Detection of Moving Objects Based on Mixture Gaussian Model

Abstract:

The paper proposes an improved adaptive Gaussian mixture model (GMM) approach with online EM algorithms for updating, which solves the video segmentation problems carried by busy environment and illumination change. Different learning rates are set for foreground district and background district respectively, which improves the convergence speed of background model. A shadow removal scheme is also introduced for extracting complete moving objects. It is based on brightness distortion and chromaticity distortion in RGB color space. Morphological filtering and connected components analysis algorithm are also introduced to process the result of background subtraction. The experiment results show that the improved GMM has good accuracy and high adaptability in video segmentation. It can extract a complete and clear moving object when it is incorporated with shadow removal.

• Periodical: Advanced Materials Research (Volume 1039)
• Pages: 274-279
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1039.274
• Online since: October 2014
• Authors: Guang Hua Chen, Gui Zhi Sheng*
• Keywords: Brightness Distortion, Chromaticity Distortion, EM Algorithm, GMM, Shadow Removal

References

[1] Ashit Talukder, Larry Matthies, Real-time detection of moving objects from moving vehicles using dense stereo and optical flow, J. Intelligent Robots and Systems, 2004 (4) 3718-3725.

DOI: 10.1109/iros.2004.1389993

[2] Du-Ming Tsai, Shia-Chih Lai, Independent Component Analysis-Based Background Subtraction for Indoor Surveillance, J. IEEE Transactions on Image Processing. 18 (1) 158-160.

DOI: 10.1109/tip.2008.2007558

[3] Chris Stauffer, W. E. L Grimson, Adaptive background mixture models for real-time tracking, C. Computer vision and pattern recognition, IEEE Computer Society Conference, (1999).

DOI: 10.1109/cvpr.1999.784637

[4] Chris Stauffer, W. E. L Grimson, Learning patterns of activity using real-time tracking, IEEE Transactions on Pattern Analysis & Machine Intelligence, 2000, pp.747-757.

DOI: 10.1109/34.868677

[5] Dar-Shyang Lee. Genetic-based EM algorithm for learning Gaussian mixture models, J. Pattern Analysis and Machine Intelligence, 27 (8): 1344-1348.

DOI: 10.1109/tpami.2005.162

[6] P. KaewTrakKul Pong, R. Bowden. An improved adaptive background mixture model for real-time tracking with shadow detection, in: (second ed. ), Introduction to the Video-Based Surveillance Systems, 2002, Springer US, pp.135-144.

DOI: 10.1007/978-1-4615-0913-4_11

[7] Wang Yong, Tan Yihua, Video Segmentation Algorithm with Gaussian Mixture Model and Shadow Removal, J. Opto-Electronic Engineering. 35 (3) 21-25.

[8] Rui Zhang, Sizhu Zhang. Moving objects detection method based on brightness distortion and chromaticity distortio, J. Consumer Electronics, IEEE Transactions, 53 (3) 1177-1185.

DOI: 10.1109/tce.2007.4341602

[9] Ariel Amato, Mikhail Mozerov. Background subtraction technique based on chromaticity and intensity patterns, C. Pattern Recognition, (2008).

DOI: 10.1109/icpr.2008.4761588