Compressed Domain Motion Analysis for Video Semantic Events Detection

In this paper, a novel approach is proposed to estimate camera motion and segment moving objects from compressed video streams, aiming to detect semantic events in video clips. Simultaneously using the motion vectors and DC components of MPEG macroblocks (MB), the camera motion type and motion parameters of each frame are estimated with simplified models. Then the segmentation of moving objects is done at macroblock level. Exploring the variation of motion information in consecutive frame sequence, a composite feature can be formed to detect semantic events. The experiment results on TRECVID video corpus show that our approach is very effective and efficient.

[1]  Bernd Freisleben,et al.  Segmenting Moving Objects in MPEG Videos in the Presence of Camera Motion , 2007, 14th International Conference on Image Analysis and Processing (ICIAP 2007).

[2]  Chen-Chiung Hsieh,et al.  A Real Time Spatial/Temporal/Motion Integrated Surveillance System in Compressed Domain , 2008, 2008 Eighth International Conference on Intelligent Systems Design and Applications.

[3]  Patrick Bouthemy,et al.  Recognition of Dynamic Video Contents With Global Probabilistic Models of Visual Motion , 2006, IEEE Transactions on Image Processing.

[4]  Stéphane Marchand-Maillet,et al.  Local Feature Trajectories for Efficient Event-Based Indexing of Video Sequences , 2006, CIVR.

[5]  Rangasami L. Kashyap,et al.  Models for motion-based video indexing and retrieval , 2000, IEEE Trans. Image Process..

[6]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[7]  R. Venkatesh Babu,et al.  Video object segmentation: a compressed domain approach , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[8]  Michael G. Strintzis,et al.  Real-time compressed-domain spatiotemporal segmentation and ontologies for video indexing and retrieval , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Boon-Lock Yeo,et al.  On the extraction of DC sequence from MPEG compressed video , 1995, Proceedings., International Conference on Image Processing.

[10]  Cedric Nishan Canagarajah,et al.  Motion-Based Video Object Tracking in the Compressed Domain , 2007, 2007 IEEE International Conference on Image Processing.

[11]  R. Venkatesh Babu,et al.  Compressed domain motion segmentation for video object extraction , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[12]  Tianli Yu,et al.  Retrieval of video clips using global motion information , 2001 .

[13]  Milan Sonka,et al.  Image processing analysis and machine vision [2nd ed.] , 1999 .