A multiview approach to robust detection in the presence of cast shadows

Ming Xu; Jie Ren; Dongyong Chen; Jeremy S. Smith; Zhechi Liu

doi:10.1109/ICIG.2011.180

A multiview approach to robust detection in the presence of cast shadows

Ming Xu^*, Jie Ren, Dongyong Chen, Jeremy S. Smith, Zhechi Liu

^*Corresponding author for this work

Department of Electrical and Electronic Engineering

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

Abstract

This paper presents an object detection algorithm using multiple cameras, which is robust in the presence of cast shadows. The information fusion is based on homography mapping of the foreground regions to a top view image. The homography is based on multiple planar planes parallel to the ground plane. Two novel approaches to estimating such homography have been proposed. The results on an open video dataset are demonstrated.

Original language	English
Title of host publication	Proceedings - 6th International Conference on Image and Graphics, ICIG 2011
Pages	494-499
Number of pages	6
DOIs	https://doi.org/10.1109/ICIG.2011.180
Publication status	Published - 2011
Event	6th International Conference on Image and Graphics, ICIG 2011 - Hefei, Anhui, China Duration: 12 Aug 2011 → 15 Aug 2011

Publication series

Name	Proceedings - 6th International Conference on Image and Graphics, ICIG 2011

Conference

Conference	6th International Conference on Image and Graphics, ICIG 2011
Country/Territory	China
City	Hefei, Anhui
Period	12/08/11 → 15/08/11

Keywords

Detection
Homography
Motion analysis
Video surveillance

Access to Document

10.1109/ICIG.2011.180

Cite this

@inproceedings{fe72c61b6c8148d0b6ecbb7f19711f6d,

title = "A multiview approach to robust detection in the presence of cast shadows",

abstract = "This paper presents an object detection algorithm using multiple cameras, which is robust in the presence of cast shadows. The information fusion is based on homography mapping of the foreground regions to a top view image. The homography is based on multiple planar planes parallel to the ground plane. Two novel approaches to estimating such homography have been proposed. The results on an open video dataset are demonstrated.",

keywords = "Detection, Homography, Motion analysis, Video surveillance",

author = "Ming Xu and Jie Ren and Dongyong Chen and Smith, {Jeremy S.} and Zhechi Liu",

year = "2011",

doi = "10.1109/ICIG.2011.180",

language = "English",

isbn = "9780769545417",

series = "Proceedings - 6th International Conference on Image and Graphics, ICIG 2011",

pages = "494--499",

booktitle = "Proceedings - 6th International Conference on Image and Graphics, ICIG 2011",

note = "6th International Conference on Image and Graphics, ICIG 2011 ; Conference date: 12-08-2011 Through 15-08-2011",

}

Xu, M, Ren, J, Chen, D, Smith, JS & Liu, Z 2011, A multiview approach to robust detection in the presence of cast shadows. in Proceedings - 6th International Conference on Image and Graphics, ICIG 2011., 6005850, Proceedings - 6th International Conference on Image and Graphics, ICIG 2011, pp. 494-499, 6th International Conference on Image and Graphics, ICIG 2011, Hefei, Anhui, China, 12/08/11. https://doi.org/10.1109/ICIG.2011.180

A multiview approach to robust detection in the presence of cast shadows. / Xu, Ming; Ren, Jie; Chen, Dongyong et al.
Proceedings - 6th International Conference on Image and Graphics, ICIG 2011. 2011. p. 494-499 6005850 (Proceedings - 6th International Conference on Image and Graphics, ICIG 2011).

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

TY - GEN

T1 - A multiview approach to robust detection in the presence of cast shadows

AU - Xu, Ming

AU - Ren, Jie

AU - Chen, Dongyong

AU - Smith, Jeremy S.

AU - Liu, Zhechi

PY - 2011

Y1 - 2011

N2 - This paper presents an object detection algorithm using multiple cameras, which is robust in the presence of cast shadows. The information fusion is based on homography mapping of the foreground regions to a top view image. The homography is based on multiple planar planes parallel to the ground plane. Two novel approaches to estimating such homography have been proposed. The results on an open video dataset are demonstrated.

AB - This paper presents an object detection algorithm using multiple cameras, which is robust in the presence of cast shadows. The information fusion is based on homography mapping of the foreground regions to a top view image. The homography is based on multiple planar planes parallel to the ground plane. Two novel approaches to estimating such homography have been proposed. The results on an open video dataset are demonstrated.

KW - Detection

KW - Homography

KW - Motion analysis

KW - Video surveillance

UR - http://www.scopus.com/inward/record.url?scp=80053027424&partnerID=8YFLogxK

U2 - 10.1109/ICIG.2011.180

DO - 10.1109/ICIG.2011.180

M3 - Conference Proceeding

AN - SCOPUS:80053027424

SN - 9780769545417

T3 - Proceedings - 6th International Conference on Image and Graphics, ICIG 2011

SP - 494

EP - 499

BT - Proceedings - 6th International Conference on Image and Graphics, ICIG 2011

T2 - 6th International Conference on Image and Graphics, ICIG 2011

Y2 - 12 August 2011 through 15 August 2011

ER -

A multiview approach to robust detection in the presence of cast shadows

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this