A framework for video representation and transcoding using appearance spaces

We present a novel scheme for object-based video sequence presentation using appearance spaces. Our scheme enables fully automatic extraction of semantic video objects for a class of sequences, and their supervised organization in an object-class hierarchy. The hierarchy can be used for generic classification of query video objects, and transcoding using semantics of video objects.

[1]  Michael J. Black,et al.  EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation , 1996, ECCV.

[2]  Hiroshi Murase,et al.  Visual learning and recognition of 3-d objects from appearance , 2005, International Journal of Computer Vision.

[3]  Shih-Fu Chang,et al.  An integrated approach for content-based video object segmentation and retrieval , 1999, IEEE Trans. Circuits Syst. Video Technol..

[4]  Santanu Chaudhury,et al.  An appearance based approach for video object extraction and representation , 2002, Object recognition supported by user interaction for service robots.

[5]  Gene H. Golub,et al.  Matrix computations , 1983 .

[6]  Touradj Ebrahimi,et al.  Video segmentation based on multiple features for interactive multimedia applications , 1998, IEEE Trans. Circuits Syst. Video Technol..

[7]  Michael J. Black,et al.  The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields , 1996, Comput. Vis. Image Underst..

[8]  Biswajit Bose,et al.  Enhanced Video Representation Using Objects , 2002, ICVGIP.

[9]  Ming-Chieh Lee,et al.  Semiautomatic segmentation and tracking of semantic video objects , 1998, IEEE Trans. Circuits Syst. Video Technol..

[10]  Tsuhan Chen,et al.  Model-based error concealment for wireless video , 2002, IEEE Trans. Circuits Syst. Video Technol..