Beyond static detectors:  a Bayesian approach to fusing long-term motion with appearance for robust people detection in highly cluttered scenes

Jianguo Zhang; Shaogang Gong

Beyond static detectors: a Bayesian approach to fusing long-term motion with appearance for robust people detection in highly cluttered scenes

Jianguo Zhang, Shaogang Gong

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

Abstract

In this work we present a framework for robust people de-tection in highly cluttered scenes with low resolution im-age sequences. Our model utilises both human appearance and their long-term motion information through a fusion formulated in a Bayesian framework. In particular, peo-ple appearance is modeled by histograms of oriented gra-dients. Motion information is computed via an improved background modeling by spatial motion constrains. Exper-iments demonstrate that our method reduces significantly the false positive rate compared to that of a state of the art human detector under very challenging conditions.

Original language	English
Title of host publication	Proceedings of the Sixth International IEEE Workshop on Visual Surveillance
Editors	Pascal Fua, Stephen Maybank, Graeme A. Jones
Place of Publication	Kingston-Upon-Thames
Publisher	IEEE
Pages	121-128
Number of pages	8
ISBN (Print)	9780955300301, 0955300304
Publication status	Published - 2006
Event	6th IEEE International Workshop on Visual Surveillance - Graz, Austria Duration: 13 May 2006 → 13 May 2006

Conference

Conference	6th IEEE International Workshop on Visual Surveillance
Country/Territory	Austria
City	Graz
Period	13/05/06 → 13/05/06

Access to Document

http://dircweb.king.ac.uk/Vs2006/home.htm

Cite this

@inproceedings{03b15570ca1646bd91b4da4ec810bbb2,

title = "Beyond static detectors: a Bayesian approach to fusing long-term motion with appearance for robust people detection in highly cluttered scenes",

abstract = "In this work we present a framework for robust people de-tection in highly cluttered scenes with low resolution im-age sequences. Our model utilises both human appearance and their long-term motion information through a fusion formulated in a Bayesian framework. In particular, peo-ple appearance is modeled by histograms of oriented gra-dients. Motion information is computed via an improved background modeling by spatial motion constrains. Exper-iments demonstrate that our method reduces significantly the false positive rate compared to that of a state of the art human detector under very challenging conditions.",

author = "Jianguo Zhang and Shaogang Gong",

note = "Workshop held in conjunction with 9th European Conference on Computer Vision (ECCV 2006), Graz, Austria, 7-13 May, 2006; 6th IEEE International Workshop on Visual Surveillance ; Conference date: 13-05-2006 Through 13-05-2006",

year = "2006",

language = "English",

isbn = "9780955300301",

pages = "121--128",

editor = "Pascal Fua and Maybank, \{Stephen \} and Jones, \{Graeme A.\}",

booktitle = "Proceedings of the Sixth International IEEE Workshop on Visual Surveillance",

publisher = "IEEE",

}

Zhang, J & Gong, S 2006, Beyond static detectors: a Bayesian approach to fusing long-term motion with appearance for robust people detection in highly cluttered scenes. in P Fua, S Maybank & GA Jones (eds), Proceedings of the Sixth International IEEE Workshop on Visual Surveillance. IEEE, Kingston-Upon-Thames, pp. 121-128, 6th IEEE International Workshop on Visual Surveillance, Graz, Austria, 13/05/06. <http://dircweb.king.ac.uk/Vs2006/home.htm>

Beyond static detectors: a Bayesian approach to fusing long-term motion with appearance for robust people detection in highly cluttered scenes. / Zhang, Jianguo; Gong, Shaogang.
Proceedings of the Sixth International IEEE Workshop on Visual Surveillance. ed. / Pascal Fua; Stephen Maybank; Graeme A. Jones. Kingston-Upon-Thames: IEEE, 2006. p. 121-128.

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

TY - GEN

T1 - Beyond static detectors

T2 - 6th IEEE International Workshop on Visual Surveillance

AU - Zhang, Jianguo

AU - Gong, Shaogang

N1 - Workshop held in conjunction with 9th European Conference on Computer Vision (ECCV 2006), Graz, Austria, 7-13 May, 2006

PY - 2006

Y1 - 2006

N2 - In this work we present a framework for robust people de-tection in highly cluttered scenes with low resolution im-age sequences. Our model utilises both human appearance and their long-term motion information through a fusion formulated in a Bayesian framework. In particular, peo-ple appearance is modeled by histograms of oriented gra-dients. Motion information is computed via an improved background modeling by spatial motion constrains. Exper-iments demonstrate that our method reduces significantly the false positive rate compared to that of a state of the art human detector under very challenging conditions.

AB - In this work we present a framework for robust people de-tection in highly cluttered scenes with low resolution im-age sequences. Our model utilises both human appearance and their long-term motion information through a fusion formulated in a Bayesian framework. In particular, peo-ple appearance is modeled by histograms of oriented gra-dients. Motion information is computed via an improved background modeling by spatial motion constrains. Exper-iments demonstrate that our method reduces significantly the false positive rate compared to that of a state of the art human detector under very challenging conditions.

M3 - Conference contribution

SN - 9780955300301

SN - 0955300304

SP - 121

EP - 128

BT - Proceedings of the Sixth International IEEE Workshop on Visual Surveillance

A2 - Fua, Pascal

A2 - Maybank, Stephen

A2 - Jones, Graeme A.

PB - IEEE

CY - Kingston-Upon-Thames

Y2 - 13 May 2006 through 13 May 2006

ER -

Beyond static detectors: a Bayesian approach to fusing long-term motion with appearance for robust people detection in highly cluttered scenes

Abstract

Conference

Access to Document

Fingerprint

Cite this