Feature-based patch matching for moving object detection

Mosin Russell; Ju Jia Zou; Gu Fang; Weidong Cai

doi:10.1109/VCIP47243.2019.8966047

Feature-based patch matching for moving object detection

Mosin Russell, Ju Jia Zou, Gu Fang, Weidong Cai

Western Sydney University

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

Abstract

![CDATA[In this paper, a new background subtraction framework is proposed to deal with possible scenarios occurring in natural scenes. In this method, a combination of two feature descriptors, namely color information in HSV color format and global texture descriptor T, are introduced to effectively identify background points under varying conditions. Using these features, an adaptive background model is constructed to automatically adapt to scene changes. The proposed framework is evaluated on common change detection datasets, showing improved performance compared to three well-known methods.]]

Original language	English
Title of host publication	Proceedings of the 2019 IEEE International Conference on Visual Communications and Image Processing (VCIP), December 1-4, 2019, Sydney, Australia
Publisher	IEEE
Number of pages	4
ISBN (Print)	9781728137230
DOIs	https://doi.org/10.1109/VCIP47243.2019.8966047
Publication status	Published - 2019
Event	IEEE Visual Communications and Image Processing (Conference) - Duration: 1 Dec 2019 → …

Publication series

Name
ISSN (Print)	2642-9357

Conference

Conference	IEEE Visual Communications and Image Processing (Conference)
Period	1/12/19 → …

Keywords

computer vision
image processing
pattern recognition systems

Access to Document

10.1109/VCIP47243.2019.8966047

Cite this

@inproceedings{00518d37248d4b41adbbd389c74f83f6,

title = "Feature-based patch matching for moving object detection",

abstract = "![CDATA[In this paper, a new background subtraction framework is proposed to deal with possible scenarios occurring in natural scenes. In this method, a combination of two feature descriptors, namely color information in HSV color format and global texture descriptor T, are introduced to effectively identify background points under varying conditions. Using these features, an adaptive background model is constructed to automatically adapt to scene changes. The proposed framework is evaluated on common change detection datasets, showing improved performance compared to three well-known methods.]]",

keywords = "computer vision, image processing, pattern recognition systems",

author = "Mosin Russell and Zou, {Ju Jia} and Gu Fang and Weidong Cai",

year = "2019",

doi = "10.1109/VCIP47243.2019.8966047",

language = "English",

isbn = "9781728137230",

publisher = "IEEE",

booktitle = "Proceedings of the 2019 IEEE International Conference on Visual Communications and Image Processing (VCIP), December 1-4, 2019, Sydney, Australia",

note = "IEEE Visual Communications and Image Processing (Conference) ; Conference date: 01-12-2019",

}

Russell, M, Zou, JJ , Fang, G & Cai, W 2019, Feature-based patch matching for moving object detection. in Proceedings of the 2019 IEEE International Conference on Visual Communications and Image Processing (VCIP), December 1-4, 2019, Sydney, Australia. IEEE, IEEE Visual Communications and Image Processing (Conference), 1/12/19. https://doi.org/10.1109/VCIP47243.2019.8966047

TY - GEN

T1 - Feature-based patch matching for moving object detection

AU - Russell, Mosin

AU - Zou, Ju Jia

AU - Fang, Gu

AU - Cai, Weidong

PY - 2019

Y1 - 2019

N2 - ![CDATA[In this paper, a new background subtraction framework is proposed to deal with possible scenarios occurring in natural scenes. In this method, a combination of two feature descriptors, namely color information in HSV color format and global texture descriptor T, are introduced to effectively identify background points under varying conditions. Using these features, an adaptive background model is constructed to automatically adapt to scene changes. The proposed framework is evaluated on common change detection datasets, showing improved performance compared to three well-known methods.]]

AB - ![CDATA[In this paper, a new background subtraction framework is proposed to deal with possible scenarios occurring in natural scenes. In this method, a combination of two feature descriptors, namely color information in HSV color format and global texture descriptor T, are introduced to effectively identify background points under varying conditions. Using these features, an adaptive background model is constructed to automatically adapt to scene changes. The proposed framework is evaluated on common change detection datasets, showing improved performance compared to three well-known methods.]]

KW - computer vision

KW - image processing

KW - pattern recognition systems

UR - https://hdl.handle.net/1959.7/uws:54139

U2 - 10.1109/VCIP47243.2019.8966047

DO - 10.1109/VCIP47243.2019.8966047

M3 - Conference Paper

SN - 9781728137230

BT - Proceedings of the 2019 IEEE International Conference on Visual Communications and Image Processing (VCIP), December 1-4, 2019, Sydney, Australia

PB - IEEE

T2 - IEEE Visual Communications and Image Processing (Conference)

Y2 - 1 December 2019

ER -

Feature-based patch matching for moving object detection

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this