Content and transformation effect matching for automated home video editing

While camcordcrs havc bccome a commodity home appliance, few watch the recorded vidcos or sharc thcm with friends and relatives duc to the difficulty of turning thc raw footagc into a compclling vidco story. Previous works on Automated Video Editing (AVE) dcvelopcd an automatic solution for vidco contcnt selection and video-music matching. Howcvcr, to automatically apply vidco transformation effects, such a fastislow motion, thresholding, binariration and watercolor, has not been solved or even addressed. In this paper, we proposed several automatic video effect and contcnt matching schemes, which facilitate generating more compelling and intcrcsting AVE rcsults.

[1]  HongJiang Zhang,et al.  A novel motion-based representation for video mining , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[2]  Nicolai Petkov,et al.  Comparison of texture features based on Gabor filters , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[3]  Lie Lu,et al.  AVE: automated home video editing , 2003, ACM Multimedia.

[4]  Alain Jacot-Descombes,et al.  Video segmentation and camera motion characterization using compressed data , 1997, Other Conferences.

[5]  Nicolai Petkov,et al.  Comparison of texture features based on Gabor filters , 2002, IEEE Trans. Image Process..

[6]  Yanjun Qi,et al.  A probabilistic model for camera zoom detection , 2002, Object recognition supported by user interaction for service robots.