A multi-modal moving object detection method based on GrowCut segmentation

Xiuwei Zhang; Yanning Zhang; Stephen John Maybank; Jun Liang

doi:10.1109/CIMSIVP.2014.7013295

A multi-modal moving object detection method based on GrowCut segmentation

Xiuwei Zhang, Yanning Zhang, Stephen John Maybank, Jun Liang

School of Computer Science

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

3 Scopus citations

Abstract

Commonly-used motion detection methods, such as background subtraction, optical flow and frame subtraction are all based on the differences between consecutive image frames. There are many difficulties, including similarities between objects and background, shadows, low illumination, thermal halo. Visible light images and thermal images are complementary. Many difficulties in motion detection do not occur simultaneously in visible and thermal images. The proposed multimodal detection method combines the advantages of multi-modal image and GrowCut segmentation, overcomes the difficulties mentioned above and works well in complicated outdoor surveillance environments. Experiments showed our method yields better results than commonly-used fusion methods.

Original language	English
Title of host publication	IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014
Subtitle of host publication	2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781479945047
DOIs	https://doi.org/10.1109/CIMSIVP.2014.7013295
State	Published - 16 Jan 2015
Event	2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, CIMSIVP 2014 - Orlando, United States Duration: 9 Dec 2014 → 12 Dec 2014

Publication series

Name	IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings

Conference

Conference	2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, CIMSIVP 2014
Country/Territory	United States
City	Orlando
Period	9/12/14 → 12/12/14

Keywords

GrowCut segmentation
moving object detection
thermal images
visible light images

Access to Document

10.1109/CIMSIVP.2014.7013295

Cite this

Zhang, X., Zhang, Y., Maybank, S. J., & Liang, J. (2015). A multi-modal moving object detection method based on GrowCut segmentation. In IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings Article 7013295 (IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIMSIVP.2014.7013295

Zhang, Xiuwei ; Zhang, Yanning ; Maybank, Stephen John et al. / A multi-modal moving object detection method based on GrowCut segmentation. IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. (IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings).

@inproceedings{30bbb509a0ec4bfc826f5805f8cd20cf,

title = "A multi-modal moving object detection method based on GrowCut segmentation",

abstract = "Commonly-used motion detection methods, such as background subtraction, optical flow and frame subtraction are all based on the differences between consecutive image frames. There are many difficulties, including similarities between objects and background, shadows, low illumination, thermal halo. Visible light images and thermal images are complementary. Many difficulties in motion detection do not occur simultaneously in visible and thermal images. The proposed multimodal detection method combines the advantages of multi-modal image and GrowCut segmentation, overcomes the difficulties mentioned above and works well in complicated outdoor surveillance environments. Experiments showed our method yields better results than commonly-used fusion methods.",

keywords = "GrowCut segmentation, moving object detection, thermal images, visible light images",

author = "Xiuwei Zhang and Yanning Zhang and Maybank, {Stephen John} and Jun Liang",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, CIMSIVP 2014 ; Conference date: 09-12-2014 Through 12-12-2014",

year = "2015",

month = jan,

day = "16",

doi = "10.1109/CIMSIVP.2014.7013295",

language = "英语",

series = "IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings",

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

booktitle = "IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014",

}

Zhang, X, Zhang, Y, Maybank, SJ & Liang, J 2015, A multi-modal moving object detection method based on GrowCut segmentation. in IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings., 7013295, IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings, Institute of Electrical and Electronics Engineers Inc., 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, CIMSIVP 2014, Orlando, United States, 9/12/14. https://doi.org/10.1109/CIMSIVP.2014.7013295

A multi-modal moving object detection method based on GrowCut segmentation. / Zhang, Xiuwei; Zhang, Yanning; Maybank, Stephen John et al.
IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. 7013295 (IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings).

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

TY - GEN

T1 - A multi-modal moving object detection method based on GrowCut segmentation

AU - Zhang, Xiuwei

AU - Zhang, Yanning

AU - Maybank, Stephen John

AU - Liang, Jun

PY - 2015/1/16

Y1 - 2015/1/16

N2 - Commonly-used motion detection methods, such as background subtraction, optical flow and frame subtraction are all based on the differences between consecutive image frames. There are many difficulties, including similarities between objects and background, shadows, low illumination, thermal halo. Visible light images and thermal images are complementary. Many difficulties in motion detection do not occur simultaneously in visible and thermal images. The proposed multimodal detection method combines the advantages of multi-modal image and GrowCut segmentation, overcomes the difficulties mentioned above and works well in complicated outdoor surveillance environments. Experiments showed our method yields better results than commonly-used fusion methods.

AB - Commonly-used motion detection methods, such as background subtraction, optical flow and frame subtraction are all based on the differences between consecutive image frames. There are many difficulties, including similarities between objects and background, shadows, low illumination, thermal halo. Visible light images and thermal images are complementary. Many difficulties in motion detection do not occur simultaneously in visible and thermal images. The proposed multimodal detection method combines the advantages of multi-modal image and GrowCut segmentation, overcomes the difficulties mentioned above and works well in complicated outdoor surveillance environments. Experiments showed our method yields better results than commonly-used fusion methods.

KW - GrowCut segmentation

KW - moving object detection

KW - thermal images

KW - visible light images

UR - http://www.scopus.com/inward/record.url?scp=84924236129&partnerID=8YFLogxK

U2 - 10.1109/CIMSIVP.2014.7013295

DO - 10.1109/CIMSIVP.2014.7013295

M3 - 会议稿件

AN - SCOPUS:84924236129

T3 - IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings

BT - IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, CIMSIVP 2014

Y2 - 9 December 2014 through 12 December 2014

ER -

Zhang X, Zhang Y, Maybank SJ, Liang J. A multi-modal moving object detection method based on GrowCut segmentation. In IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. 7013295. (IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIMSIVP 2014: 2014 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, Proceedings). doi: 10.1109/CIMSIVP.2014.7013295

A multi-modal moving object detection method based on GrowCut segmentation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this