Research on Scoring Method of Skiing Action Based on Human Key Points
梅健 1孙珈玥 2邹青宇2
扫码查看
点击上方二维码区域，可以放大扫码查看
作者信息
1. 吉林化工学院信息与控制工程学院,吉林吉林 132022
2. 北华大学电气与信息工程学院,吉林吉林 132021
折叠
摘要
针对使用传统方法识别评估滑雪运动员的训练动作存在人为主观、准确率低等问题,提出了一种基于改进OpenPose 和 YOLOv5(You Only Look Once version 5)的动作分析算法.利用 CSP-Darknet53(Cross Stage Paritial-Network 53)作为OpenPose外部网络将输入图片降维处理并提取特征图.融合优化YOLOv5算法,提取人体骨骼关键点构成人体骨架与标准动作进行对比,根据角度信息评分,并在模型中加入损失函数,量化实际检测动作与标准动作的误差.该模型可对运动员动作即时监控,能完成初步的动作评估.实验结果表明,检测识别准确率达到95％,可满足日常滑雪训练需求.
Abstract
The training actions of skiing athletes can directly reflect their level,but traditional methods for identifying and evaluating actions have shortcomings such as subjectivity and low accuracy.To achieve accurate analysis of skiing posture,a motion analysis algorithm based on improved OpenPose and YOLOv5(You Only Look Once version 5)is proposed to analyze athletes'movements.There are two main improvements.First,CSP-Darknct53(Cross Stage Paritial-Network 53)is used as the external network for OpenPose to reduce the dimension of the input image and extract the feature map.Then,the YOLOv5 algorithm is fused to optimize it.The key points of the human skeleton are extracted to form the human skeleton and compared with the standard action.According to the angle information,the loss function is added to the model to quantify the error between the actual detected action and the standard action.This model achieves accurate and real-time monitoring of athlete action evaluation in training scenarios and can complete preliminary action evaluation.The experimental results show that the detection and recognition accuracy reaches 95％,which can meet the needs of daily skiing training.
关键词
OpenPose算法/YOLOv5算法/深度学习/滑雪动作分析/损失函数
Key words
OpenPose/you only look Once version 5(YOLOv5)/deep learning/skiing movement analysis/loss function
维普
万方数据