Detection-Free Multiobject Tracking by Reconfigurable Inference With Bundle Representations
- 29 September 2015
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 46 (11), 2447-2458
- https://doi.org/10.1109/tcyb.2015.2478515
Abstract
This paper presents a conceptually simple but effective approach to track multiobject in videos without requiring elaborate supervision (i.e., training object detectors or templates offline). Our framework performs a bi-layer inference of spatio-temporal grouping to exploit rich appearance and motion information in the observed sequence. First, we generate a robust middle-level video representation based on clustered point tracks, namely video bundles. Each bundle encapsulates a chunk of point tracks satisfying both spatial proximity and temporal coherency. Taking the video bundles as vertices, we build a spatio-temporal graph that incorporates both competitive and compatible relations among vertices. The multiobject tracking can be then phrased as a graph partition problem under the Bayesian framework, and we solve it by developing a reconfigurable belief propagation (BP) algorithm. This algorithm improves the traditional BP method by allowing a converged solution to be reconfigured during optimization, so that the inference can be reactivated once it gets stuck in local minima and thus conduct more reliable results. In the experiments, we demonstrate the superior performances of our approach on the challenging benchmarks compared with other state-of-the-art methods.Keywords
Funding Information
- National Natural Science Foundation of China (61271093)
- Guangdong Natural Science Foundation (S2013050014548, 2014A030313201)
- Program of Guangzhou Zhujiang Star of Science and Technology (2013J2200067)
- Science and Technology Program of Guangzhou (1563000439)
This publication has 35 references indexed in Scilit:
- Visual Tracking via Weighted Local Cosine SimilarityIEEE Transactions on Cybernetics, 2014
- Tracking by Third-Order Tensor RepresentationIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2010
- Monocular 3D pose estimation and tracking by detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Efficiently Scaling Up Video Annotation with Crowdsourced MarketplacesLecture Notes in Computer Science, 2010
- Segmentation and Tracking of Multiple Humans in Crowded EnvironmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part DetectorsInternational Journal of Computer Vision, 2007
- Understanding popout through repulsionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A Boosted Particle Filter: Multitarget Detection and TrackingLecture Notes in Computer Science, 2004
- Fast approximate energy minimization via graph cutsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Factor graphs and the sum-product algorithmIEEE Transactions on Information Theory, 2001