会议专题

iFrames: A Multi-Level Keyframe Extraction and Navigation Tool for Videos

A video sequence can be represented as a sequence of points in a high dimensional feature space that forms a polyline curve. Mapping a video frame onto a point is based on the geometric features detected in the frame which provide the perceptual differences between frames. The polyline is then analyzed and simplified using two metrics considering the mutual relationships among the nodes. The polyline is recursively simplified and a multi-level representation is obtained. The nodes at the low level polyline correspond to the key frames of the video. After transforming the polyline from the high dimensional space into 3D space, users can view the keyframes as well as their mutual relationships in an intuitive and easy manner. The multi-level representation of polylines offers a coarse-to-fine key frames for the video, and provides users a favorable experience on navigating the video.

Key frame extraction video abstraction video navigation

国际会议

2011国际计算机辅助设计与图形学学术会议(CAD/Graphics 2011)

济南

英文

1-7

2011-09-15(万方平台首次上网日期,不代表论文的发表时间)