Home // MOBILITY 2023, The Thirteenth International Conference on Mobile Services, Resources, and Users // View article

A Real-time Multiple People Tracking System in a Complex Environment

Authors:
Shi-Jinn Horng
Hu-Ke Li

Keywords: Deep learning; Target tracking; MOTA; MOTP.

Abstract:
Multiple Object Tracking is a major research field of computer vision due to increasing demand. Its application has become more and more extensive. The model proposed in this paper is an improved version of the traditional Deep Sort, which is mainly divided into two parts, the object detection part and the target tracking part. YOLOv5 (PA), the improved version of YOLOv5, is used as the front object detection model and it was trained specifically for the category of "person" in the CrowdHuman data set, which greatly improved the detection accuracy of the model in a complex environment. Based on the Deep Sort tracking architecture, the Re-ID accuracy of the model was improved by using Mahalanobis distance, Hungarian algorithm, Aligned ReID, etc., and the tracking was predicted by Kalman filtering. In this paper, we use videos from the MOT20 dataset as the main test scenario. While achieving good MOTA and MOTP, the running speed of this model is guaranteed to achieve the effect of real-time

Pages: 1 to 7

Copyright: Copyright (c) IARIA, 2023

Publication date: June 26, 2023

Published in: conference

ISSN: 2308-3468

ISBN: 978-1-68558-074-2

Location: Nice, France

Dates: from June 26, 2023 to June 30, 2023