Zhang Liangliang
Academy of Sports and Leisure, Xi'an Physical Education University, Xi'an, China.
Front Neurorobot. 2022 May 20;16:860981. doi: 10.3389/fnbot.2022.860981. eCollection 2022.
The exploration here intends to compensate for the traditional human motion recognition (HMR) systems' poor performance on large-scale datasets and micromotions. To this end, improvement is designed for the HMR in sports competition based on the deep learning (DL) algorithm. First, the background and research status of HMR are introduced. Then, a new HMR algorithm is proposed based on kernel extreme learning machine (KELM) multidimensional feature fusion (MFF). Afterward, a simulation experiment is designed to evaluate the performance of the proposed KELM-MFF-based HMR algorithm. The results showed that the recognition rate of the proposed KELM-MFF-based HMR is higher than other algorithms. The recognition rate at 10 video frame sampling points is ranked from high to low: the proposed KELM-MFF-based HMR, support vector machine (SVM)-MFF-based HMR, convolutional neural network (CNN) + optical flow (CNN-T)-based HMR, improved dense trajectory (IDT)-based HMR, converse3D (C3D)-based HMR, and CNN-based HMR. Meanwhile, the feature recognition rate of the proposed KELM-MFF-based HMR for the color dimension is higher than the time dimension, by up to 24%. Besides, the proposed KELM-MFF-based HMR algorithm's recognition rate is 92.4% under early feature fusion and 92.1% under late feature fusion, higher than 91.8 and 90.5% of the SVM-MFF-based HMR. Finally, the proposed KELM-MFF-based HMR algorithm takes 30 and 15 s for training and testing. Therefore, the algorithm designed here can be used to deal with large-scale datasets and capture and recognize micromotions. The research content provides a reference for applying extreme learning machine algorithms in sports competitions.
此处的探索旨在弥补传统人体运动识别（HMR）系统在大规模数据集和微观运动方面的不佳表现。为此，基于深度学习（DL）算法对体育竞赛中的HMR进行了改进设计。首先，介绍了HMR的背景和研究现状。然后，提出了一种基于核极限学习机（KELM）多维特征融合（MFF）的新型HMR算法。随后，设计了一个仿真实验来评估所提出的基于KELM-MFF的HMR算法的性能。结果表明，所提出的基于KELM-MFF的HMR的识别率高于其他算法。在10个视频帧采样点处的识别率从高到低依次为：所提出的基于KELM-MFF的HMR、基于支持向量机（SVM）-MFF的HMR、基于卷积神经网络（CNN）+光流（CNN-T）的HMR、基于改进密集轨迹（IDT）的HMR、基于Converse3D（C3D）的HMR和基于CNN的HMR。同时，所提出的基于KELM-MFF的HMR对颜色维度的特征识别率高于时间维度，最高可达24%。此外，所提出的基于KELM-MFF的HMR算法在早期特征融合下的识别率为92.4%，在晚期特征融合下为92.1%，高于基于SVM-MFF的HMR的91.8%和90.5%。最后，所提出的基于KELM-MFF的HMR算法训练和测试分别耗时30秒和15秒。因此，此处设计的算法可用于处理大规模数据集并捕捉和识别微观运动。该研究内容为极限学习机算法在体育竞赛中的应用提供了参考。
