Visual Tracking via Nonnegative Multiple Coding

Publisher:
Institute of Electrical and Electronics Engineers
Publication Type:
Journal Article
Citation:
IEEE Transactions on Multimedia, 2017
Issue Date:
2017-05-28
Full metadata record
Files in This Item:
Filename Description Size
TMM2708424-1.pdfAccepted Manuscript1.79 MB
Adobe PDF
It has been extensively observed that an accurate appearance model is critical to achieving satisfactory performance for robust object tracking. Most existing top-ranked methods rely on linear representation over a single dictionary, which brings about improper understanding on the target appearance. To address this problem, in this paper, we propose a novel appearance model named as “Nonnegative Multiple Coding” (NMC) to accurately represent a target. First, a series of local dictionaries are created with different pre-defined numbers of nearest neighbors, and then the contributions of these dictionaries are automatically learned. As a result, this ensemble of dictionaries can comprehensively exploit the appearance information carried by all the constituted dictionaries. Second, the existing methods explicitly impose the nonnegative constraint to coefficient vectors, but in the proposed model, we directly deploy an efficient `2 norm regularization to achieve the similar nonnegative purpose with theoretical guarantees. Moreover, an efficient occlusion detection scheme is designed to alleviate tracking drifts, and it investigates whether negative templates are selected to represent the severely occluded target. Experimental results on two benchmarks demonstrate that our NMC tracker is able to achieve superior performance to state-of-the-art methods.
Please use this identifier to cite or link to this item: