计算机应用 ›› 2016, Vol. 36 ›› Issue (8): 2287-2291.DOI: 10.11772/j.issn.1001-9081.2016.08.2287

• 人工智能 • 上一篇    下一篇

基于关键帧特征库统计特征的双人交互行为识别

姬晓飞, 左鑫孟   

  1. 沈阳航空航天大学 自动化学院, 沈阳 110136
  • 收稿日期:2015-12-14 修回日期:2016-03-22 出版日期:2016-08-10 发布日期:2016-08-10
  • 通讯作者: 姬晓飞
  • 作者简介:姬晓飞(1978-),女,辽宁鞍山人,副教授,博士,CCF会员,主要研究方向:视频分析与处理、模式识别;左鑫孟(1991-),男,黑龙江鹤岗人,硕士研究生,主要研究方向:视频分析。
  • 基金资助:
    国家自然科学基金资助项目(61103123);辽宁省高等学校优秀人才支持计划项目(LJQ2014018)。

Human interaction recognition based on statistical features of key frame feature library

JI Xiaofei, ZUO Xinmeng   

  1. School of Automation, Shenyang Aerospace University, Shenyang Liaoning 110136, China
  • Received:2015-12-14 Revised:2016-03-22 Online:2016-08-10 Published:2016-08-10
  • Supported by:
    This work is partially supported by the Scientific and Technological Research Program of Chongqing Education Commission (KJ1501014), the Natural Science Foundation Project of Chongqing (cstc2014jcyjA1316, cstc2014jcyjA40035, cstc2016jcyjA0063).

摘要: 针对双人交互行为识别算法中普遍存在的算法计算复杂度高、识别准确性低的问题,提出一种新的基于关键帧特征库统计特征的双人交互行为识别方法。首先,对预处理后的交互视频分别提取全局GIST和分区域方向梯度直方图(HOG)特征。然后,采用k-means聚类算法对每类动作训练视频的所有帧的特征表示进行聚类,得到若干个近似描述同类动作视频的关键帧特征,构造出训练动作类别对应的关键帧特征库;同时,根据相似性度量统计出特征库中各个关键帧在交互视频中出现的频率,得到一个动作视频的统计直方图特征表示。最后,利用训练后的直方图相交核支持向量机(SVM),对待识别视频采用决策级加权融合的方法得到交互行为的识别结果。在标准数据库测试的结果表明,该方法简单有效,对交互行为的正确识别率达到了85%。

关键词: GIST特征, 方向梯度直方图, 关键帧特征库, 直方图相交核, UT-interaction数据库

Abstract: Some issues such as high computational complexity and low recognition accuracy still exist in human interaction recognition. In order to solve those problems, an innovative and effective method based on statistical features of key frame feature library was proposed. Firstly, features of global GIST and regional Histogram of Oriented Gradient (HOG) were extracted from the pre-processed videos. Secondly, training videos with different kind of actions were clustered by the k-means algorithm respectively to get key frame feature of each action for constructing key frame feature library; in addition, similarity measure was utilized to calculate the frequency of different key frames in every interactive video, then the statistical histogram representation of interactive videos were obtained. Finally, the decision level fusion was achieved by using Support Vector Machine (SVM) classifier based on histogram intersection kernel to obtain impressive results on UT-interaction dataset. The experimental results on standard database show that the correct recognition rate of the proposed method is 85%, which indicates that the proposed method is simple and effective.

Key words: GIST feature, Histogram of Oriented Gradient(HOG), key frame feature library, histogram intersection kernel, UT-interaction dataset

中图分类号: