CN-114155503-B - Vehicle for performing automatic parking and control method thereof

Abstract

A vehicle for performing automatic parking includes a camera configured to acquire a surrounding image of the vehicle including a parking line, and a controller configured to derive spatial identification data based on the surrounding image of the vehicle as an input value, derive feature points corresponding to the parking line based on the surrounding image and the spatial identification data, determine a candidate parking line based on a cluster of the feature points, and control the vehicle to perform parking in a parking area composed of the candidate parking line.

Inventors

• Jin Zhongmo
• Sun Mincheng
• LI HEJUAN
• Cui Zhenxu
• LI YUANJUN
• Liu Suxi

Assignees

• 现代自动车株式会社
• 起亚株式会社
• 现代摩比斯株式会社

Dates

Publication Date

20260512

Application Date

20210714

Priority Date

20200907

Claims (16)

1. 1. A vehicle for performing automatic parking, comprising: A camera for acquiring a surrounding image of the vehicle including a stop line, and A controller configured to: deriving spatial identification data based on the surrounding image as input value, Deriving feature points corresponding to the parking line based on the surrounding image and the spatial identification data, Deriving candidate parking lines based on the clustering of the feature points, and Controlling the vehicle to perform parking in a parking area consisting of the candidate parking lines, Wherein the controller is configured to determine the candidate parking line based on the first feature point and the second feature point when an overlap ratio of the first feature point determined based on the surrounding image of the vehicle and the second feature point determined based on the spatial identification data exceeds a predetermined value.
2. 2. The vehicle according to claim 1, wherein, The controller is configured to remove noise of a surrounding image of the vehicle by using a first filter, and extract an edge based on a gradient of each pixel included in the surrounding image of the vehicle.
3. 3. The vehicle according to claim 1, wherein, The controller is configured to classify objects included in a surrounding image of the vehicle into at least one category based on the spatial identification data.
4. 4. The vehicle according to claim 1, wherein, The controller is configured to derive a plurality of feature points corresponding to the parking line from the surrounding image of the vehicle and the spatial identification data using a second filter corresponding to a width of the parking line.
5. 5. The vehicle according to claim 4, wherein, The controller is configured to determine reliability of each of the plurality of feature points based on consistency of a direction value of each of the plurality of feature points corresponding to the parking line, and determine the candidate parking line based on feature points whose reliability exceeds a predetermined value.
6. 6. The vehicle according to claim 1, wherein, The controller is configured to determine the parking area based on the feature point corresponding to the parking line when the feature point corresponds to the parking line included in the surrounding image of the vehicle and the space identification data.
7. 7. The vehicle according to claim 1, wherein, The controller is configured to determine the parking area based on a ratio of a number of pixels corresponding to the parking line to a number of pixels of the feature point and the feature point.
8. 8. The vehicle according to claim 1, wherein, The controller is configured to determine a plurality of candidate park lines, determine a first region provided bounded by end points of the candidate park lines, determine a second region between the candidate park lines where the candidate park lines are not provided, and determine the park region based on a ratio of a number of pixels in the first region to a number of pixels in the second region.
9. 9. A control method for a vehicle that performs automatic parking, comprising: acquiring a surrounding image of the vehicle including a stop line; deriving spatial identification data based on the surrounding image as an input value; deriving feature points corresponding to the parking line based on the surrounding image and the spatial identification data; determining candidate parking lines based on the clusters of the feature points, and Controlling the vehicle to perform parking in a parking area consisting of the candidate parking lines, Wherein determining the candidate parking line includes determining the candidate parking line based on a first feature point determined based on a surrounding image of the vehicle and a second feature point determined based on the spatial identification data when an overlap ratio of the first feature point and the second feature point exceeds a predetermined value.
10. 10. The method of claim 9, wherein, Determining the candidate parking line includes: removing noise of surrounding image of the vehicle by using a first filter, and An edge is extracted based on a gradient of each pixel included in a surrounding image of the vehicle.
11. 11. The method of claim 9, wherein, Determining the candidate parking line includes: Objects included in the surrounding image of the vehicle are classified into at least one category based on the spatial identification data.
12. 12. The method of claim 9, wherein, Determining the candidate parking line includes deriving a plurality of feature points corresponding to the parking line from the surrounding image of the vehicle and the spatial identification data using a second filter corresponding to a width of the parking line.
13. 13. The method of claim 12, wherein, Determining the candidate parking line includes: determining reliability of each of the plurality of feature points based on consistency of direction values of each of the plurality of feature points corresponding to the parking line, and The candidate parking line is determined based on feature points whose reliability exceeds a predetermined value.
14. 14. The method of claim 9, wherein, Determining the candidate parking line includes determining the parking area based on the feature point corresponding to the parking line when the feature point corresponds to the parking line included in the surrounding image of the vehicle and the spatial identification data.
15. 15. The method of claim 9, wherein, Controlling the vehicle to perform parking in the parking area includes determining the parking area based on a ratio of a number of pixels corresponding to the parking line to a number of pixels of the feature point and the feature point.
16. 16. The method of claim 9, wherein, Controlling the vehicle to perform parking in the parking area includes: Determining a plurality of candidate parking lines; Determining a first region provided with an end point of the candidate parking line as a boundary; determining a second region between the candidate stop lines not providing the candidate stop lines, and The parking area is determined based on a ratio of a number of pixels in the first area to a number of pixels in the second area.

