Tracking multiple mouse contours (without too many samples)

Research output: Contribution to journal › Conference article › Research › peer-review

Standard

Tracking multiple mouse contours (without too many samples). / Branson, Kristin; Belongie, Serge.

In: Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, 2005, p. 1039-1046.

Research output: Contribution to journal › Conference article › Research › peer-review

Harvard

Branson, K & Belongie, S 2005, 'Tracking multiple mouse contours (without too many samples)', Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, pp. 1039-1046. https://doi.org/10.1109/CVPR.2005.349

APA

Branson, K., & Belongie, S. (2005). Tracking multiple mouse contours (without too many samples). Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, 1039-1046. https://doi.org/10.1109/CVPR.2005.349

Vancouver

Branson K, Belongie S. Tracking multiple mouse contours (without too many samples). Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. 2005;1039-1046. https://doi.org/10.1109/CVPR.2005.349

Author

Branson, Kristin ; Belongie, Serge. / Tracking multiple mouse contours (without too many samples). In: Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. 2005 ; pp. 1039-1046.

Bibtex

@inproceedings{0a6e574e67ea48c58fc755162c0b5321,
title = "Tracking multiple mouse contours (without too many samples)",
abstract = "We present a particle filtering algorithm for robustly tracking the contours of multiple deformable objects through severe occlusions. Our algorithm combines a multiple blob tracker with a contour tracker in a manner that keeps the required number of samples small This is a natural combination because both algorithms have complementary strengths. The multiple blob tracker uses a natural multitarget model and searches a smaller and simpler space. On the other hand, contour tracking gives more fine-tuned results and relies on cues that are available during severe occlusions. Our choice of combination of these two algorithms accentuates the advantages of each. We demonstrate good performance on challenging video of three identical mice that contains multiple instances of severe occlusion.",
author = "Kristin Branson and Serge Belongie",
year = "2005",
doi = "10.1109/CVPR.2005.349",
language = "English",
pages = "1039--1046",
journal = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",
note = "2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 ; Conference date: 20-06-2005 Through 25-06-2005",

}

RIS

TY - GEN

T1 - Tracking multiple mouse contours (without too many samples)

AU - Branson, Kristin

AU - Belongie, Serge

PY - 2005

Y1 - 2005

N2 - We present a particle filtering algorithm for robustly tracking the contours of multiple deformable objects through severe occlusions. Our algorithm combines a multiple blob tracker with a contour tracker in a manner that keeps the required number of samples small This is a natural combination because both algorithms have complementary strengths. The multiple blob tracker uses a natural multitarget model and searches a smaller and simpler space. On the other hand, contour tracking gives more fine-tuned results and relies on cues that are available during severe occlusions. Our choice of combination of these two algorithms accentuates the advantages of each. We demonstrate good performance on challenging video of three identical mice that contains multiple instances of severe occlusion.

AB - We present a particle filtering algorithm for robustly tracking the contours of multiple deformable objects through severe occlusions. Our algorithm combines a multiple blob tracker with a contour tracker in a manner that keeps the required number of samples small This is a natural combination because both algorithms have complementary strengths. The multiple blob tracker uses a natural multitarget model and searches a smaller and simpler space. On the other hand, contour tracking gives more fine-tuned results and relies on cues that are available during severe occlusions. Our choice of combination of these two algorithms accentuates the advantages of each. We demonstrate good performance on challenging video of three identical mice that contains multiple instances of severe occlusion.

UR - http://www.scopus.com/inward/record.url?scp=33745171104&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2005.349

DO - 10.1109/CVPR.2005.349

M3 - Conference article

AN - SCOPUS:33745171104

SP - 1039

EP - 1046

JO - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

JF - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

T2 - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

Y2 - 20 June 2005 through 25 June 2005

ER -

ID: 302054819