G06V 20/588: {Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road}
- G08G 1/0116: {from roadside infrastructure, e.g. beacons}
- G08G 1/0137: {for specific applications}
- G08G 1/0175: {by photographing vehicles, e.g. when violating traffic rules}
- G08G 1/04: using optical or ultrasonic detectors
- G08G 1/147: {where the parking area is within an open public zone, e.g. city centre}
- G08G 1/148: {Management of a network of parking areas}
- Y02T 10/40: Engine management systems
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})
- Y02T: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION

## Abstract

A parking detection method, a system, a processing device and a storage medium are provided. The parking detection method includes: acquiring an image to be detected; acquiring a projection area of a vehicle on the ground according to vanishing points and a vanishing line in the image to be detected in combination with outline key points of the vehicle in the image to be detected; judging whether the vehicle is parked regularly.

## Claims

### Claim 1

A parking detection method, comprising:
acquiring an image to be detected;
acquiring projection area information of a vehicle on a ground according to vanishing points and a vanishing line of parking lines in the image to be detected in combination with outline key points of the vehicle in the image to be detected; and
judging whether the vehicle is parked regularly.

### Claim 2 (depends on 1)

The parking detection method according to claim 1, wherein acquiring the projection area information of the vehicle on the ground according to the vanishing points and the vanishing line of the parking lines in the image to be detected in combination with the outline key points of the vehicle in the image to be detected comprises:
determining the parking lines in the image to be detected, determining the vanishing points and the vanishing line of the parking lines according to the parking lines, and detecting visible outline key points of the vehicle in the image to be detected; and
determining the projection area information of the vehicle on the ground according to the visible outline key points of the vehicle and the vanishing line.

### Claim 3 (depends on 2)

The parking detection method according to claim 2, wherein judging whether the vehicle is parked regularly comprises:
judging whether the vehicle is parked regularly according to the parking lines and the projection area of the vehicle on the ground.

### Claim 4 (depends on 2)

The parking detection method according to claim 2, wherein determining the projection area information of the vehicle on the ground according to the visible outline key points of the vehicle and the vanishing line comprises:
determining vanishing points of the vehicle according to the visible outline key points of the vehicle and the vanishing line, and determining blocked outline key points of the vehicle in the image to be detected according to the vanishing points of the vehicle; and
obtaining the projection area information of the vehicle on the ground according to the visible outline key points of the vehicle and the determined blocked outline key points of the vehicle.

### Claim 5 (depends on 2)

The parking detection method according to claim 2, wherein detecting the visible outline key points of the vehicle in the image to be detected comprises:
detecting the visible outline key points of the vehicle in the image to be detected by using a target detection algorithm, and outputting results including positions and attribute values of the visible outline key points of the vehicle, wherein the attribute values include identifications of the outline key points of the vehicle, height attribute values and position attribute values, wherein the height attribute values are used to identify a height level to which the outline key points of the vehicle belong, and the position attribute values are used to identify which side of the vehicle the outline key points of the vehicle belong to.

### Claim 6 (depends on 2)

The parking detection method according to claim 2, wherein before detecting the visible outline key points of the vehicle in the image to be detected, the method further comprises:
preprocessing the image to be detected to obtain a pixel-level segmentation result of the vehicle or position range information of the vehicle.

### Claim 7 (depends on 1)

The parking detection method according to claim 1, wherein judging whether the vehicle is parked regularly comprises any one or more of following judgments:
judging whether the vehicle presses at least one of the parking lines;
judging whether a parking angle of the vehicle is within a preset angle offset range;
judging whether a center-of-gravity of the vehicle is within a preset center-of-gravity offset range.

### Claim 8 (depends on 7)

The parking detection method according to claim 7, wherein judging whether the vehicle presses at least one of the parking lines comprises any one or more of following judgments:
judging whether projection lines of the vehicle on the ground coincide with at least one of the parking lines, and if so, the vehicle is determined to press at least one of the parking lines;
judging whether the projection lines of the vehicle on the ground intersect with at least one of the parking lines, and if so, the vehicle is determined to press at least one of the parking lines;
judging whether the outline key points at a bottom level of the vehicle are located on at least one of the parking lines, and as long as one outline key point is located on at least one of the parking lines, the vehicle is determined to press at least one of the parking lines;
judging whether the outline key points at the bottom level of the vehicle are located outside of the parking lines, and as long as one outline key point is located outside of the parking lines, the vehicle is determined to press the parking lines.

