US 12,293,565 B2
Method and apparatus for classifying object and recording medium storing program to execute the method
So Jin Jang, Seoul (KR); Jin Kyu Hwang, Suwon-si (KR); Hyun Ju Kim, Yongin-si (KR); Min Seong Park, Seoul (KR); Won Je Jang, Goyang-si (KR); and Eun Tai Kim, Seoul (KR)
Assigned to HYUNDAI MOTOR COMPANY, Seoul (KR); KIA CORPORATION, Seoul (KR); and INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITY, Seoul (KR)
Filed by HYUNDAI MOTOR COMPANY, Seoul (KR); KIA CORPORATION, Seoul (KR); and INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITY, Seoul (KR)
Filed on Jun. 22, 2022, as Appl. No. 17/846,627.
Claims priority of application No. 10-2021-0080955 (KR), filed on Jun. 22, 2021.
Prior Publication US 2022/0406037 A1, Dec. 22, 2022
Int. Cl. G06N 20/10 (2019.01); G01S 17/89 (2020.01); G01S 17/931 (2020.01); G06V 10/26 (2022.01); G06V 10/50 (2022.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/764 (2022.01) [G01S 17/89 (2013.01); G01S 17/931 (2020.01); G06N 20/10 (2019.01); G06V 10/26 (2022.01); G06V 10/50 (2022.01); G06V 10/762 (2022.01); G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method of classifying an object, the method comprising:
extracting, by a processor, a first feature by transforming rectangular coordinates of points included in a box of the object, obtained from a point cloud acquired using a LiDAR sensor, into complex coordinates and performing Fast Fourier Transform (FFT) on the complex coordinates;
obtaining, by the processor, an average and a standard deviation as a second feature, the average and the standard deviation being parameters of a Gaussian model for the points included in the box of the object;
classifying, by the processor, a type of the object based on at least one of the first feature or the second feature; and
controlling, by the processor, a host vehicle to autonomously drive based on the classified type of the object.