Ensembles of correlation filters for object detection

Ryan Tokola; David Bolme

doi:10.1109/WACV.2015.129

Ensembles of correlation filters for object detection

Ryan Tokola, David Bolme

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

5 Scopus citations

Abstract

Traditional correlation filters for object detection are efficient and provide good localization, but require scalar valued image features and only perform well on objects with consistent appearance. Some newer filters work with feature spaces that introduce some invariance to small deformations, but more difficult detection problems require more than one filter. We introduce a method for jointly learning an ensemble of correlation filters that collectively capture as much variation in object appearance as possible. During training our filters adapt to the needs of the training data with no restrictions on size or scope. We demonstrate performance that exceeds the state of the art in several challenging experiments.

Original language	English
Title of host publication	Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	935-942
Number of pages	8
ISBN (Electronic)	9781479966820
DOIs	https://doi.org/10.1109/WACV.2015.129
State	Published - Feb 19 2015
Event	2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015 - Waikoloa, United States Duration: Jan 5 2015 → Jan 9 2015

Publication series

Name	Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

Conference

Conference	2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015
Country/Territory	United States
City	Waikoloa
Period	01/5/15 → 01/9/15

Funding

Funders	Funder number
Defense Advanced Research Projects Agency	HR0011-13-2-0016

Access to Document

10.1109/WACV.2015.129

Cite this

Tokola, R., & Bolme, D. (2015). Ensembles of correlation filters for object detection. In Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015 (pp. 935-942). Article 7045983 (Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WACV.2015.129

@inproceedings{c22bb0fa75244cab9aed481cd8d6c216,

title = "Ensembles of correlation filters for object detection",

abstract = "Traditional correlation filters for object detection are efficient and provide good localization, but require scalar valued image features and only perform well on objects with consistent appearance. Some newer filters work with feature spaces that introduce some invariance to small deformations, but more difficult detection problems require more than one filter. We introduce a method for jointly learning an ensemble of correlation filters that collectively capture as much variation in object appearance as possible. During training our filters adapt to the needs of the training data with no restrictions on size or scope. We demonstrate performance that exceeds the state of the art in several challenging experiments.",

author = "Ryan Tokola and David Bolme",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015 ; Conference date: 05-01-2015 Through 09-01-2015",

year = "2015",

month = feb,

day = "19",

doi = "10.1109/WACV.2015.129",

language = "English",

series = "Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "935--942",

booktitle = "Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015",

}

Tokola, R & Bolme, D 2015, Ensembles of correlation filters for object detection. in Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015., 7045983, Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015, Institute of Electrical and Electronics Engineers Inc., pp. 935-942, 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015, Waikoloa, United States, 01/5/15. https://doi.org/10.1109/WACV.2015.129

Ensembles of correlation filters for object detection. / Tokola, Ryan ; Bolme, David.
Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 935-942 7045983 (Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015).

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

TY - GEN

T1 - Ensembles of correlation filters for object detection

AU - Tokola, Ryan

AU - Bolme, David

PY - 2015/2/19

Y1 - 2015/2/19

N2 - Traditional correlation filters for object detection are efficient and provide good localization, but require scalar valued image features and only perform well on objects with consistent appearance. Some newer filters work with feature spaces that introduce some invariance to small deformations, but more difficult detection problems require more than one filter. We introduce a method for jointly learning an ensemble of correlation filters that collectively capture as much variation in object appearance as possible. During training our filters adapt to the needs of the training data with no restrictions on size or scope. We demonstrate performance that exceeds the state of the art in several challenging experiments.

AB - Traditional correlation filters for object detection are efficient and provide good localization, but require scalar valued image features and only perform well on objects with consistent appearance. Some newer filters work with feature spaces that introduce some invariance to small deformations, but more difficult detection problems require more than one filter. We introduce a method for jointly learning an ensemble of correlation filters that collectively capture as much variation in object appearance as possible. During training our filters adapt to the needs of the training data with no restrictions on size or scope. We demonstrate performance that exceeds the state of the art in several challenging experiments.

UR - http://www.scopus.com/inward/record.url?scp=84925433362&partnerID=8YFLogxK

U2 - 10.1109/WACV.2015.129

DO - 10.1109/WACV.2015.129

M3 - Conference contribution

AN - SCOPUS:84925433362

T3 - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

SP - 935

EP - 942

BT - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015

Y2 - 5 January 2015 through 9 January 2015

ER -

Ensembles of correlation filters for object detection

Abstract

Publication series

Conference

Funding

Access to Document

Other files and links

Fingerprint

Cite this