Combination of Self-organization Map and Kernel Mutual Subspace method for video surveillance

Bailing Zhang, Junbum Park, Hanseok Ko

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

1 Citation (Scopus)

Abstract

This paper addresses the video surveillance issue of automatically identifying moving vehicles and people from continuous observation of image sequences. With a single far-field surveillance camera, moving objects are first segmented by simple background subtraction. To reduce the redundancy and select the representative prototypes from input video streams, the Self-organizing Feature Map (SOM) is applied for both training and testing sequences. The recognition scheme is designed based on the recently proposed Kernel Mutual Subspace (KMS) model. As an alternative to some probability-based models, KMS does not make assumptions about the data sampling processing and offers an efficient and robust classifier. Experiments demonstrated a highly accurate recognition result, showing the model's applicability in real-world surveillance system.

Original languageEnglish
Title of host publication2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings
Pages123-128
Number of pages6
DOIs
Publication statusPublished - 2007 Dec 1
Event2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 - London, United Kingdom
Duration: 2007 Sep 52007 Sep 7

Other

Other2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007
CountryUnited Kingdom
CityLondon
Period07/9/507/9/7

Fingerprint

Self organizing maps
Redundancy
Classifiers
Cameras
Sampling
Testing
Processing
Experiments

ASJC Scopus subject areas

  • Computer Science Applications
  • Signal Processing

Cite this

Zhang, B., Park, J., & Ko, H. (2007). Combination of Self-organization Map and Kernel Mutual Subspace method for video surveillance. In 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings (pp. 123-128). [4425297] https://doi.org/10.1109/AVSS.2007.4425297

Combination of Self-organization Map and Kernel Mutual Subspace method for video surveillance. / Zhang, Bailing; Park, Junbum; Ko, Hanseok.

2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings. 2007. p. 123-128 4425297.

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

Zhang, B, Park, J & Ko, H 2007, Combination of Self-organization Map and Kernel Mutual Subspace method for video surveillance. in 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings., 4425297, pp. 123-128, 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007, London, United Kingdom, 07/9/5. https://doi.org/10.1109/AVSS.2007.4425297
Zhang B, Park J, Ko H. Combination of Self-organization Map and Kernel Mutual Subspace method for video surveillance. In 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings. 2007. p. 123-128. 4425297 https://doi.org/10.1109/AVSS.2007.4425297
Zhang, Bailing ; Park, Junbum ; Ko, Hanseok. / Combination of Self-organization Map and Kernel Mutual Subspace method for video surveillance. 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings. 2007. pp. 123-128
@inproceedings{34bde08f514046da9a0c994f5e3d6168,
title = "Combination of Self-organization Map and Kernel Mutual Subspace method for video surveillance",
abstract = "This paper addresses the video surveillance issue of automatically identifying moving vehicles and people from continuous observation of image sequences. With a single far-field surveillance camera, moving objects are first segmented by simple background subtraction. To reduce the redundancy and select the representative prototypes from input video streams, the Self-organizing Feature Map (SOM) is applied for both training and testing sequences. The recognition scheme is designed based on the recently proposed Kernel Mutual Subspace (KMS) model. As an alternative to some probability-based models, KMS does not make assumptions about the data sampling processing and offers an efficient and robust classifier. Experiments demonstrated a highly accurate recognition result, showing the model's applicability in real-world surveillance system.",
author = "Bailing Zhang and Junbum Park and Hanseok Ko",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/AVSS.2007.4425297",
language = "English",
isbn = "9781424416967",
pages = "123--128",
booktitle = "2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings",

}

TY - GEN

T1 - Combination of Self-organization Map and Kernel Mutual Subspace method for video surveillance

AU - Zhang, Bailing

AU - Park, Junbum

AU - Ko, Hanseok

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This paper addresses the video surveillance issue of automatically identifying moving vehicles and people from continuous observation of image sequences. With a single far-field surveillance camera, moving objects are first segmented by simple background subtraction. To reduce the redundancy and select the representative prototypes from input video streams, the Self-organizing Feature Map (SOM) is applied for both training and testing sequences. The recognition scheme is designed based on the recently proposed Kernel Mutual Subspace (KMS) model. As an alternative to some probability-based models, KMS does not make assumptions about the data sampling processing and offers an efficient and robust classifier. Experiments demonstrated a highly accurate recognition result, showing the model's applicability in real-world surveillance system.

AB - This paper addresses the video surveillance issue of automatically identifying moving vehicles and people from continuous observation of image sequences. With a single far-field surveillance camera, moving objects are first segmented by simple background subtraction. To reduce the redundancy and select the representative prototypes from input video streams, the Self-organizing Feature Map (SOM) is applied for both training and testing sequences. The recognition scheme is designed based on the recently proposed Kernel Mutual Subspace (KMS) model. As an alternative to some probability-based models, KMS does not make assumptions about the data sampling processing and offers an efficient and robust classifier. Experiments demonstrated a highly accurate recognition result, showing the model's applicability in real-world surveillance system.

UR - http://www.scopus.com/inward/record.url?scp=44849088775&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44849088775&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2007.4425297

DO - 10.1109/AVSS.2007.4425297

M3 - Conference contribution

SN - 9781424416967

SP - 123

EP - 128

BT - 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2007 Proceedings

ER -