Pose-based clustering in action sequences

First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003. Pub Date : 2003-10-17 DOI:10.1109/HLK.2003.1240860

G. Loy, Josephine Sullivan, S. Carlsson

引用次数: 22

Abstract

A method is presented for automatically extracting key frames from an image sequence. The sequence is divided into clusters of frames with similar appearance, and the most central frame in each cluster defines a key frame. Clustering is done using an extension of the normalized cut segmentation technique based on the inter-frame similarities. The similarity between every pair of frames in the sequence is determined from the spatial image characteristics via a shape matching technique. Our algorithm is demonstrated successfully extracting 20 key frames for a tennis player in action over a 30 second (900 frame) video sequence.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

动作序列中基于姿态的聚类

提出了一种从图像序列中自动提取关键帧的方法。该序列被分成具有相似外观的帧簇，每簇中最中心的帧定义一个关键帧。聚类是基于帧间相似性的归一化分割技术的扩展。序列中每对帧之间的相似性通过形状匹配技术从空间图像特征中确定。我们的算法成功地从一个30秒(900帧)的视频序列中提取了一个网球运动员的20个关键帧。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.

自引率

0.00%

发文量

期刊最新文献

Symmetry-based photo editing Regularized 3D morphable models Pose-based clustering in action sequences A unified linear fitting approach for singular and nonsingular 3D quadrics from occluding contours Reconstruction of objects with jagged edges through Rao-Blackwellized fitting of piecewise smooth subdivision curves