US 12,306,009 B2
Method and apparatus for recognizing parking space
Wan Jin Kim, Yongin-si (KR)
Assigned to HYUNDAI MOBIS CO., LTD., Seoul (KR)
Filed by HYUNDAI MOBIS CO., LTD., Seoul (KR)
Filed on Nov. 9, 2022, as Appl. No. 17/983,768.
Claims priority of application No. 10-2022-0001480 (KR), filed on Jan. 5, 2022.
Prior Publication US 2023/0213352 A1, Jul. 6, 2023
Int. Cl. G01C 21/00 (2006.01); B60W 30/06 (2006.01); G01S 7/48 (2006.01); G01S 17/86 (2020.01); G01S 17/89 (2020.01); G06F 18/23 (2023.01); G06V 20/58 (2022.01)
CPC G01C 21/3815 (2020.08) [B60W 30/06 (2013.01); G01C 21/3841 (2020.08); G01S 7/4802 (2013.01); G01S 17/86 (2020.01); G01S 17/89 (2013.01); G06F 18/23 (2023.01); G06V 20/586 (2022.01); G06V 20/582 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A method, performed by an apparatus of a host vehicle, for recognizing a parking space, the method comprising:
recognizing another vehicle and a pillar based on data acquired from a light detection and ranging (lidar) device, including:
clustering points related to a single object from a point cloud acquired from the lidar device;
calculating a first point and a second point with a longest distance from a straight line distance in the clustered points;
calculating a third point, from the clustered points, at a longest distance from a first straight line that connects the first point and the second point;
calculating a second straight line connecting the first and third points and a third straight line connecting the second and third points; and
identifying whether the single object is the another vehicle or the pillar, based on a value of an angle between the second straight line and the third straight line;
recognizing a parking slot marking based on an image captured by a camera;
generating a map of an indoor parking lot comprising one or more available parking spaces based on information on the recognized another vehicle, the recognized pillar, and the recognized parking slot marking;
guiding a movement of the host vehicle to one of the one or more available parking spaces based on the generated map.