Research on Pedestrian Multi-Object Tracking Network Based on Multi-Order Semantic Fusion

Aiming at the problem of insufficient tracking accuracy caused by object occlusion in the process of multi-object tracking, this paper proposes a multi-order semantic fusion pedestrian multi-object tracking network. Firstly, the feature pyramid attention module is used in the backbone network to enl...

Full description

Bibliographic Details

Published in:	World Electric Vehicle Journal
Main Authors:	Cong Liu, Chao Han
Format:	Article
Language:	English
Published:	MDPI AG 2023-10-01
Subjects:	multi-object tracking object occlusion tracking accuracy semantic fusion autonomous driving
Online Access:	https://www.mdpi.com/2032-6653/14/10/272