基于SIFT的足球运动员检测和跟踪  

Football player detection and tracking based on SIFT

作　　者：闵军[1] 孟朝晖[1] 

机构地区：[1]河海大学计算机与信息学院,南京211100

出　　处：《信息技术》2016年第5期195-198,共4页Information Technology

摘　　要：当前足球视频的解说和分析是智能领域研究的热点问题,文中提出一种基于尺度不变特征(SIFT)的球员检测和跟踪算法。该算法首先利用颜色特征提取场地区域,再以尺度不变特征点检测来确定球员位置,最后通过帧间特征点关联图实现对球员的跟踪。在MATLAB软件上借助图像处理工具箱进行编译,经过测试,球员检测和跟踪正确率达到90%。In modern society commentary and analysis of soccer video being issue in intelligent field,a player detection and tracking algorithm based on scale-invariant feature transform（ SIFT） is proposed in this paper. Firstly,using color feature of each pixels it extracts the field area; then determining the position of players based on the scale-invariant feature detection; finally,through the connectivity map of feature points between frames tracking players. This algorithm builds the experimental platform on MATLAB by means of image processing toolbox,and the test results show that player detection and tracking accuracy reached 90%.

关 键 词：足球视频 颜色特征 尺度不变 跟踪 检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]