Multi-video Supervisory Target Tracking Improved by Interactive On-line Learning

Abstract

It is difficult for a human operator to monitor multiple video streams in real-time surveillance tasks. A variety of machine learning algorithms have been proposed for target tracking, but human intervention is still necessary because the algorithms have limitations to detect and recover from tracking failures. In this paper, we propose a supervisory target tracking method for multi-video surveillance tasks based on hTLD (human-in-the-loop Tracking-Learning-Detection). The human operator can monitor both the original video streams and the calculated confidence values of the tracking results. Human intervention allows to update the training data for TLD whenever a tracking failure is observed, by manually drawing a bounding box or using an eye-tracker to relocate the target. Meanwhile, an interactive on-line learning algorithm is used to learn the relations between the confidence values and the tracking results. In this way, the confidence values help avoid unnecessary intervention caused by false alarms of tracking failures. Experimental results have demonstrated that the proposed method can reduce the task completion time.

Affiliations

College of Intelligent Systems, National University of Defense Technology

De Ya Lu 109, Changsha, Hu’nan, China, 410073

Contributors

Chang Wang

Yifeng Niu

Conference

Publication date: July 2018

Publication date (Print): July 2018

Pages: 1-5

ID: 10.14236/ewic/HCI2018.133

Copyright statement: © Wang et al. Published by BCS Learning and Development Ltd. Proceedings of British HCI 2018. Belfast, UK.

License:

This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

Conference name: Proceedings of the 32nd International BCS Human Computer Interaction Conference

Conference acronym: HCI

Conference number: 32

Conference location: Belfast, UK

Conference date: 4 - 6 July 2018

Conference sponsor: Electronic Workshops in Computing (eWiC)

Conference theme: Human Computer Interaction Conference

Product

Product Information: 1477-9358 BCS Learning & Development

Self URI (article page): https://www.scienceopen.com/hosted-document?doi=10.14236/ewic/HCI2018.133

Self URI (journal page): https://ewic.bcs.org/

Categories

Series title: Electronic Workshops in Computing