湖北农业科学 ›› 2022, Vol. 61 ›› Issue (20): 172-178.doi: 10.14088/j.cnki.issn0439-8114.2022.20.033

• 信息工程 • 上一篇    下一篇

基于Sobel-LBP的农技知识视频关键帧提取优化算法

刘立2, 丰洪才1b, 黄清1a   

  1. 1.武汉轻工大学,a.数学与计算机学院,b.网络与信息中心,武汉 430023;
    2.武汉市东西湖职业技术学校信息技术系,武汉 430023
  • 收稿日期:2021-10-27 出版日期:2022-10-25 发布日期:2022-11-23
  • 通讯作者: 丰洪才(1963-),男,湖北汉川人,教授,硕士生导师,博士,主要从事多媒体信息技术与计算机网络研究,(电子信箱)fenghc@whpu.edu.cn。
  • 作者简介:刘 立(1986-),女,湖北武汉人,中学二级教师,硕士,主要从事多媒体信息技术研究,(电话)18154307077(电子信箱)474614457@qq.com。
  • 基金资助:
    湖北省教育厅重点科研计划项目(D20101703)

Optimization algorithm of key-frame extraction for agricultural technology knowledge video based on Sobel-LBP

LIU Li2, FENG Hong-cai1b, HUANG Qing1a   

  1. 1a. School of Mathematics and Computer Science, 1b. Network and Information Center, Wuhan Polytechnic University, Wuhan 430023, China;
    2. Department of Information Technology, Wuhan Dongxihu Vocational and Technical School, Wuhan 430023, China
  • Received:2021-10-27 Online:2022-10-25 Published:2022-11-23

摘要: 为提高农技知识视频中找出关键信息的效率,以水果病虫害知识视频为例,首先提取视频图像Sobel边缘局部二值模式(Sobel-LBP,Sobel Local Binary Patterns)作为特征,融合帧间差计算得出初步选取的关键帧集合;再利用初次提取关键帧在视频序列中的位置间隔大小,进行二次优化提取关键帧。通过对4段不同种类水果病虫害知识视频测试结果表明,该算法提取关键帧的综合指数F1平均值可达0.925,平均精确度为91.35%,平均缺失因子为2.46,平均保真度高达92.18%,能有效提取农技知识视频中关键帧,从而减少视频中的冗余信息,有助于将新型农业技术快速有效地传递给广大农友。

关键词: 水果知识视频, 关键帧提取, Sobel-LBP, 二次优化

Abstract: In order to improve the efficiency of finding key information in agricultural technology knowledge video, taking fruit pest knowledge video as an example, firstly, Sobel Edge Local Binary Patterns (Sobel-LBP) of the video image are extracted as features, and the preliminarily selected key frame set is calculated by fusing inter frame difference; then, the position interval of the first extracted key frame in the video sequence is used for secondary optimization to extract the key frame. The test results of four videos of different kinds of fruit diseases and insect pests knowledge show that the average value of the comprehensive index F1 of the key frame extracted by the algorithm can reach 0.925, the average accuracy is 91.35%, the average deletion factor is 2.46, and the average fidelity is 92.18%. It can effectively extract the key frames in the agricultural technology knowledge video, so as to reduce the redundant information in the video, and help to quickly and effectively transfer the new agricultural technology to the majority of farmers.

Key words: fruit knowledge video, key frame extraction, Sobel-LBP, quadratic optimization

中图分类号: