Journal
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 27, Issue 9, Pages 4478-4489Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2018.2839916
Keywords
Visual tracking; sparse representation; template update; spatio-temporal context
Funding
- National Key Research and Development Program of China [2018YFB1003702]
- Hunan Provincial Natural Science Foundation of China for Distinguished Young Scholars [2018JJ025]
- NSF of Jiangsu Province [BK20151529, BK20170040]
- Six Talent Peaks Project in Jiangsu Province [R2017L07]
- Natural Science Foundation of China [61773002]
- Applied Basic Research Project in Shanxi Province [201601D011007]
- National Natural Science Foundation of China [61672215, 91320103]
- Special Project on the Integration of Industry, Education and Research of Guangdong Province, China [2012A090300003]
- Science and Technology Planning Project of Guangdong Province, China [2013B090700003]
Ask authors/readers for more resources
Sparse representation has been widely exploited to develop an effective appearance model for object tracking due to its well discriminative capability in distinguishing the target from its surrounding background. However, most of these methods only consider either the holistic representation or the local one for each patch with equal importance, and hence may fail when the target suffers from severe occlusion or large-scale pose variation. In this paper, we propose a simple yet effective approach that exploits rich feature information from reliable patches based on weighted local sparse representation that takes into account the importance of each patch. Specifically, we design a reconstruction-error based weight function with the reconstruction error of each patch via sparse coding to measure the patch reliability. Moreover, we explore spatio-temporal context information to enhance the robustness of the appearance model, in which the global temporal context is learned via incremental subspace and sparse representation learning with a novel dynamic template update strategy to update the dictionary, while the local spatial context considers the correlation between the target and its surrounding background via measuring the similarity among their sparse coefficients. Extensive experimental evaluations on two large tracking benchmarks demonstrate favorable performance of the proposed method over some state-of-the-art trackers.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available