Adaptive Background Image Calculation for Video Sequences Based on Optical Flow

Abstract:

A new method is proposed to calculate the background in video sequences. The optical flow is estimated to determine the local regions occupied by moving objects. The background image is calculated by an efficient averaging process excluding the moving object regions, which overcomes the foreground-occluding problem in direct averaging method for background estimation. The experiments for traffic video processing prove the method’s effectiveness and robustness.

• Periodical: Advanced Materials Research (Volumes 945-949)
• Pages: 1820-1824
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.945-949.1820
• Online since: June 2014
• Authors: Hui Zhu*, Xiao Peng Ji
• Keywords: Background Estimation, Image Segmentation, Optical Flow, Video Processing

References

[1] Fatih Porikli, Franuois Brémond, Shiloh Dockstader, et. al., IEEE Signal Processing Magazine, Vol. 30, No. 3 (2013), pp.190-198.

[2] Cheng-Hung Chuang, Zhen-You Lian, ICIC Express Letters, Vol. 8, No. 4 (2014), pp.1111-1118.

[3] Kenji Watanabe, Michikazu Umemura, Masakatsu Higashikubo, SEI Technical Review, No. 76 (2013), pp.90-93.

[4] Marco Cristani, R. Raghavendra, Alessio Del Bue, Murino Vittorio, Neurocomputing, Vol. 100 (2013), pp.86-97.

DOI: 10.1016/j.neucom.2011.12.038

[5] Stephen J. McKenna, Sumer Jabri, Zoran Duric, et. al., Computer Vision & Image Understanding, Vol. 80, No. 1 (2000), pp.42-56.

DOI: 10.1006/cviu.2000.0870

[6] Manuel Vargas, Jose Manuel Milla, Sergio L. Toral, Federico Barrero, IEEE Transactions on Vehicular Technology, Vol. 59, No. 8 (2010), pp.3694-3709.

DOI: 10.1109/tvt.2010.2058134

[7] Information on http: /www. cse. msu. edu/~gutchess/traffic, Dan Gutchess, Motion Estimation of Traffic.

[8] Richard P. Wildes, Michael J. Amabile, Ann-Marie Lanzillotto, Tzong-Shyng Leu, Computer Vision & Image Understanding, Vol. 80 No. 2 (2000), pp.246-266.

DOI: 10.1006/cviu.2000.0874

[9] Bineng Zhong, Yan Chen, Yingju Shen, et. al., Neurocomputing, Vol. 123 (2014), pp.344-353.

[10] Yi Tang, Weining Liu, Journal of Information and Computational Science, Vol. 10, No. 14 (2013) , pp.4593-4601.

[11] Hamidreza Baradaran Kashani, Hadi Sadoghi Yazdi, Seyed Alireza Seyedin, International Journal of Pattern Recognition and Artificial Intelligence, Vol. 25, No. 1 (2011), pp.1-35.

[12] Berthold K. P. Horn, Brian G. Schrunck: Determining Optical Flow, A. I. Memo No. 572, Massachusetts Institute of Technology, (1980).

[13] Martin Mueller, Peter Karasev, Ivan Kolesov, Allen Tannenbaum, IEEE Transactions on Image Processing, Vol. 22, No. 7 (2013), pp.2786-2797.

DOI: 10.1109/tip.2013.2258353

[14] Mikhail G. Mozerov, IEEE Transactions on Image Processing, Vol. 22, No. 5 (2013), p.2044-(2055).