Fast object tracking using color histograms and patch differences

Dae Youn Lee; Jae Young Sim; Chang-Su Kim

doi:10.1109/ICIP.2013.6738804

Fast object tracking using color histograms and patch differences

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

A fast visual object tracking algorithm using novel object appearance models is proposed in this work. We develop a color histogram model and a patch difference model to extract color and texture feature vectors, respectively. Then, we apply k-nearest neighbor classifiers to the color and texture feature vectors and obtain the foreground probability map. We then perform a hierarchical mean shift process on the map to identify the object window. Experimental results demonstrate that proposed algorithm outperforms the conventional algorithms in terms of both tracking accuracy and processing speed.

Original language	English
Title of host publication	2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Pages	3905-3908
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2013.6738804
Publication status	Published - 2013
Event	2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, Australia Duration: 2013 Sept 15 → 2013 Sept 18

Publication series

Name	2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

Other

Other	2013 20th IEEE International Conference on Image Processing, ICIP 2013
Country/Territory	Australia
City	Melbourne, VIC
Period	13/9/15 → 13/9/18

Keywords

Object tracking
appearance model
k-nearest neighbor
mean shift localization
tracking-by-detection

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICIP.2013.6738804

Cite this

Fast object tracking using color histograms and patch differences. / Lee, Dae Youn; Sim, Jae Young; Kim, Chang-Su.
2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 3905-3908 6738804 (2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lee, DY, Sim, JY & Kim, C-S 2013, Fast object tracking using color histograms and patch differences. in 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings., 6738804, 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings, pp. 3905-3908, 2013 20th IEEE International Conference on Image Processing, ICIP 2013, Melbourne, VIC, Australia, 13/9/15. https://doi.org/10.1109/ICIP.2013.6738804

@inproceedings{08dc6340d23943ab9c076d7a13578fdf,

title = "Fast object tracking using color histograms and patch differences",

abstract = "A fast visual object tracking algorithm using novel object appearance models is proposed in this work. We develop a color histogram model and a patch difference model to extract color and texture feature vectors, respectively. Then, we apply k-nearest neighbor classifiers to the color and texture feature vectors and obtain the foreground probability map. We then perform a hierarchical mean shift process on the map to identify the object window. Experimental results demonstrate that proposed algorithm outperforms the conventional algorithms in terms of both tracking accuracy and processing speed.",

keywords = "Object tracking, appearance model, k-nearest neighbor, mean shift localization, tracking-by-detection",

author = "Lee, {Dae Youn} and Sim, {Jae Young} and Chang-Su Kim",

year = "2013",

doi = "10.1109/ICIP.2013.6738804",

language = "English",

isbn = "9781479923410",

series = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

pages = "3905--3908",

booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

note = "2013 20th IEEE International Conference on Image Processing, ICIP 2013 ; Conference date: 15-09-2013 Through 18-09-2013",

}

TY - GEN

T1 - Fast object tracking using color histograms and patch differences

AU - Lee, Dae Youn

AU - Sim, Jae Young

AU - Kim, Chang-Su

PY - 2013

Y1 - 2013

N2 - A fast visual object tracking algorithm using novel object appearance models is proposed in this work. We develop a color histogram model and a patch difference model to extract color and texture feature vectors, respectively. Then, we apply k-nearest neighbor classifiers to the color and texture feature vectors and obtain the foreground probability map. We then perform a hierarchical mean shift process on the map to identify the object window. Experimental results demonstrate that proposed algorithm outperforms the conventional algorithms in terms of both tracking accuracy and processing speed.

AB - A fast visual object tracking algorithm using novel object appearance models is proposed in this work. We develop a color histogram model and a patch difference model to extract color and texture feature vectors, respectively. Then, we apply k-nearest neighbor classifiers to the color and texture feature vectors and obtain the foreground probability map. We then perform a hierarchical mean shift process on the map to identify the object window. Experimental results demonstrate that proposed algorithm outperforms the conventional algorithms in terms of both tracking accuracy and processing speed.

KW - Object tracking

KW - appearance model

KW - k-nearest neighbor

KW - mean shift localization

KW - tracking-by-detection

UR - http://www.scopus.com/inward/record.url?scp=84897769469&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897769469&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738804

DO - 10.1109/ICIP.2013.6738804

M3 - Conference contribution

AN - SCOPUS:84897769469

SN - 9781479923410

T3 - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

SP - 3905

EP - 3908

BT - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

T2 - 2013 20th IEEE International Conference on Image Processing, ICIP 2013

Y2 - 15 September 2013 through 18 September 2013

ER -

Fast object tracking using color histograms and patch differences

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this