TY - GEN
T1 - SOWP
T2 - 15th IEEE International Conference on Computer Vision, ICCV 2015
AU - Kim, Han Ul
AU - Lee, Dae Youn
AU - Sim, Jae Young
AU - Kim, Chang Su
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/2/17
Y1 - 2015/2/17
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84973879720&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2015.345
DO - 10.1109/ICCV.2015.345
M3 - Conference contribution
AN - SCOPUS:84973879720
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 3011
EP - 3019
BT - 2015 International Conference on Computer Vision, ICCV 2015
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 11 December 2015 through 18 December 2015
ER -