Deep Relative Tracking
- 20 January 2017
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 26 (4), 1845-1858
- https://doi.org/10.1109/tip.2017.2656628
Abstract
Most existing tracking methods are direct trackers, which directly exploit foreground or/and background information for object appearance modeling and decide whether an image patch is target object or not. As a result, these trackers cannot perform well when target appearance changes heavily and becomes different from its model. To deal with this issue, we propose a novel relative tracker, which can effectively exploit the relative relationship among image patches from both foreground and background for object appearance modeling. Different from direct trackers, the proposed relative tracker is robust to localize target object by use of the best image patch with the highest relative score to the target appearance model. To model relative relationship among large-scale image patch pairs, we propose a novel and effective deep relative learning algorithm through the convolutional neural network. We test the proposed approach on challenging sequences involving heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that our method consistently outperforms the state-of-the-art trackers due to the powerful capacity of the proposed deep relative model.Keywords
Funding Information
- National Natural Science Foundation of China (61225009, 61432019, 61572498, 61532009, 61572296)
- Importation and Development of High-Caliber Talents Project of Beijing Municipal Institutions (IDHT20140224)
This publication has 40 references indexed in Scilit:
- Object Tracking BenchmarkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Cross-Domain Feature Learning in MultimediaIEEE Transactions on Multimedia, 2014
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Robust Visual Tracking Via Consistent Low-Rank Sparse LearningInternational Journal of Computer Vision, 2014
- Visual Tracking: An Experimental SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- A survey of appearance models in visual object trackingACM Transactions on Intelligent Systems and Technology, 2013
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Robust Visual Tracking via Structured Multi-Task Sparse LearningInternational Journal of Computer Vision, 2012
- Incremental Learning for Robust Visual TrackingInternational Journal of Computer Vision, 2007
- Kernel-based object trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003