International Conference on Computer Vision (ICCV), 2015 IEEE Conference on.
SOWP: Spatially Ordered and Weighted Patch Descriptor for Visual Tracking
Abstract
A simple yet effective object descriptor for visual tracking is proposed in this paper. We first decompose the bounding box of a target object into multiple patches, which are described by color and gradient histograms. Then, we concatenate the features of the spatially ordered patches to represent the object appearance. Moreover, to alleviate the impacts of background information possibly included in the bounding box, we determine patch weights using random walk with restart (RWR) simulations. The patch weights represent the importance of each patch in the description of foreground information, and are used to construct an object descriptor, called spatially ordered and weighted patch (SOWP) descriptor. We incorporate the proposed SOWP descriptor into the structured output tracking framework. Experimental results demonstrate that the proposed algorithm yields significantly better performance than the state-of-the-art trackers on a recent benchmark dataset, and also excels in another recent benchmark dataset.
Results
We evaluate the performance of the proposed tracker on the CVPR 2013 visual tracking benchmark dataset. [results]
Publication
Han-Ul Kim, Dae-Youn Lee, Jae-Young Sim, and Chang-Su Kim, "SOWP: Spatially Ordered and Weighted Patch Descriptor for Visual Tracking," in ICCV, Dec. 2015. [pdf] [binary file] [source code] [bibex]