Track initialization and re-identification for 3D multi-view multi-object tracking

Linh Van Ma, Tran Thien Dat Nguyen, Ba-Ngu Vo, Hyunsung Jang, Moongu Jeon

Abstract: Highlights•Novel 3D multi-object tracking models with re-identification features.•A filter that performs 3D tracking by fusing multi-view 2D camera detections.•Our Method automatically initializes/terminates, re-identifies, and handles occlusion.•An efficient filter with linear complexity in the number of detections.•Extensive experiments to evaluate the performance on challenging benchmark. datasets.

External IDs:dblp:journals/inffus/MaNVJJ24