Abstract
As a whole-body sport, skipping rope plays an increasingly important role in daily life. In rope-skipping education, due to the lack of professional teachers, the training efficiency of students is low. The rope-skipping monitoring device is heavy and expensive, and the cost of labor statistics and energy consumption are high. In order to quickly analyze the movement process of students and provide correct guidance, this article implements the movement analysis method of the human body movement process. The problem of limb posture analysis in rope skipping is transformed into a multilabel classification problem, a real-time human motion analysis method based on mobile vision is proposed, and the algorithm model is verified in the rope-skipping scene. The experimental results prove that this paper proposes the improved algorithm, which achieved the expected effect. In the analysis of rope-skipping action, the choice of hyperparameters during the experiment is introduced, and it is verified that the proposed ALSTM-LSTM can solve the problem of multilabel classification in the rope-skipping process. The accuracy rate reaches 95.1%, and it can provide the best in all indicators and good performance. It is of great significance for movement analysis and movement quality evaluation during exercise.
Highlights
In the study of human motion recognition, we apply a convolution neural network to it, choose a one-dimensional CNN + LSTM algorithm as the optimal algorithm, and select sensors that can support smart wearable devices, build a recognition network model, and process the collected data. is method can be used under any circumstances, and the cost is relatively low, which is mostly used in sports events [1]
In order to evaluate the performance of Bluetooth, especially the body area network (BAN) using magnetic inertial sensor units (M-IMUs) for human motion tracking, we propose a method for throughput performance in general sensor network applications [2]. e analysis of human motion is of great significance in the diagnosis of musculoskeletal diseases
We use micro-Doppler features measured by the radar to analyze human motion, but deep learning requires a huge amount of data and the cost is quite high. erefore, we have studied a more accurate method to improve the analysis, that is, to expand the mode of micro-Doppler data of human motion by generating countermeasure networks (GANs) [3]
Summary
In the study of human motion recognition, we apply a convolution neural network to it, choose a one-dimensional CNN + LSTM algorithm as the optimal algorithm, and select sensors that can support smart wearable devices, build a recognition network model, and process the collected data. is method can be used under any circumstances, and the cost is relatively low, which is mostly used in sports events [1]. Erefore, we have studied a more accurate method to improve the analysis, that is, to expand the mode of micro-Doppler data of human motion by generating countermeasure networks (GANs) [3]. Cyclic neural network (RNN) is one of the most widely used basic structures in deep learning. Because the cyclic neural network has a certain storage capacity, it can capture the information in data and learn the logical relationship between the data before and after, so RNN is often used to solve the problem of time series characteristics in data. A deep learning model including an RNN structure of Lee et al is used for human motion recognition [11, 12]. Cyclic neural networks are very sensitive to the temporal characteristics of sequential data, and models based on the RNN structure can be given priority [15]. There are 96 boys, 104 girls, and 52 girls. 80 people
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
