ABSTRACT
This paper presents a novel object-based video coding framework for videos obtained from a static camera. As opposed to most existing methods, the proposed method does not require explicit 2D or 3D models of objects and hence is general enough to cater for varying types of objects in the scene. The proposed system detects and tracks objects in the scene and learns the appearance model of each object online using incremental principal component analysis (IPCA). Each object is then coded using the coefficients of the most significant principal components of its learned appearance space. Due to smooth transitions between limited number of poses of an object, usually a limited number of significant principal components contribute to most of the variance in the object's appearance space and therefore only a small number of coefficients are required to code the object. The rigid component of the object's motion is coded in terms of its affine parameters. The framework is applied to compressing videos in surveillance and video phone domains. The proposed method is evaluated on videos containing a variety of scenarios such as multiple objects undergoing occlusion, splitting, merging, entering and exiting, as well as a changing background. Results on standard MPEG-7 videos are also presented. For all the videos, the proposed method displays higher Peak Signal to Noise Ratio (PSNR) compared to MPEG-2 and MPEG-4 methods, and provides comparable or better compression.
- Y. Altunbasak and A. M. Tekalp, "Occlusion-adaptive content-based 2-D mesh design and tracking for object-based coding," In IEEE Transactions on Image Processing, vol. 6, no. 9, pp.1270--1280, 1997. Google ScholarDigital Library
- K. Aizawa and T. Huang, "Model Based Image Coding: Advanced Video Coding Techniques for Very Low Bit-Rate Applications," In Proceedings of the IEEE, vol. 83, no. 2, pp.259--271, 1995.Google ScholarCross Ref
- J. Bergen, P. Anandan, K. Hanna, and R. Hingorani. "Hierarchical model-based motion estimation". In European Conference on Computer Vision, pp.237--252, 1992. Google ScholarDigital Library
- Buck, "Segmentation of moving head-and-shoulder shapes," In Picture Coding Symposium, Boston, 1990.Google Scholar
- C. S. Choi and T. Tekebe, "Analysis and synthesis of facial image sequences in model-based image coding," In IEEE Transactions on Video Technology, pp.257--275, 1994.Google Scholar
- D. DeCarlo, D. Metaxas, and M.Stone, "An Anthropometric Face Model using Variational Techniques," In Proc. SIGGRAPH, pp.67--74, 1998. Google ScholarDigital Library
- O. Javed, K. Shafique, and M. Shah. "A hierarchical approach to robust background subtraction using color and gradient Information". In Workshop on Motion and Video Computing, pp.22--27, 2002. Google ScholarDigital Library
- O. Javed, Z. Rasheed, O. Alatas, and M. Shah, "KNIGHTM:A Real Time Surveillance System for Multiple Overlapping and Non-Overlapping Cameras". In The Fourth International Conference on Multimedia and Expo, Baltimore, Maryland, 2003. Google ScholarDigital Library
- O. Javed, and M. Shah. "Tracking and Object Classification for Automated Surveillance". In European Conference on Computer Vision, pp.343--357, 2002. Google ScholarDigital Library
- I. T. Jolliffe. "Principal component analysis". New York: Springer-Verlag, 1986.Google Scholar
- R. Koch, "Dynamic 3D scene analysis through synthesis feedback control", In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15(6), June, 1993. Google ScholarDigital Library
- I. Martins and L. Corte-Real, "A Video-coder using 3D model-based background for video surveillance applications,". In IEEE Internation Conference on Image Processing, pp.919--923, 1998.Google Scholar
- G. Menegaz and J. Thiran, "Lossy to lossless object-based coding of 3D MRI data". In IEEE Transactions on Image Processing, Vol.11(9), pp.1053--1061, 2002. Google ScholarDigital Library
- Y. Nakaya, K. Aizawa, and H. Harashima, "Texture updating methods in model-based coding of facial images,". In Picture Coding Symposium, Boston, 1990.Google Scholar
- C. Staffer, and W. E. L. Grimson. "Learning patterns of actvity using real-time tracking." In IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.22(8), pp.747--757, 2000. Google ScholarDigital Library
- G. Strang. "Linear algebra and its applications". New York: Academic, 1980.Google Scholar
- M. G. Strinzis, "Object-based coding of stereospic and 3D image sequences,". In IEEE Signal Processing Magazine, pp.14--28, 1999.Google ScholarCross Ref
- M. J. Turk, and A. Pentland. "Eigenfaces for recognition". In Workshop on Human Computer Interaction, Vol.3, pp.71--86, 1991.Google ScholarDigital Library
- A. Vetro, T Haga, K. Sumi, and H. Sun, "Object based coding for long term archive of surveillance video". In Technical Report, TR-2003-98, MERL, July 2003.Google Scholar
- W. J. Welsh "Model-based coding of videophone images," In Electronic and Communication Engineering Journal, Vol.3(1), pp.29--36, 1991.Google ScholarCross Ref
- J. Weng, Y. Zhang, and W. Hwang. "Candid covariance-free incremental principal component analysis". In IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.25(8), pp.1034--1040, 2003. Google ScholarDigital Library
- Y. Zhang, and J. Weng. "Convergence analysis of complementary candid incremental principal component analysis". Technical Report MSU-CSE-01-23, Michigan State University, East Lansing, 2001.Google Scholar
- A. Yilmaz, X. Li, and M. Shah. "Contour-based object tracking with occlusion handling in video acquired using mobile cameras". In IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.26(11), 2004. Google ScholarDigital Library
- A. L. Yuille, P. W. Hallina, and D. S. Cohen, "Feature extraction from faces using deformable templates," In International Journal of Computer Vision, Vol.8(2), pp.99--111, 1992. Google ScholarDigital Library
- "CAVIAR: Context Aware Vision using Image-based Active Recognition", Downloadable from http://homepages.inf.ed.ac.uk/rbf/CAVIAR/.Google Scholar
- "PETS: Performance Evaluation of Tracking and Surveillance", Downloadable from http://pets2002.visualsurveillance.org/.Google Scholar
Index Terms
- An object-based video coding framework for video sequences obtained from static cameras
Recommendations
Moving object extraction with cooperative cameras
We present a novel approach to robust extraction of moving objects with cooperative static and active cameras. The active camera, for usual broadcasts, is fixed in location but free to rotate and zoom. The static camera is a completely fixed panoramic ...
Hybrid model-and-object-based real-time conversational video coding
Bandwidth-constrained real-time conversational video communications (such as mobile teleconferencing) require video codecs with good rate-distortion characteristics at low bit-rates and modest computational complexity. While target-specific object-based ...
Multi-object Tracking in Video Sequences Based on Background Subtraction and SIFT Feature Matching
ICCIT '09: Proceedings of the 2009 Fourth International Conference on Computer Sciences and Convergence Information TechnologyWe have presented a method for tracking multiple objects in video sequences based on background subtraction and SIFT feature matching where camera is fixed and input video sequences are real time or self captured. Object is detected automatically by ...
Comments