Visual multi-object tracking with re-identification and occlusion handling using labeled random finite sets

Download PDF
Open Webpage

Linh Van Ma, Tran Thien Dat Nguyen, Changbeom Shim, Du Yong Kim, Namkoo Ha, Moongu Jeon

Published: 01 Jan 2024, Last Modified: 11 Nov 2025Pattern Recognit. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Deep features and occlusion handling model enhance visual MOT performance.•Deep features improve track re-ID and appearance–reappearance resolution.•Labeled random finite set filters (GLMB and LMB) are effective for visual tracking.