Foreground-Background Separation From Video Clips Using RMAMR Method Along With Ground Truth Extraction

Nifi C Joy, Federal Institute Of Science and Technology; Dr Prasad J.C ,Federal Institute Of Science and Technology

Background subtraction, Foreground Detection, ADM ,Motion Detection, Ground truth extraction

Foreground-Background Separation from video clips using RMAMR method along with ground truth extraction plays a great role in video surveillance systems. The method proves to be a fully and important technique, making recognition, classification, and scene analysis more efficient. Initially ground truth images are extracted for the given video. A motion-assisted matrix restoration (MAMR) model for foreground background separation in video clips is proposed. In the proposed MAMR model, the backgrounds across frames are modeled by a low-rank matrix, while the foreground objects are modeled by a sparse matrix. To facilitate efficient foreground background separation, a dense motion field is estimated for each frame, and mapped into a weighting matrix which indicates the likelihood that each pixel belongs to the background. Anchor frames are selected in the dense motion estimation to overcome the difficulty of detecting slowly moving objects and camouflages. A robust MAMR model (RMAMR) is proposed against noise for practical applications. Experiment shows that the proposed methodology affirms a good performance in separation of foreground and background from video clips.
    [1] C. R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland, “Pfinder: Real-time tracking of the human body", in IEEE Trans. Pattern Anal. Mach. Intell., Jul. 1997 [2] L.Li, W.Huang, I.Gu, and Q.Tian, “Foreground Object Detection from Videos Containing Complex Background ", ACM 2003. [3] Jing Zhong, Stan Sclarofi , “Segmenting Foreground Objects from a Dynamic Textured Background via a Robust Kalman Filter", in Proc. IEEE, 2003 [4] S. Derin Babacan, Martin Luessi and RafaelMolina, “Sparse Bayesian Methods for Low-Rank Matrix Estimation", in Proc. IEEE , Jun2012. [5] Zoran Zivkovic,”Improved Adaptive Gaussian Mixture Model for Background Subtraction" ICPR, Aug. 2004. [6] Martin Hofmann, Philipp Tiefenbacher, Gerhard Rigoll, “Background Segmentation with Feedback: The Pixel-Based Adaptive Segmenter ", in Proc. IEEE Int. , Jan. 2012,pp. 21532160. [7] Olivier Barnich and Marc Van Droogenbroeck, “ ViBe: A Universal Background Subtraction Algorithm for Video Sequences ", in Proc. IEEE, 2011. [8] Candles, Xiaodong Li, Yi Ma, and John Wright, “Robust Principal Component Analysis", ACM, 2011. [9] Lucia Maddalena and Alfredo Petrosino, ”A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications", IEEE Trans., Jul. 2008. [10] Xiaowei Zhou, Can Yang and W Yu, “GoDec: Randomized Low-rank and Sparse Matrix Decomposition in Noisy Case", International Conference on Machine Learning, 2011. [11] Xinchen Ye, Jingyu Yang,Xin Sun, Kun Li, “Foreground Background Separation From Video Clips via Motion-Assisted Matrix Restoration", in Proc. IEEE , 2015, pp.25772580.
Paper ID: GRDJEV01I100071
Published in: Volume : 1, Issue : 10
Publication Date: 2016-10-01
Page(s): 79 - 88