计算机应用 ›› 2016, Vol. 36 ›› Issue (8): 2134-2138.DOI: 10.11772/j.issn.1001-9081.2016.08.2134

• 第六届中国数据挖掘会议(CCDM 2016) • 上一篇    下一篇

基于尺度自适应局部时空特征的足球比赛视频中的多运动员行为表示

王智文1, 蒋联源1,2, 王宇航3, 王日凤1, 张灿龙4, 黄镇谨1,2, 王鹏涛5   

  1. 1. 广西科技大学 计算机科学与通信工程学院, 广西 柳州 545006;
    2. 桂林电子科技大学 广西信息科学实验中心, 广西 桂林 541004;
    3. 桂林航天工业学院 汽车与交通工程学院, 广西 桂林 541004;
    4. 广西师范大学 计算机科学与信息工程学院, 广西 桂林 541004;
    5. 广西科技大学 电气与信息工程学院, 广西 柳州 545006
  • 收稿日期:2016-03-01 修回日期:2016-05-17 出版日期:2016-08-10 发布日期:2016-08-10
  • 通讯作者: 王智文
  • 作者简介:王智文(1969-),男,湖南邵东人,教授,博士,主要研究方向:机器学习、计算机视觉、移动目标检测、行为识别;蒋联源(1981-),男,广西全州人,副教授,硕士,主要研究方向:图形图像处理;王宇航(1994-),男,湖南邵东人,主要研究方向:图像处理;王日凤(1974-),女,广西桂林人,副教授,博士,主要研究方向:医学图像处理;张灿龙(1975-),男,湖南娄底人,副教授,博士,主要研究方向:图像处理;黄镇谨(1975-),男,广西柳州人,副教授,硕士,主要研究方向:数据挖掘;王鹏涛(1990-),男,陕西西安人,硕士研究生,主要研究方向:图像处理。
  • 基金资助:
    国家自然科学基金资助项目(61462008,61440017,61365009);广西自然科学基金项目(2013GXNSFAA019336,2014GXNSFAA118368);广西信息科学实验中心开放基金项目(KF1403);广西科技大学博士基金项目(院科博12Z14);2015年广西科技大学创新团队项目。

Behavior representation of multi-athletes for football game video based on scale adaptive local spatial and temporal characteristics

WANG Zhiwen1, JIANG Lianyuan1,2, WANG Yuhang3, WANG Rifeng1, ZHANG Canlong4, HUANG Zhenjin1,2, WANG Pengtao5   

  1. 1. College of Computer Science and Communication Engineering, Guangxi University of Science and Technology, Liuzhou Guangxi 545006, China;
    2. Guangxi Experiment Center of Information Science, Guilin University of Electronic Technology, Guilin Guangxi 541004, China;
    3. Institute of Automobile and Traffic Engineering, Guilin University of Aerospace Technology, Guilin Guangxi 541004, China;
    4. College of Computer Science & Information Technology, Guangxi Normal University, Guilin Guangxi 541004, China;
    5. College of Electrical and Information Engineering, Guangxi University of Science and Technology, Liuzhou Guangxi 545006, China
  • Received:2016-03-01 Revised:2016-05-17 Online:2016-08-10 Published:2016-08-10
  • Supported by:
    This work is partially supported by the Natural Science Foundation of China (61170222, 11301466, 11361048), the Science Foundation of the Education Department of Yunnan Province (2015J007).

摘要: 为提高足球比赛视频中的多运动员行为识别的准确率,提出一种基于尺度自适应局部时空特征的足球比赛视频中的多运动员行为表示方法,利用时空兴趣点来表示足球比赛视频中的多运动员行为。首先将足球比赛视频序列中的多运动员行为看作是三维空间中的时空兴趣点的集合,然后采用直方图量化技术将时空兴趣点集合量化为维数固定的直方图(即时空单词),最后采用K-means聚类算法生成时空码本。在聚类生成码本之前,对每个时空兴趣点都进行了归一化,以保证其缩放和平移不变性。实验结果表明,该方法能够大大减少足球比赛视频中的多运动员行为识别算法的计算量,显著提高识别的准确率。

关键词: 时空兴趣点, 多运动员行为表示, 行为识别, K-means聚类算法, 时空特征检测操作数

Abstract: In order to improve the accuracy of behavior recognition of multi-athletes in football game video, a behavior representation method of multi-athletes for video football game based on scale adaptive local spatial and temporal characteristics was put forward. Behavior recognition was carried on using spatial-timporal interest point to represent behavior of multi-athletes in video football game. Firstly, multi-athletes behavior in the sequence of video football game was regarded as a collection of spatial-timporal interest points in three-dimensional space. Secondly, the set of spatial-temporal interest points was quantified as histogram which has fixed dimension (ie temporal word) by using quantitative technique of histogram. Finally, spatial-temporal codebook was generated by using K-means clustering algorithm. Each spatial-timporal interest point was normalized to ensure its scaling and translation invariance before clustering codebook generated. Experimental results show that the proposed method can greatly reduce the computational amount of the algorithm,and the accuracy of recognition can be significantly improved.

Key words: spatial-temporal interest point, multi-athletes behavior representation, behavior recognition, K-means clustering algorithm, spatial-temporal feature detection operand

中图分类号: