Structure-aware multi-object discovery for weakly supervised tracking
Authors:
- 1 October 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 466-470
Abstract
Recent progress on tracking has focused on designing robust statistical model or proposing effective appearance features to improve precision. This paper addresses another problem, namely the discovery and tracking of generic multi-object which have the similar appearance and motion pattern based on limited human annotations. We present a model-free tracking method that can automatically discover and track multi-object sharing the same spatial and motion structure, and update the structure during the tracking without prior acknowledge. The candidate objects are first selected by a SVM classifier trained on histogram-of-gradient (HOG) features. Then a segment algorithm is exploited to decide the suitable sizes of tracking boxes. The structure constrains are updated in a real-time manner according to the motion measure among the specified object and corresponding candidates. Experimental results reveal significant convenience and remarkable performance of our approach for the task of structure preserving multi-object discovery and tracking.Keywords
This publication has 8 references indexed in Scilit:
- HOGgles: Visualizing Object Detection Features2013
- Structure Preserving Object Tracking2013
- Robust Object Tracking with Online Multiple Instance LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- P-N learning: Bootstrapping binary classifiers by structural constraints2010
- Visual tracking decomposition2010
- Real-time hand-tracking with a color glove2009
- Model-free tracking of cars and people based on color regionsImage and Vision Computing, 2006
- Tracking multiple humans in complex situationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004