Video Browsing Using Edges and Motion
Abstract
Automatic video browsing requires algorithms for detecting a variety of events, including production effects (e.g., scene breaks and captions) and moving objects. We present new methods that use edges and motion for detecting production effects and computing motion segmentation. Production effects, such as cuts, dissolves, wipes and captions, can be detected by looking for new edges that are far from previous edges. A global motion computation, is used to register consecutive images. We have also developed a method for motion segmentation, which does not require computing local optical flow. Our methods run at several frames per second on a Sparc workstation, and tolerate compression artifacts.
Cite
Text
Zabih et al. "Video Browsing Using Edges and Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517109Markdown
[Zabih et al. "Video Browsing Using Edges and Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/zabih1996cvpr-video/) doi:10.1109/CVPR.1996.517109BibTeX
@inproceedings{zabih1996cvpr-video,
title = {{Video Browsing Using Edges and Motion}},
author = {Zabih, Ramin and Miller, Justin and Mai, Kevin},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1996},
pages = {439-446},
doi = {10.1109/CVPR.1996.517109},
url = {https://mlanthology.org/cvpr/1996/zabih1996cvpr-video/}
}