基于熵的自适应网球比赛视频镜头边界检测技术
daptive shot boundary detection technology of tennis match video based on Entropy
镜头分割通常是视频分析的一个重要流程，镜头分割技术又叫做镜头边界检测，其中，基于视频时域分割又分为镜头的切变检测和渐变检测。本文提出了一种基于熵和局部描述子的镜头边界检测的改进技术，通过分析网球视频帧的特点，进行了一定的创新，引入自适应阈值法，在利用熵进行判断时，进行判断的两个阈值可以使用滑动窗口的方式进行确定，实验结果证明，该方法在网球比赛视频中准确率高，且有一定的泛用性，可拓展到其他视频的边界检测方法中。
In this paper we proposes an improved shot boundary detection technology based on entropy and local descriptor. By analyzing the characteristics of tennis video frame, some innovation is made, and the adaptive threshold method is introduced. When using entropy to judge, the two thresholds can be determined by sliding window. The experimental results show that this method has high accuracy in tennis video It can be extended to other video boundary detection methods.
徐明昆、余天效
电视电子技术应用
镜头分割熵自适应阈值网球视频切变帧渐变帧
shot segmentationentropyadaptive thresholdtennis videoshear framegradient frame
徐明昆,余天效.基于熵的自适应网球比赛视频镜头边界检测技术[EB/OL].(2021-03-16)[2025-08-11].http://www.paper.edu.cn/releasepaper/content/202103-163.点此复制
评论