A Low Complexity Motion Segmentation Based on Semantic Representation of Encoded Video Streams
Abstract
Video streaming is characterized by a deep heterogeneity due to the availability of many different video standards such as H.262, H.263, MPEG-4/H.264, H.261 and others. In this situation two approaches to motion segmentation are possible: the first needs to decode each stream before processing it, with a high computational complexity, while the second is based on video processing in the coded domain, with the disadvantage of coupling between implementation and the coded stream. In this paper a motion segmentation based on a “generic encoded video model” is proposed. It aims at building applications in the encoded domain independently by target codec. This can be done by a video stream representation based on a semantic abstraction of the video syntax. This model joins the advantages of the two previous approaches by making it possible working in real time, with low complexity, and with small latency. The effectiveness of the proposed representation is evaluated on a low complexity video segmentation of moving objects.
Keywords
Video Sequence Motion Vector Semantic Representation Semantic Description Video StandardReferences
- 1.Ahmad, A., Ahmad, B., Lee, S.: Fast and robust object detection framework in compressed domain. In: Proc. IEEE Sixth Int. Symposium on Multimedia Software Engineering, pp. 210–217 (December 2004)Google Scholar
- 2.Chung, R., Chin, F., Wong, K., Chow, K., Luo, T., Fung, H.: Efficient block-based motion segmentation method using motion vector consistency. In: MVA 2005 IAPR Conference on Machine Vision Applications, pp. 550–553 (May 2005)Google Scholar
- 3.Hong, W., Lee, T., Chang, P.: Real-time foreground segmentation for the moving camera based on h.264 video coding information. In: Proc. IEEE Int. Conf. on Future Generation Communication and Networking, pp. 385–390 (December 2007)Google Scholar
- 4.Hsieh, C., Lai, W., Chiang, A.: A real time spatial/temporal/motion integrated surveillance system in compressed domain. In: Proc. IEEE Int. Conf. on Intelligent Systems Design and Applications, pp. 658–665 (November 2008)Google Scholar
- 5.Ji, S., Park, H.: Region-based video segmentation using dct coefficients. In: Proc. IEEE Int. Con. Image Processing, vol. 2, pp. 150–154 (October 1999)Google Scholar
- 6.Karayiannis, Varughese, Tao, Frost, Wise, Mizrahi.: Quantifying motion in video recordings of neonatal seizures by regularized optical flow methods. IEEE Trans. Image Process.14(7), 890–903 (July)Google Scholar
- 7.Lee, S.W., Kim, Y.M., Choi, S.W.: Fast scene change detection using direct feature extraction from mpeg compressed video. IEEE Trans. Multimedia 2(4), 240–254 (2000)CrossRefGoogle Scholar
- 8.Neri, A., Colonnese, S., Russo, G., Talone, P.: Automatic moving object and background separation. Signal Process.(Special Issue) (66), 219–232 (1998)Google Scholar
- 9.Nguyen, H., Worring, M., Dev, A.: Detection of moving objects in video using a robust motion similarity measure. IEEE Trans. Image Process. 1(9), 137–141 (2000)CrossRefGoogle Scholar
- 10.Pons, J., Prades-Nebot, J., Albiol, A., Molina, J.: Fast motion detection in compressed domain for video surveillance. IEEE Electronics Letters 38(9), 409–411 (2002)CrossRefGoogle Scholar
- 11.Porikli, F., Bashir, F., Sun, H.: Compressed domain video object segmentation. IEEE Trans. Image Process. 1(5297), 2–14 (2010)Google Scholar
- 12.Ritch, M., Canagarajah, N.: Motion-based video object tracking in the compressed domain. In: Proc. IEEE Int. Con. Image Processing, vol. 6, pp. 301–306 (2007)Google Scholar
- 13.Tao, K., Lin, S., Zhang, Y.: Compressed domain motion analysis for video semantic events detection. In: Proc. IEEE Int. Conf. on Information Engineering, pp. 201–204 (July 2009)Google Scholar
- 14.Zeng, W., Gao, W., Zhao, D.: Automatic moving object extraction in mpeg video. In: Proc. IEEE Int. Symposium on Circuits and Systems, vol. 2, pp. 524–527 (2003)Google Scholar