Abstract
Extraction of the moving foreground object from a given video shot is an important task for spatiotemporal analysis and content representation in many computer vision and digital video processing applications. We propose an iterative framework based on energy minimization, for segmenting the prominent moving foreground object efficiently from moving camera video (MCV) shots. The solution obtained using graph-cut for figure-ground classification is enhanced using features extracted over a set of neighboring frames. This is used to iteratively update the foreground and background probability (tri-) maps and hence the graph weights. The segmentation results from neighboring frames are integrated as constraints to iteratively guide the energy minimization process, for an efficient solution. The proposed framework is automatic and does not require any human interaction (neither initialization nor refinement). Our method outperforms recent state-of-the-art moving object segmentation techniques on benchmark datasets with MCV shots.
Similar content being viewed by others
References
Mittal, A., Monnet, A., Paragios, N.: Scene modeling and change detection in dynamic scenes: a subspace approach. CVIU 113(1), 63–79 (2009)
Barnich, O., Van Droogenbroeck, M.: ViBe: A universal background subtraction algorithm for video sequences, IEEE TIP, 1709–1724 (2011)
Mittal, A., Paragios, N.: Motion-based background subtraction using adaptive kernel density estimation. CVPR (2004)
Dou, J., Li, J.: Moving object detection based on improved VIBE and graph cut optimization. Optik-Int. J. Light Electron Opt. (2013)
Ren, X., Han, T.X., He, Z.: Ensemble video object cut in highly dynamic scenes. CVPR (2013)
Stauffer, Chris, Grimson, W. E. L.: Adaptive background mixture models for real-time tracking. CVPR (1999)
Zhang, G., Jia, J., Hua, W., Bao, H.: Robust bilayer segmentation and motion/depth estimation with a handheld camera. Pattern Anal. Mach. 33(8), 603–617 (2011)
Reddy, Kishore K., Shah, Mubarak: Recognizing 50 human action categories of web videos. MVA 24(5), 971–981 (2013)
Arslan Basharat and Yun Zhai and Mubarak Shah: Content based video matching using spatiotemporal volumes. CVIU 110(3), 360–377 (2008)
Elqursh, A., Elgammal, A.: Online moving camera background subtraction. ECCV (2012)
Bai, X., Sapiro, G.: A geodesic framework for fast interactive image and video segmentation and matting. ICCV (2007)
Chattopadhyay, Chiranjoy, Das, Sukhendu: STAR: A Content Based Video Retrieval System for Moving Camera Video Shots, IEEE NCVPRIPG (2013)
Brox, T., Malik, J.: Object segmentation by long term analysis of point trajectories. ECCV (2010)
Mohand Sad Allili and Djemel Ziou: Active contours for video object tracking using region, boundary and shape information. SIViP 1(2), 101–117 (2007)
Papazoglou, A., Ferrari, V.: Fast object segmentation in unconstrained video. ICCV (2013)
Zhang, D., Javed, O., Shah, M.: Video object segmentation through spatially accurate and temporally dense extraction of primary object regions. CVPR (2013)
Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. ICCV (2011)
Narayana, M., Hanson, A., Learned-Miller, E.: Coherent motion segmentation in moving camera videos using optical flow orientations. ICCV (2013)
Kwak, S., Lim, T., Nam, W., Han, B., Han, J.H.: Generalized background subtraction based on hybrid inference by belief propagation and bayesian filtering. ICCV (2011)
Ma, T., Latecki, L.J.: Maximum weight cliques with mutex constraints for video object segmentation. CVPR (2012)
Tsai, David, Flagg, Matthew, Nakazawa, Atsushi, Rehg, James M.: Motion coherent tracking using multi-label MRF optimization. IJCV 100(2), 190–202 (2012)
Sand, P., Teller, S.: Particle video: long-range motion estimation using point trajectories. CVPR (2006)
Sheikh, Y., Javed, O., Kanade, T.: Background subtraction for freely moving cameras. ICCV (2009)
Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. CVPR (2009)
Bekkerman, R., Sahami, M., Learned-Miller, E.: Combinatorial Markov random fields. ECML (2006)
Li, J., Levine, M.D., An, X., Xu, X., He, H.: Visual saliency based on scale-space analysis in the frequency domain. IEEE T-PAMI 35(4), 996–1010 (2013)
Cheng, M.-M., Zhang, G.-X., Mitra, N.J., Huang, X., Hu, S.-M.: Global contrast based salient region detection. CVPR (2011)
Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.-H.: Saliency detection via graph-based manifold ranking. CVPR (2013)
McFarlane, Nigel J.B., Schofield, C.P.: Segmentation and tracking of piglets in images. MVA 3(8), 187–193 (1995)
Tsai, D., Flagg, M., Rehg, J.M.: Motion coherent tracking with multi-label MRF optimization. BMVC (2010)
Results of moving foreground blob segmentation from MCVs. http://www.cse.iitm.ac.in/vplab/results/mos_mcv/sivip.html
Zhang, K., Zhang, L., Yang, M.-H.: Real-time compressive tracking. ECCV (2012)
Takeda, Hiroyuki, Farsiu, Sina, Milanfar, Peyman: Kernel regression for image processing and reconstruction. IEEE TIP 16(2), 349–366 (2007)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chattopadhyay, C., Das, S. Prominent moving object segmentation from moving camera video shots using iterative energy minimization. SIViP 9, 1927–1934 (2015). https://doi.org/10.1007/s11760-014-0686-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-014-0686-8