公开(公告)号：US20250166415A1

公开(公告)日：2025-05-22

申请号：US18592497

申请日：2024-02-29

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Je-Seok HAM ,  Dae Hoe KIM ,  Jinyoung MOON ,  Sungchan OH

IPC: G06V40/20 ,  G06V10/42 ,  G06V10/44 ,  G06V10/82 ,  G06V20/58 ,  G06V20/70 ,  G06V40/10

Abstract: A method of generating pedestrian behavior prediction information includes setting image information from present to a certain time in the past as the target observation image, extract multiple visual input feature information and non-visual input feature information from the target observation image, grouping the multiple visual input feature information and non-visual input feature information, and inputting the grouped information to separated processing modules and generating pedestrian behavior prediction information by concatenating output results of the processing modules.

公开(公告)号：US20250166381A1

公开(公告)日：2025-05-22

申请号：US18584703

申请日：2024-02-22

Applicant: Electronics and Telecommunications Research Institute

Inventor： Dae Hoe KIM ,  Jinyoung MOON ,  Sungchan OH ,  Je-Seok HAM

IPC: G06V20/52 ,  G06V10/25 ,  G06V10/26 ,  G06V10/75 ,  G06V10/82 ,  G06V40/10 ,  G08G1/16

Abstract: A method of estimating a pedestrian risk situation includes receiving an image captured by a CCTV camera that is installed at a predetermined location, generating a bounding box of a pedestrian within the image, generating a segmentation map by performing semantic segmentation on the image, generating a ground area map by identifying a ground area in the segmentation map, and estimating semantic location information of the pedestrian based on the bounding box and the ground area map.