Skip to main navigation Skip to search Skip to main content

Multiple object tracking by incorporating a particle filter into the min-cost flow model

  • Liang Yingyi*
  • , Li Xin
  • , He Zhenyu
  • , You Xinge
  • *Corresponding author for this work
  • Harbin Institute of Technology Shenzhen
  • Huazhong University of Science and Technology

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

Abstract

A novel network flow model is proposed for multiple object tracking. Based on tracklets, only a short and reliable detection sequence is needed for an effective tracking. Our model fuses the local and global data association strategies to compensate for their respective shortcomings, which can be divided into two stages: A local stage and a global stage. In the local stage, we follow the tracking-by-detection framework to generate confident tracklets by employing a boosted particle filter. In the global stage, the data association problem is formulated as a Maximum-a-Posteriori (MAP) problem and solved by a typical min-cost flow algorithm. A double-step optimization is designed to solve the long term occlusion. The experimental results show that our method outperforms several state-of-the-art methods for multiple object tracking.

Original languageEnglish
Title of host publication2017 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages106-111
Number of pages6
ISBN (Electronic)9781538630167
DOIs
StatePublished - 2 Jul 2017
Externally publishedYes
Event2017 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2017 - Shenzhen, China
Duration: 15 Dec 201717 Dec 2017

Publication series

Name2017 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2017
Volume2018-January

Conference

Conference2017 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2017
Country/TerritoryChina
CityShenzhen
Period15/12/1717/12/17

Keywords

  • multiple cues
  • network flow
  • particle filter

Fingerprint

Dive into the research topics of 'Multiple object tracking by incorporating a particle filter into the min-cost flow model'. Together they form a unique fingerprint.

Cite this