基于BP神经网络的体育视频关键姿态检测  

Key Pose Detection of Sports Video Based on BP Neural Network

作　　者：韩美林 HAN Mei-lin(School of Electronic Information and Electrical Engineering,Shangluo University,Shangluo 726000,Shaanxi)

机构地区：[1]商洛学院电子信息与电气工程学院

出　　处：《商洛学院学报》2019年第6期14-17,共4页Journal of Shangluo University

基　　金：陕西省自然科学基础研究计划项目（2019JQ-541）;陕西省体育局常规课题（2019084）

摘　　要：块背景估计法进行人体目标检测,根据边缘特征来完成目标的特征提取,利用改进的BP神经网络对举重运动中常见的四种人体姿态进行识别。仿真结果表明,本算法可以较为准确的识别出举重运动中四种常见的人体姿态。本技术还可适用于其他体育项目视频关键姿态的检测,提高体育运动的技能。In order to enable athletes and coaches to train more effectively,this thesis aims at weightlifting video,using hierarchical block background estimation method to detect human targets,and then extracting features based on edge features.Finally,using improved BP neural network for weightlifting Three human postures that are common in sports are identified.The simulation results show that the proposed algorithm can accurately identify three common human postures in weightlifting.At the same time,the technology can also be applied to the detection of key poses of other sports videos,and improve the skills of sports.

关 键 词：误差反向传播算法 神经网络 姿态检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]