Real-time automatic moving object extraction and tracing based on improved active contour model

Geng Yunchuan, Liu Yangxing, Goto Satoshi, Takeshi Ikenaga

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A real-time moving object extraction and tracing algorithm is proposed for videophone application. Semantic objects, mainly moving objects in this specified case, are extracted by block based change detection from first several frames. Improved active contour model is then utilized for object tracing. Since there is little difference between continuous two frames, only limited pixels need to be searched instead of whole frame scan so that computing complexity is greatly decreased. Therefore, it is able to be used for real-time applications such as that in videophone. However, previous active contour model is sensitive to noise. Error originating from noise traps accumulates and deteriorates the tracing results. So gradient projection (GP) and jump back (JB) mechanisms are introduced to suppress noise trap effect and error accumulation in this paper. Experiment results demonstrate that proposed algorithm is an efficient noise tolerable real-time approach.

Original languageEnglish
Title of host publicationProceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005
Pages149-152
Number of pages4
Volume2005
Publication statusPublished - 2005
Event2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005 - Hong Kong
Duration: 2005 Dec 132005 Dec 16

Other

Other2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005
CityHong Kong
Period05/12/1305/12/16

Fingerprint

Pixels
Semantics
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Yunchuan, G., Yangxing, L., Satoshi, G., & Ikenaga, T. (2005). Real-time automatic moving object extraction and tracing based on improved active contour model. In Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005 (Vol. 2005, pp. 149-152). [1595368]

Real-time automatic moving object extraction and tracing based on improved active contour model. / Yunchuan, Geng; Yangxing, Liu; Satoshi, Goto; Ikenaga, Takeshi.

Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005. Vol. 2005 2005. p. 149-152 1595368.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yunchuan, G, Yangxing, L, Satoshi, G & Ikenaga, T 2005, Real-time automatic moving object extraction and tracing based on improved active contour model. in Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005. vol. 2005, 1595368, pp. 149-152, 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005, Hong Kong, 05/12/13.
Yunchuan G, Yangxing L, Satoshi G, Ikenaga T. Real-time automatic moving object extraction and tracing based on improved active contour model. In Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005. Vol. 2005. 2005. p. 149-152. 1595368
Yunchuan, Geng ; Yangxing, Liu ; Satoshi, Goto ; Ikenaga, Takeshi. / Real-time automatic moving object extraction and tracing based on improved active contour model. Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005. Vol. 2005 2005. pp. 149-152
@inproceedings{901fb3aae4f146838c375994c5dd4539,
title = "Real-time automatic moving object extraction and tracing based on improved active contour model",
abstract = "A real-time moving object extraction and tracing algorithm is proposed for videophone application. Semantic objects, mainly moving objects in this specified case, are extracted by block based change detection from first several frames. Improved active contour model is then utilized for object tracing. Since there is little difference between continuous two frames, only limited pixels need to be searched instead of whole frame scan so that computing complexity is greatly decreased. Therefore, it is able to be used for real-time applications such as that in videophone. However, previous active contour model is sensitive to noise. Error originating from noise traps accumulates and deteriorates the tracing results. So gradient projection (GP) and jump back (JB) mechanisms are introduced to suppress noise trap effect and error accumulation in this paper. Experiment results demonstrate that proposed algorithm is an efficient noise tolerable real-time approach.",
author = "Geng Yunchuan and Liu Yangxing and Goto Satoshi and Takeshi Ikenaga",
year = "2005",
language = "English",
isbn = "0780392663",
volume = "2005",
pages = "149--152",
booktitle = "Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005",

}

TY - GEN

T1 - Real-time automatic moving object extraction and tracing based on improved active contour model

AU - Yunchuan, Geng

AU - Yangxing, Liu

AU - Satoshi, Goto

AU - Ikenaga, Takeshi

PY - 2005

Y1 - 2005

N2 - A real-time moving object extraction and tracing algorithm is proposed for videophone application. Semantic objects, mainly moving objects in this specified case, are extracted by block based change detection from first several frames. Improved active contour model is then utilized for object tracing. Since there is little difference between continuous two frames, only limited pixels need to be searched instead of whole frame scan so that computing complexity is greatly decreased. Therefore, it is able to be used for real-time applications such as that in videophone. However, previous active contour model is sensitive to noise. Error originating from noise traps accumulates and deteriorates the tracing results. So gradient projection (GP) and jump back (JB) mechanisms are introduced to suppress noise trap effect and error accumulation in this paper. Experiment results demonstrate that proposed algorithm is an efficient noise tolerable real-time approach.

AB - A real-time moving object extraction and tracing algorithm is proposed for videophone application. Semantic objects, mainly moving objects in this specified case, are extracted by block based change detection from first several frames. Improved active contour model is then utilized for object tracing. Since there is little difference between continuous two frames, only limited pixels need to be searched instead of whole frame scan so that computing complexity is greatly decreased. Therefore, it is able to be used for real-time applications such as that in videophone. However, previous active contour model is sensitive to noise. Error originating from noise traps accumulates and deteriorates the tracing results. So gradient projection (GP) and jump back (JB) mechanisms are introduced to suppress noise trap effect and error accumulation in this paper. Experiment results demonstrate that proposed algorithm is an efficient noise tolerable real-time approach.

UR - http://www.scopus.com/inward/record.url?scp=33847180563&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847180563&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780392663

SN - 9780780392663

VL - 2005

SP - 149

EP - 152

BT - Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2005

ER -