Multi-object model-free tracking with joint appearance and motion inference

Chongyu Liu, Rui Yao, S. Hamid Rezatofighi, Ian Reid, Qinfeng Shi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)

Abstract

Multi-object model-free tracking is challenging because the tracker is not aware of the objects' type (not allowed to use object detectors), and needs to distinguish one object from background as well as other similar objects. Most existing methods keep updating their appearance model individually for each target, and their performance is hampered by sudden appearance change and/or occlusion. We propose to use both appearance model and motion model to overcome this issue. We introduce an indicator variable to predict sudden appearance change and occlusion. When they happen, our model stops updating the appearance model to avoid parameter update based on background or incorrect object, and rely more on motion model to track. Moreover, we consider the correlation among all targets, and seek the joint optimal locations for all target simultaneously. We formulate the problem of finding the most likely locations jointly as a graphical model inference problem, and learn the joint parameters for both appearance model and motion model in an online fashion in the framework of LaRank. Experiment results show that our method outperforms the state-of-the-art.

Original languageEnglish
Title of host publication2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
EditorsYi Guo, Hongdong Li, Tom Cai, Manzur Murshed
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages604-611
Number of pages8
ISBN (Electronic)9781538628393, 9781538628386
ISBN (Print)9781538628409
DOIs
Publication statusPublished - 2017
Externally publishedYes
EventDigital Image Computing Techniques and Applications 2017
- Novotel Sydney Manly Pacific , Sydney, Australia
Duration: 29 Nov 20171 Dec 2017
Conference number: 19th
http://dicta2017.dictaconference.org/
https://ieeexplore.ieee.org/xpl/conhome/8226656/proceeding (Proceedings)

Conference

ConferenceDigital Image Computing Techniques and Applications 2017
Abbreviated titleDICTA 2017
CountryAustralia
CitySydney
Period29/11/171/12/17
Internet address

Cite this