Background Independent Moving Object Segmentation for Video Surveillance

M. Ali Akber DEWAN; M. Julius HOSSAIN; Oksam CHAE

doi:10.1587/transcom.E92.B.585

Background Independent Moving Object Segmentation for Video Surveillance

M. Ali Akber DEWAN, M. Julius HOSSAIN, Oksam CHAE

Full Text Views

0

Cite this

Summary :

Background modeling is one of the most challenging and time consuming tasks in motion detection from video sequence. This paper presents a background independent moving object segmentation algorithm utilizing the spatio-temporal information of the last three frames. Existing three-frame based methods face challenges due to the insignificant gradient information in the overlapping region of difference images and edge localization errors. These methods extract scattered moving edges and experience poor detection rate especially when objects with slow movement exist in the scene. Moreover, they are not much suitable for moving object segmentation and tracking. The proposed method solves these problems by representing edges as segments and applying a novel segment based flexible edge matching algorithm which makes use of gradient accumulation through distance transformation. Due to working with three most recent frames, the proposed method can adapt to changes in the environment. Segment based representation facilitates local geometric transformation and thus it can make proper use of flexible matching to provide an effective solution for tracking. To segment the moving object region from the detected moving edges, we introduce a watershed based algorithm followed by an iterative background removal procedure. Watershed based segmentation algorithm helps to extract moving object with more accurate boundary which eventually achieves higher coding efficiency in content based applications and ensures a good visual quality even in the limited bit rate multimedia communication.

Publication: IEICE TRANSACTIONS on Communications Vol.E92-B No.2 pp.585-598

Publication Date: 2009/02/01

Publicized

Online ISSN: 1745-1345

DOI: 10.1587/transcom.E92.B.585

Type of Manuscript: PAPER

Category: Multimedia Systems for Communications

Cite this

Copy

M. Ali Akber DEWAN, M. Julius HOSSAIN, Oksam CHAE, "Background Independent Moving Object Segmentation for Video Surveillance" in IEICE TRANSACTIONS on Communications, vol. E92-B, no. 2, pp. 585-598, February 2009, doi: 10.1587/transcom.E92.B.585.
Abstract: Background modeling is one of the most challenging and time consuming tasks in motion detection from video sequence. This paper presents a background independent moving object segmentation algorithm utilizing the spatio-temporal information of the last three frames. Existing three-frame based methods face challenges due to the insignificant gradient information in the overlapping region of difference images and edge localization errors. These methods extract scattered moving edges and experience poor detection rate especially when objects with slow movement exist in the scene. Moreover, they are not much suitable for moving object segmentation and tracking. The proposed method solves these problems by representing edges as segments and applying a novel segment based flexible edge matching algorithm which makes use of gradient accumulation through distance transformation. Due to working with three most recent frames, the proposed method can adapt to changes in the environment. Segment based representation facilitates local geometric transformation and thus it can make proper use of flexible matching to provide an effective solution for tracking. To segment the moving object region from the detected moving edges, we introduce a watershed based algorithm followed by an iterative background removal procedure. Watershed based segmentation algorithm helps to extract moving object with more accurate boundary which eventually achieves higher coding efficiency in content based applications and ensures a good visual quality even in the limited bit rate multimedia communication.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.E92.B.585/_p

Copy

@ARTICLE{e92-b_2_585,
author={M. Ali Akber DEWAN, M. Julius HOSSAIN, Oksam CHAE, },
journal={IEICE TRANSACTIONS on Communications},
title={Background Independent Moving Object Segmentation for Video Surveillance},
year={2009},
volume={E92-B},
number={2},
pages={585-598},
abstract={Background modeling is one of the most challenging and time consuming tasks in motion detection from video sequence. This paper presents a background independent moving object segmentation algorithm utilizing the spatio-temporal information of the last three frames. Existing three-frame based methods face challenges due to the insignificant gradient information in the overlapping region of difference images and edge localization errors. These methods extract scattered moving edges and experience poor detection rate especially when objects with slow movement exist in the scene. Moreover, they are not much suitable for moving object segmentation and tracking. The proposed method solves these problems by representing edges as segments and applying a novel segment based flexible edge matching algorithm which makes use of gradient accumulation through distance transformation. Due to working with three most recent frames, the proposed method can adapt to changes in the environment. Segment based representation facilitates local geometric transformation and thus it can make proper use of flexible matching to provide an effective solution for tracking. To segment the moving object region from the detected moving edges, we introduce a watershed based algorithm followed by an iterative background removal procedure. Watershed based segmentation algorithm helps to extract moving object with more accurate boundary which eventually achieves higher coding efficiency in content based applications and ensures a good visual quality even in the limited bit rate multimedia communication.},
keywords={},
doi={10.1587/transcom.E92.B.585},
ISSN={1745-1345},
month={February},}

Copy

TY - JOUR
TI - Background Independent Moving Object Segmentation for Video Surveillance
T2 - IEICE TRANSACTIONS on Communications
SP - 585
EP - 598
AU - M. Ali Akber DEWAN
AU - M. Julius HOSSAIN
AU - Oksam CHAE
PY - 2009
DO - 10.1587/transcom.E92.B.585
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E92-B
IS - 2
JA - IEICE TRANSACTIONS on Communications
Y1 - February 2009
AB - Background modeling is one of the most challenging and time consuming tasks in motion detection from video sequence. This paper presents a background independent moving object segmentation algorithm utilizing the spatio-temporal information of the last three frames. Existing three-frame based methods face challenges due to the insignificant gradient information in the overlapping region of difference images and edge localization errors. These methods extract scattered moving edges and experience poor detection rate especially when objects with slow movement exist in the scene. Moreover, they are not much suitable for moving object segmentation and tracking. The proposed method solves these problems by representing edges as segments and applying a novel segment based flexible edge matching algorithm which makes use of gradient accumulation through distance transformation. Due to working with three most recent frames, the proposed method can adapt to changes in the environment. Segment based representation facilitates local geometric transformation and thus it can make proper use of flexible matching to provide an effective solution for tracking. To segment the moving object region from the detected moving edges, we introduce a watershed based algorithm followed by an iterative background removal procedure. Watershed based segmentation algorithm helps to extract moving object with more accurate boundary which eventually achieves higher coding efficiency in content based applications and ensures a good visual quality even in the limited bit rate multimedia communication.
ER -