Description

Vehicle for performing automatic parking and control method thereof Technical Field The present disclosure relates to a vehicle for performing automatic parking and a control method thereof. Background The automatic driving technique is a technique that a vehicle grasps a road condition and automatically drives even if a driver does not manually control a brake, a steering wheel, or an accelerator pedal. The automatic driving technology is a core technology for realizing an intelligent automobile, and includes technologies such as a highway driving assistance system (HDA, technology for automatically maintaining a vehicle distance), a rear side warning system (BSD, technology for detecting a nearby vehicle and alerting when reversing), an automatic emergency braking system (AEB, technology for activating a braking system when a preceding vehicle is not recognized), a Lane Departure Warning System (LDWS), a lane keeping assistance system (LKAS, technology for compensating for departure from a lane without a steering signal), advanced intelligent cruise control (ASCC, technology for maintaining a distance between automobiles at a set speed and traveling at a constant speed), a congested road section driving assistance system (TJA), a parking assistance (PCA), and an automatic parking system (remote intelligent parking assistance). In a technique of identifying surrounding objects and parking spaces for automatic parking control of a vehicle, parking is performed using ultrasonic signals. In recent years, research into an automatic parking system that performs parking by additionally using a camera has been actively conducted. Disclosure of Invention The present disclosure provides a vehicle capable of performing an accurate automatic parking operation by learning an image obtained by a camera and using the learned data, and a control method thereof. According to aspects of the present disclosure, a vehicle for performing automatic parking may include a camera configured to acquire a surrounding image of the vehicle including a parking line, and a controller configured to derive spatial identification data based on the surrounding image of the vehicle as an input value, derive feature points corresponding to the parking line based on the surrounding image and the spatial identification data, determine a candidate parking line based on a cluster of the feature points, and control the vehicle to perform parking in a parking area having the candidate parking line. The controller may be configured to remove noise of a surrounding image of the vehicle by using a predetermined first filter, and extract an edge based on a gradient of each pixel included in the surrounding image of the vehicle. The controller may be configured to classify objects included in the surrounding image of the vehicle into at least one category based on the spatial identification data. The controller may be configured to derive a plurality of feature points corresponding to the parking line from the surrounding image of the vehicle and the spatial identification data using a predetermined second filter corresponding to the width of the parking line. The controller may be configured to determine reliability of each of the plurality of feature points based on consistency of the direction value of each of the plurality of feature points corresponding to the parking line, and determine the candidate parking line based on the feature points whose reliability exceeds a predetermined value. The controller may be configured to determine the parking area based on the feature points corresponding to the parking line when the feature points correspond to the parking line included in the surrounding image of the vehicle and the spatial identification data. The controller may be configured to determine the parking area based on a ratio of the number of pixels corresponding to the parking line to the number of pixels of the feature point and the feature point. The controller may be configured to determine the candidate parking line based on the first feature point and the second feature point when an overlap ratio of the first feature point determined based on the surrounding image of the vehicle and the second feature point determined based on the spatial identification data exceeds a predetermined value. The controller may be configured to determine a plurality of candidate parking lines, determine a first region provided bordering end points of the candidate parking lines, determine a second region between the candidate parking lines where the candidate parking lines are not provided, and determine a parking region based on a ratio of a number of pixels in the first region to a number of pixels in the second region. A control method for a vehicle that performs automatic parking includes acquiring a surrounding image of the vehicle including a parking line, deriving spatial identification data based on the surrounding image of the vehicle as an input va