### Claim 9 (depends on 7)

The parking detection method according to claim 7, wherein judging whether the parking angle of the vehicle is within the preset angle offset range comprises:
judging whether the parking angle of the vehicle is within the preset angle offset range by slopes of the parking lines and slopes of projection lines of the vehicle on the ground; or
judging whether the parking angle of the vehicle is within the preset angle offset range according to positions of the vanishing points of the parking lines and positions of vanishing points of the vehicle.

### Claim 10 (depends on 9)

The parking detection method according to claim 9, wherein judging whether the parking angle of the vehicle is within the preset angle offset range according to the positions of the vanishing points of the parking lines and the positions of the vanishing points of the vehicle comprises:
using a following formula to calculate a parking slope R1, and when the parking slope is judged to be within a first threshold range, determining the parking angle of the vehicle is within a preset angle offset range: R1=k*((Da+Db)/Dc),
wherein Da represents a distance between a first vanishing point of a parking line and a first vanishing point of the vehicle, Db represents a distance between a second vanishing point of a parking line and a second vanishing point of the vehicle, Dc represents a distance between the first vanishing point of the parking line and the second vanishing point of the parking line, k is a constant, k∈(0,1/2].

### Claim 11 (depends on 7)

The parking detection method according to claim 7, wherein judging whether the center-of-gravity of the vehicle is within the preset center-of-gravity offset range comprises:
judging whether the center of gravity of the vehicle is within the preset center-of-gravity offset range according to a deviation of a center of gravity of the projection area of the vehicle on the ground from a center of gravity of a parking area formed by the parking lines.

### Claim 12 (depends on 11)

The parking detection method according to claim 11, wherein judging whether the center-of-gravity of the vehicle is within the preset center-of-gravity offset range according to the deviation of the center of gravity of the projection area of the vehicle on the ground from the center-of-gravity of the parking area formed by the parking lines comprises:
using a following formula to calculate a parking offset rate R2, and when the parking offset rate is judged to be within a second threshold range, the center-of-gravity of the vehicle is determined to be within the preset center-of-gravity offset range: R2=Dd/f(P),
wherein Dd represents a distance between the center-of-gravity of the projection area of the vehicle on the ground and the center-of-gravity of the parking area formed by the parking lines, P represents area of a parking space, and f(x)=√{square root over (x)}.

### Claim 13 (depends on 1)

A processing device, comprising: a memory, a processor and a computer program stored on the memory and executable by the processor, wherein steps of the method according to claim 1 are implemented when the processor executes the program.

### Claim 14 (depends on 13)

A parking detection system, comprising: an image acquisition device and the processing device according to claim 13.

### Claim 15 (depends on 1)

A non-transitory computer readable storage medium storing computer executable instructions for performing the method according to claim 1.

### Claim 16 (depends on 5)

The parking detection method according to claim 5, wherein before detecting the visible outline key points of the vehicle in the image to be detected, the method further comprises:
preprocessing the image to be detected to obtain a pixel-level segmentation result of the vehicle or position range information of the vehicle.

### Claim 17 (depends on 2)

The parking detection method according to claim 2, wherein judging whether the vehicle is parked regularly comprises any one or more of following judgments:
judging whether the vehicle presses at least one of the parking lines;
judging whether a parking angle of the vehicle is within a preset angle offset range;
judging whether a center-of-gravity of the vehicle is within a preset center-of-gravity offset range.

### Claim 18 (depends on 3)

The parking detection method according to claim 3, wherein judging whether the vehicle is parked regularly comprises any one or more of following judgments:
judging whether the vehicle presses at least one of the parking lines;
judging whether a parking angle of the vehicle is within a preset angle offset range;
judging whether a center-of-gravity of the vehicle is within a preset center-of-gravity offset range.

### Claim 19 (depends on 2)

A processing device, comprising: a memory, a processor and a computer program stored on the memory and executable by the processor, wherein steps of the method according to claim 2 are implemented when the processor executes the program.

### Claim 20 (depends on 3)

A processing device, comprising: a memory, a processor and a computer program stored on the memory and executable by the processor, wherein steps of the method according to claim 3 are implemented when the processor executes the program.
