Adaptive search of background models for object detection in images taken by moving cameras

Tsubasa Minematsu; Hideaki Uchiyama; Atsushi Shimada; Hajime Nagahara; Rin Ichiro Taniguchi

doi:10.1109/ICIP.2015.7351278

Adaptive search of background models for object detection in images taken by moving cameras

Tsubasa Minematsu, Hideaki Uchiyama, Atsushi Shimada, Hajime Nagahara, Rin Ichiro Taniguchi

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

4 Citations (Scopus)

Abstract

We propose a strategy of background subtraction for an image sequence captured by a moving camera. To adapt for camera motion, it is necessary to estimate the relation between consecutive frames in background subtraction. However, simple background subtraction using the relation between consecutive frames results in many false detections. We use re-projection error to handle this problem. The re-projection error has a low value in a background region. According to re-projection error, our method searches neighboring background models and tunes a threshold value for detection in order to reduce false detections. We evaluated the accuracy of detection of our method in experiments. Our method provided better detection than a method that does not search neighboring background models. Our method thus reduced the number of false detections.

Original language	English
Title of host publication	2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
Publisher	IEEE Computer Society
Pages	2626-2630
Number of pages	5
ISBN (Electronic)	9781479983391
DOIs	https://doi.org/10.1109/ICIP.2015.7351278
Publication status	Published - Dec 9 2015
Event	IEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada Duration: Sept 27 2015 → Sept 30 2015

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2015-December
ISSN (Print)	1522-4880

Other

Other	IEEE International Conference on Image Processing, ICIP 2015
Country/Territory	Canada
City	Quebec City
Period	9/27/15 → 9/30/15

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2015.7351278

Cite this

Minematsu, T., Uchiyama, H., Shimada, A., Nagahara, H., & Taniguchi, R. I. (2015). Adaptive search of background models for object detection in images taken by moving cameras. In 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings (pp. 2626-2630). Article 7351278 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2015-December). IEEE Computer Society. https://doi.org/10.1109/ICIP.2015.7351278

Adaptive search of background models for object detection in images taken by moving cameras. / Minematsu, Tsubasa; Uchiyama, Hideaki; Shimada, Atsushi et al.
2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. IEEE Computer Society, 2015. p. 2626-2630 7351278 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2015-December).

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

Minematsu, T, Uchiyama, H, Shimada, A, Nagahara, H & Taniguchi, RI 2015, Adaptive search of background models for object detection in images taken by moving cameras. in 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings., 7351278, Proceedings - International Conference on Image Processing, ICIP, vol. 2015-December, IEEE Computer Society, pp. 2626-2630, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 9/27/15. https://doi.org/10.1109/ICIP.2015.7351278

Minematsu T, Uchiyama H, Shimada A, Nagahara H, Taniguchi RI. Adaptive search of background models for object detection in images taken by moving cameras. In 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. IEEE Computer Society. 2015. p. 2626-2630. 7351278. (Proceedings - International Conference on Image Processing, ICIP). doi: 10.1109/ICIP.2015.7351278

@inproceedings{1bbd5b8b4d2c419cad1902dc6b5bc60a,

title = "Adaptive search of background models for object detection in images taken by moving cameras",

abstract = "We propose a strategy of background subtraction for an image sequence captured by a moving camera. To adapt for camera motion, it is necessary to estimate the relation between consecutive frames in background subtraction. However, simple background subtraction using the relation between consecutive frames results in many false detections. We use re-projection error to handle this problem. The re-projection error has a low value in a background region. According to re-projection error, our method searches neighboring background models and tunes a threshold value for detection in order to reduce false detections. We evaluated the accuracy of detection of our method in experiments. Our method provided better detection than a method that does not search neighboring background models. Our method thus reduced the number of false detections.",

author = "Tsubasa Minematsu and Hideaki Uchiyama and Atsushi Shimada and Hajime Nagahara and Taniguchi, {Rin Ichiro}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE International Conference on Image Processing, ICIP 2015 ; Conference date: 27-09-2015 Through 30-09-2015",

year = "2015",

month = dec,

day = "9",

doi = "10.1109/ICIP.2015.7351278",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "2626--2630",

booktitle = "2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings",

address = "United States",

}

TY - GEN

T1 - Adaptive search of background models for object detection in images taken by moving cameras

AU - Minematsu, Tsubasa

AU - Uchiyama, Hideaki

AU - Shimada, Atsushi

AU - Nagahara, Hajime

AU - Taniguchi, Rin Ichiro

PY - 2015/12/9

Y1 - 2015/12/9

N2 - We propose a strategy of background subtraction for an image sequence captured by a moving camera. To adapt for camera motion, it is necessary to estimate the relation between consecutive frames in background subtraction. However, simple background subtraction using the relation between consecutive frames results in many false detections. We use re-projection error to handle this problem. The re-projection error has a low value in a background region. According to re-projection error, our method searches neighboring background models and tunes a threshold value for detection in order to reduce false detections. We evaluated the accuracy of detection of our method in experiments. Our method provided better detection than a method that does not search neighboring background models. Our method thus reduced the number of false detections.

AB - We propose a strategy of background subtraction for an image sequence captured by a moving camera. To adapt for camera motion, it is necessary to estimate the relation between consecutive frames in background subtraction. However, simple background subtraction using the relation between consecutive frames results in many false detections. We use re-projection error to handle this problem. The re-projection error has a low value in a background region. According to re-projection error, our method searches neighboring background models and tunes a threshold value for detection in order to reduce false detections. We evaluated the accuracy of detection of our method in experiments. Our method provided better detection than a method that does not search neighboring background models. Our method thus reduced the number of false detections.

UR - http://www.scopus.com/inward/record.url?scp=84956627642&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956627642&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7351278

DO - 10.1109/ICIP.2015.7351278

M3 - Conference contribution

AN - SCOPUS:84956627642

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 2626

EP - 2630

BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings

PB - IEEE Computer Society

T2 - IEEE International Conference on Image Processing, ICIP 2015

Y2 - 27 September 2015 through 30 September 2015

ER -

Adaptive search of background models for object detection in images taken by moving cameras

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this