Temporal information cooperated Gaussian Mixture Models for real-time surveillance with ghost detection

Tianci Huang, Chengjiao Guo, Jingbang Qiu, Takeshi Ikenaga

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

1 Citation (Scopus)

Abstract

This paper describes a new real-time approach for detecting motions in the video streams taken from stationary cameras. This method combines a temporal recording scheme with the adaptive background model subtraction scheme. To save the computation brought from conventional Gaussian Mixture Models (GMM) and achieve real-time processing, an adaptively adjusted mechanism is proposed. On the other hand, illumination changes, shadow influence, and ghost in scene, these three important problems which result in low segmentation quality are settled down by utilizing proposed features and temporal information from video streams. The experimental results validate the improvement of detection accuracy. Meanwhile, the execution time for each component per frame is calculated and compared with that of conventional Gaussian Mixture Models.

Original languageEnglish
Title of host publicationIIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing
Pages1338-1341
Number of pages4
DOIs
Publication statusPublished - 2009
EventIIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing - Kyoto
Duration: 2009 Sep 122009 Sep 14

Other

OtherIIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing
CityKyoto
Period09/9/1209/9/14

Fingerprint

Lighting
Cameras
Processing

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Huang, T., Guo, C., Qiu, J., & Ikenaga, T. (2009). Temporal information cooperated Gaussian Mixture Models for real-time surveillance with ghost detection. In IIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing (pp. 1338-1341). [5337225] https://doi.org/10.1109/IIH-MSP.2009.49

Temporal information cooperated Gaussian Mixture Models for real-time surveillance with ghost detection. / Huang, Tianci; Guo, Chengjiao; Qiu, Jingbang; Ikenaga, Takeshi.

IIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing. 2009. p. 1338-1341 5337225.

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

Huang, T, Guo, C, Qiu, J & Ikenaga, T 2009, Temporal information cooperated Gaussian Mixture Models for real-time surveillance with ghost detection. in IIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing., 5337225, pp. 1338-1341, IIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Kyoto, 09/9/12. https://doi.org/10.1109/IIH-MSP.2009.49
Huang T, Guo C, Qiu J, Ikenaga T. Temporal information cooperated Gaussian Mixture Models for real-time surveillance with ghost detection. In IIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing. 2009. p. 1338-1341. 5337225 https://doi.org/10.1109/IIH-MSP.2009.49
Huang, Tianci ; Guo, Chengjiao ; Qiu, Jingbang ; Ikenaga, Takeshi. / Temporal information cooperated Gaussian Mixture Models for real-time surveillance with ghost detection. IIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing. 2009. pp. 1338-1341
@inproceedings{2f5eed4d697c4b7a8c802ec5092f51a4,
title = "Temporal information cooperated Gaussian Mixture Models for real-time surveillance with ghost detection",
abstract = "This paper describes a new real-time approach for detecting motions in the video streams taken from stationary cameras. This method combines a temporal recording scheme with the adaptive background model subtraction scheme. To save the computation brought from conventional Gaussian Mixture Models (GMM) and achieve real-time processing, an adaptively adjusted mechanism is proposed. On the other hand, illumination changes, shadow influence, and ghost in scene, these three important problems which result in low segmentation quality are settled down by utilizing proposed features and temporal information from video streams. The experimental results validate the improvement of detection accuracy. Meanwhile, the execution time for each component per frame is calculated and compared with that of conventional Gaussian Mixture Models.",
author = "Tianci Huang and Chengjiao Guo and Jingbang Qiu and Takeshi Ikenaga",
year = "2009",
doi = "10.1109/IIH-MSP.2009.49",
language = "English",
isbn = "9780769537627",
pages = "1338--1341",
booktitle = "IIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing",

}

TY - GEN

T1 - Temporal information cooperated Gaussian Mixture Models for real-time surveillance with ghost detection

AU - Huang, Tianci

AU - Guo, Chengjiao

AU - Qiu, Jingbang

AU - Ikenaga, Takeshi

PY - 2009

Y1 - 2009

N2 - This paper describes a new real-time approach for detecting motions in the video streams taken from stationary cameras. This method combines a temporal recording scheme with the adaptive background model subtraction scheme. To save the computation brought from conventional Gaussian Mixture Models (GMM) and achieve real-time processing, an adaptively adjusted mechanism is proposed. On the other hand, illumination changes, shadow influence, and ghost in scene, these three important problems which result in low segmentation quality are settled down by utilizing proposed features and temporal information from video streams. The experimental results validate the improvement of detection accuracy. Meanwhile, the execution time for each component per frame is calculated and compared with that of conventional Gaussian Mixture Models.

AB - This paper describes a new real-time approach for detecting motions in the video streams taken from stationary cameras. This method combines a temporal recording scheme with the adaptive background model subtraction scheme. To save the computation brought from conventional Gaussian Mixture Models (GMM) and achieve real-time processing, an adaptively adjusted mechanism is proposed. On the other hand, illumination changes, shadow influence, and ghost in scene, these three important problems which result in low segmentation quality are settled down by utilizing proposed features and temporal information from video streams. The experimental results validate the improvement of detection accuracy. Meanwhile, the execution time for each component per frame is calculated and compared with that of conventional Gaussian Mixture Models.

UR - http://www.scopus.com/inward/record.url?scp=73649089280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=73649089280&partnerID=8YFLogxK

U2 - 10.1109/IIH-MSP.2009.49

DO - 10.1109/IIH-MSP.2009.49

M3 - Conference contribution

AN - SCOPUS:73649089280

SN - 9780769537627

SP - 1338

EP - 1341

BT - IIH-MSP 2009 - 2009 5th International Conference on Intelligent Information Hiding and Multimedia Signal Processing

ER -