An Improved Multi-target Tracking Method Integrating Visual Tracking Mechanism

Conference: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
12/17/2021 - 12/19/2021 at Shenyang, China

Proceedings: ICMLCA 2021

Pages: 5Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Yang, Dawei; Qi, Yan; Liu, Liping (School of Information Technology and Engineering, Shenyang Ligong University, Shenyang, China)
Wei, Chenyang (Lijin Senior High School, Dongying, China)

Abstract:
In this paper, to better solve the problem of frequent ID changes caused by false detection, missed detection and target occlusion in multi-target tracking, an improved multi-target tracking method integrating visual tracking mechanism is proposed. GOTURN algorithm integrated in the tracking method plays the role of visual tracking mechanism. Comparative experimental results between the improved method and the original method demonstrate the effectiveness of the proposed method.