影片背景重建已經被廣泛的運用，例如在做影片的物件追蹤時，需要一張真實的背景圖，或是從影片中取出一張 frame 當作背景圖片。但在現實生活中，影片中的背景多多少少會被前景所遮蔽，無法直接取出一張乾淨且完整的 frame 做為背景。本論文提出一個利用八個方向的像素資訊來重建影片背景的方法。首先先計算影片中每張 frame 的相似度，與連續 frame 當中像素的差值，用以建立每張 frame 的 mask 資訊來辨別該像素是前景或背景。接著以像素修補的方式來重建背景，利用待修補像素八個方向上的像素當做參考資訊，搭配 mask 資訊進而從影片當中找出最可靠的背景像素，重建出一張乾淨且完整的背景圖。實驗證明，我們的方法和現在最新的背景重建方法比較，可以重建出最完美的背景圖。

Video background initialization technique has been widely used in many applications. For example, a background image is required for various video object tracking methods. However, it is generally difficult to retrieve a single frame from the input video as the background image, since the background is often occluded by some stationary or moving objects. In this paper, we propose a video background initialization algorithm utilizing the multi-directional pixel information. First, the difference between successive frames are computed to construct similarity masks that are used to determine background pixels in each frame. Next, multi-directional pixel information and the constructed mask information are jointly utilized to search the candidate background pixels based on priors. We then fuse a clean and complete background image from those candidate pixels. Experimental results show that the proposed technique outperforms many state-of-the-art methods.

[1] A. Colombari and A. Fusiello, "Patch-based background initialization in heavily cluttered video," IEEE Transactions on Image Processing, vol. 19, pp. 926-933, Apr. 2010.
[2] C.-C. Chen and J. K. Aggarwal, "An adaptive background model initialization algorithm with objects moving at different depths," IEEE International
Conference on Image Processing, 2008.
[3] C. Stauffer and W. E. L. Grimson, "Learning patterns of activity using real-time tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000.
[4] K. Toyama, J. Krumm, B. Brumitt, and B. Meyers, "Wallflower: Principles
and practice of background maintenance," IEEE International Conference on
Computer Vision, vol. 1, pp. 255-261, 1999.
[5] D. Gutchess, M. Trajkovics, E. Cohen-Solal, D. Lyons, and A. Jain, "A back-ground model initialization algorithm for video surveillance," IEEE International Conference on Computer Vision, vol. 1, pp. 733-740, Nov. 2001.
[6] R. Kapoor and A. Dhamija, "Fast tracking algorithm using modified potential function," Computer Vision, IET, vol. 6, pp. 111-120, Mar. 2012.
[7] D.-M. Tsai and S.-C. Lai, "Independent component analysis-based background subtraction for indoor surveillance," IEEE Transactions on Image Processing, vol. 18, pp. 158-167, Jan. 2009.
[8] R. Marie, A. Potelle, and E. Mouaddib, "Dynamic background subtraction using moments," IEEE International Conference on Image Processing, pp. 2369-
2372, Sep. 2011.
[9] O. Barnich and M. Van Droogenbroeck, "Vibe: A universal background sub-
traction algorithm for video sequences," IEEE Transactions on Image Processing, pp. 1709-1724, Jun. 2011.
[10] V. Reddy, C. Sanderson, and B. Lovell, "An efficient and robust sequential algorithm for background estimation in video surveillance," IEEE International Conference on Image Processing, pp. 1109-1112, 2009.
[11] K. Y. S. B. Gloyer, H. K. Aghajan and T. Kailath, "Video-base freeway monitoring system using recursive vehicle tracking," Proc. of Symposium on Electronic Imaging: Image and Video Processing, pp. 173-180, 1995.
[12] C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," IEEE International Conference on Computer Vision and Pattern Recognition, pp. 246-252, 1999.
[13] W. Long and Y. Yang, "Stationary background generation: an alternative to the difference of two images," Pattern Recognition, vol. 23, pp. 1351-1359, 1990.
[14] V. Reddy, C. Sanderson, and B. Lovell, "A low-complexity algorithm for static background estimation from cluttered image sequences in surveillance contexts," Journal on Image and Video Processing, Apr. 2011.
[15] K. Moustafa and W. Badawy, "(color/gray) image in color cover hiding using modification of spatial domain hiding method," Future Generation Communication and Networking, vol. 1, pp. 56-61, 2007.
[16] X. Z. R.M. Haralick, S. Sternberg, "Image analysis using mathematical morphology," IEEE Transactions on Pattern Analysis and Machine Intelligence,
vol. PAMI-9, pp. 532-550, 1987.
[17] http://www.diegm.uniud.it/fusiello/demo/bkg/