Multiple instance learning tracking method with local sparse representation. Issue 5 (1st October 2013)

• Record Type: Journal Article
• Authors: Xie, Chengjun; Tan, Jieqing; Chen, Peng; Zhang, Jie; He, Lei
• Is Part Of: IET computer vision. Volume 7:Issue 5(2013)
• Page Start: 320
• Page End: 334
• Publication Date: 2013-10-01
• Subjects: image representation -- image sequences -- learning (artificial intelligence) -- particle filtering (numerical methods) -- video signal processing -- object tracking; multiple instance learning tracking method -- local sparse representation -- illumination variation -- partial occlusion -- visual tracking algorithms -- online algorithm -- video system -- local sparse codes -- MIL framework -- local image patches -- adaptive representation -- sparse codes -- particle filter framework -- visual drift -- two-step object tracking method -- dynamical MIL classifier -- static MIL classifier -- video sequences -- overcomplete dictionary; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2012.0228
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : When objects undergo large pose change, illumination variation or partial occlusion, most existed visual tracking algorithms tend to drift away from targets and even fail in tracking them. To address this issue, in this study, the authors propose an online algorithm by combining multiple instance learning (MIL) and local sparse representation for tracking an object in a video system. The key idea in our method is to model the appearance of an object by local sparse codes that can be formed as training data for the MIL framework. First, local image patches of a target object are represented as sparse codes with an overcomplete dictionary, where the adaptive representation can be helpful in overcoming partial occlusion in object tracking. Then MIL learns the sparse codes by a classifier to discriminate the target from the background. Finally, results from the trained classifier are input into a particle filter framework to sequentially estimate the target state over time in visual tracking. In addition, to decrease the visual drift because of the accumulative errors when updating the dictionary and classifier, a two‐step object tracking method combining a static MIL classifier with a dynamical MIL classifier is proposed. Experiments on some publicly available benchmarks of video sequences show that our proposed tracker is more robust and effective than others.