Object modelling in videos via multidimensional features of colours and textures

Zhuhan Jiang

doi:10.1109/DICTA.2009.32

Object modelling in videos via multidimensional features of colours and textures

Zhuhan Jiang

School of Computer, Data & Mathematical Sciences

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

Abstract

We propose to model a tracked object in a video sequence by locating a list of object features that are ranked according to their ability to differentiate against the image background. The Bayesian inference is utilised to derive the probabilistic location of the object in the current frame, with the prior being approximated from the previous frame and the posterior achieved via the current pixel distribution of the object. The experiment of the proposed method on the video sequences has also been conducted and has shown its effectiveness in capturing the target in a moving background and with non-rigid object motion.

Original language	English
Title of host publication	Proceedings of the 2009 Digital Image Computing: Techniques and Applications (DICTA 2009): 1-3 December 2009, Melbourne, Australia
Publisher	IEEE
Pages	154-161
Number of pages	8
ISBN (Print)	9780769538662
DOIs	https://doi.org/10.1109/DICTA.2009.32
Publication status	Published - 2009
Event	DICTA (Conference) - Duration: 25 Nov 2014 → …

Conference

Conference	DICTA (Conference)
Period	25/11/14 → …

Access to Document

10.1109/DICTA.2009.32

Cite this

@inproceedings{98f0dd39e6814641bafd68a2e427c3cd,

title = "Object modelling in videos via multidimensional features of colours and textures",

abstract = "We propose to model a tracked object in a video sequence by locating a list of object features that are ranked according to their ability to differentiate against the image background. The Bayesian inference is utilised to derive the probabilistic location of the object in the current frame, with the prior being approximated from the previous frame and the posterior achieved via the current pixel distribution of the object. The experiment of the proposed method on the video sequences has also been conducted and has shown its effectiveness in capturing the target in a moving background and with non-rigid object motion.",

author = "Zhuhan Jiang",

year = "2009",

doi = "10.1109/DICTA.2009.32",

language = "English",

isbn = "9780769538662",

pages = "154--161",

booktitle = "Proceedings of the 2009 Digital Image Computing: Techniques and Applications (DICTA 2009): 1-3 December 2009, Melbourne, Australia",

publisher = "IEEE",

note = "DICTA (Conference) ; Conference date: 25-11-2014",

}

TY - GEN

T1 - Object modelling in videos via multidimensional features of colours and textures

AU - Jiang, Zhuhan

PY - 2009

Y1 - 2009

N2 - We propose to model a tracked object in a video sequence by locating a list of object features that are ranked according to their ability to differentiate against the image background. The Bayesian inference is utilised to derive the probabilistic location of the object in the current frame, with the prior being approximated from the previous frame and the posterior achieved via the current pixel distribution of the object. The experiment of the proposed method on the video sequences has also been conducted and has shown its effectiveness in capturing the target in a moving background and with non-rigid object motion.

AB - We propose to model a tracked object in a video sequence by locating a list of object features that are ranked according to their ability to differentiate against the image background. The Bayesian inference is utilised to derive the probabilistic location of the object in the current frame, with the prior being approximated from the previous frame and the posterior achieved via the current pixel distribution of the object. The experiment of the proposed method on the video sequences has also been conducted and has shown its effectiveness in capturing the target in a moving background and with non-rigid object motion.

UR - http://handle.uws.edu.au:8081/1959.7/562996

U2 - 10.1109/DICTA.2009.32

DO - 10.1109/DICTA.2009.32

M3 - Conference Paper

SN - 9780769538662

SP - 154

EP - 161

BT - Proceedings of the 2009 Digital Image Computing: Techniques and Applications (DICTA 2009): 1-3 December 2009, Melbourne, Australia

PB - IEEE

T2 - DICTA (Conference)

Y2 - 25 November 2014

ER -

Object modelling in videos via multidimensional features of colours and textures

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this