US 12,190,560 B2
Automatic labeling method for unlabeled data of point clouds
Jin Kyu Hwang, Suwon-si (KR); Ya Gyeol Seo, Seoul (KR); Jae Hyun Park, Seoul (KR); Su Rin Jo, Anyang-si (KR); Min Hyeok Lee, Seoul (KR); Seung Hoon Lee, Uiwang-si (KR); Jun Hyeop Lee, Jeju-si (KR); and Sang Youn Lee, 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 Sep. 1, 2022, as Appl. No. 17/901,511.
Claims priority of application No. 10-2022-0025396 (KR), filed on Feb. 25, 2022.
Prior Publication US 2023/0274526 A1, Aug. 31, 2023
Int. Cl. G06V 10/762 (2022.01); G06V 10/778 (2022.01)
CPC G06V 10/762 (2022.01) [G06V 10/7784 (2022.01)] 20 Claims
OG exemplary drawing
 
1. An automatic labeling method for automatically assigning labels to unlabeled point clouds among a set of labeled and unlabeled point clouds, the automatic labeling method comprising:
(a) preparing an initial machine learning classification model;
(b) selecting a labeled point cloud for each of the unlabeled point clouds based on similarities between a feature vector of each of the unlabeled point clouds output through the model and feature vectors of the labeled point clouds output through the model and assigning a cluster label to each of the unlabeled point clouds based on a label of the selected labeled point cloud;
(c) assigning pseudo labels to the unlabeled point clouds to which the cluster labels are assigned, wherein each pseudo label is assigned based on a confidence score obtained through the model; and
(d) updating the model by training the model with the labeled point clouds and the unlabeled point clouds to which the pseudo labels are assigned, wherein, steps (b) through (d) are performed iteratively after step (d).