论文信息 - A context-based approach to crop and scale video for broadcast applications

A context-based approach to crop and scale video for broadcast applications

Within this paper an application is presented which automatically adapts SDTV (Standard Definition Television) sports productions to smaller displays through intelligent cropping and scaling. It crops regions of interest of sports productions based on a smart combination of production metadata and systematic video analysis methods. This allows a context-based repurposing. It provides a differentiation between the original SD-version of the production and the processed one adapted to the requirements for mobile TV.

[1] Anne Treisman,et al. Features and objects in visual processing , 1986 .

[2] Hermann Ney,et al. Pan, zoom, scan — Time-coherent, trained automatic video cropping , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[3] Liqing Zhang,et al. Saliency Detection: A Spectral Residual Approach , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[4] J. Schmee. Applied Statistics—A Handbook of Techniques , 1984 .

[5] Michael J. Swain,et al. Indexing via color histograms , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[6] J.-Y. Bouguet,et al. Pyramidal implementation of the lucas kanade feature tracker , 1999 .

[7] Wen-Huang Cheng,et al. A Visual Attention Based Region-of-Interest Determination Framework for Video Sequences , 2005, IEICE Trans. Inf. Syst..

[8] P. Rousseeuw. Least Median of Squares Regression , 1984 .

[9] D. Ruderman. The statistics of natural images , 1994 .

[10] Christof Koch,et al. A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[11] O. Meur,et al. Predicting visual fixations on video based on low-level visual features , 2007, Vision Research.

[12] Jean Ponce,et al. Computer Vision: A Modern Approach , 2002 .

[13] Oliver Grau,et al. Tracking football player movement from a single moving camera using particle filters , 2006 .