SOWP

Spatially ordered and weighted patch descriptor for visual tracking

Han Ul Kim, Dae Youn Lee, Jae Young Sim, Chang-Su Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

40 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3011-3019
Number of pages9
Volume11-18-December-2015
ISBN (Electronic)9781467383912
DOIs
Publication statusPublished - 2016 Feb 17
Event15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile
Duration: 2015 Dec 112015 Dec 18

Other

Other15th IEEE International Conference on Computer Vision, ICCV 2015
CountryChile
CitySantiago
Period15/12/1115/12/18

Fingerprint

Color

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Kim, H. U., Lee, D. Y., Sim, J. Y., & Kim, C-S. (2016). SOWP: Spatially ordered and weighted patch descriptor for visual tracking. In Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015 (Vol. 11-18-December-2015, pp. 3011-3019). [7410702] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2015.345

SOWP : Spatially ordered and weighted patch descriptor for visual tracking. / Kim, Han Ul; Lee, Dae Youn; Sim, Jae Young; Kim, Chang-Su.

Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. Vol. 11-18-December-2015 Institute of Electrical and Electronics Engineers Inc., 2016. p. 3011-3019 7410702.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, HU, Lee, DY, Sim, JY & Kim, C-S 2016, SOWP: Spatially ordered and weighted patch descriptor for visual tracking. in Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. vol. 11-18-December-2015, 7410702, Institute of Electrical and Electronics Engineers Inc., pp. 3011-3019, 15th IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 15/12/11. https://doi.org/10.1109/ICCV.2015.345
Kim HU, Lee DY, Sim JY, Kim C-S. SOWP: Spatially ordered and weighted patch descriptor for visual tracking. In Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. Vol. 11-18-December-2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 3011-3019. 7410702 https://doi.org/10.1109/ICCV.2015.345
Kim, Han Ul ; Lee, Dae Youn ; Sim, Jae Young ; Kim, Chang-Su. / SOWP : Spatially ordered and weighted patch descriptor for visual tracking. Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015. Vol. 11-18-December-2015 Institute of Electrical and Electronics Engineers Inc., 2016. pp. 3011-3019
@inproceedings{7ba1bf870a6c4937a50d243cd6c08fd4,
title = "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.",
author = "Kim, {Han Ul} and Lee, {Dae Youn} and Sim, {Jae Young} and Chang-Su Kim",
year = "2016",
month = "2",
day = "17",
doi = "10.1109/ICCV.2015.345",
language = "English",
volume = "11-18-December-2015",
pages = "3011--3019",
booktitle = "Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - SOWP

T2 - Spatially ordered and weighted patch descriptor for visual tracking

AU - Kim, Han Ul

AU - Lee, Dae Youn

AU - Sim, Jae Young

AU - Kim, Chang-Su

PY - 2016/2/17

Y1 - 2016/2/17

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

UR - http://www.scopus.com/inward/citedby.url?scp=84973879720&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2015.345

DO - 10.1109/ICCV.2015.345

M3 - Conference contribution

VL - 11-18-December-2015

SP - 3011

EP - 3019

BT - Proceedings - 2015 IEEE International Conference on Computer Vision, ICCV 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -