姿态估计和跟踪结合的运动视频关键帧提取-电视技术.DOC

论文引用格式： 中图分类号：TP391 文献标志码：A DOI：10.16280/j.videoe.2015.20.000 姿态估计和跟踪结合的运动视频关键帧提取 石念峰1,2, 侯小静1, 张 平3, 孙西铭2 (1.洛阳理工学院 计算机与信息工程学院，河南 洛阳 471023；2.南昆士兰大学，澳大利亚 昆士兰州 图文巴市 4350；3.河南科技大学 数学与统计学院，河南 洛阳 471023) 摘 要：提出姿态估计和特定部位跟踪相结合的动作视频关键帧提取算法。首先利用非确定人体部位的时间连续性保持提高基于柔性部件铰接人体模型的单帧图像人体姿态估计准确率，通过实施数据降维得到局部拓扑结构表达能力强的判别性运动特征向量，采用极值判定原理确定候选关键帧集合。然后利用ISODATA动态聚类算法，通过初始聚类中心优化、基于语义的关键帧集合增强等策略确定关键帧。实验表明文中算法具有较高的关键帧提取准确率和召回率，支持基于语义的关键帧提取。提取的视频关键帧可以用于运动视频压缩和批注审阅。 关键词：关键帧提取; 运动视频; 姿态估计; 拉普拉斯降维; 特征选择; ISODATA Joint Pose Estimation and Tracking for Keyframe Extraction of Motion Video SHI Nianfeng1，2, , ZHANG Ping3 , SUN Ximing2 (1. Department of Computer Science, Luoyang Institute of Science and Technology, Luoyang 471023, China?; 2. University of Southern Queensland, Toowoomba 4350, Australia?;3. School of Mathematics and Statistics, Henan University of Science and Technology, Luoyang 471023, China) Abstract: A key frame extraction framework for motion video is proposed by using pose estimation and dynamic clustering techniques. The pose configuration of body part is computed with a mixture-of-parts articulated human model in single frame, whose accuracy is promoted by using temporal feature preserving of special body-part. The body-part motion is modeled with a set of discriminative motion vectors that has a good power of locality preserving and is received by performing a feature selection based on Laplacian Scoring on the relative distances and motion directions of each body part. A candidate keyframe set is filter out in the extremum principle. The extracted keyframes are attained by using an ISODATA-based clustering with the initial cluster centers optimization and semantic-based enhancement of the candidate keyframe set. Experimental data suggest that the proposed algorithm can experience a high accuracy and recall rate, and can facilitate the semantic-based keyframe extraction. Key frames extracted can be used to sports video compress and annotation. Key words: keyf