No abstract

With the development of computer vision technology, human action pose recognition has gradually become a popular research direction, but there are still some problems in the application research based on pose recognition in sports action assisted evaluation. In this paper, the human motion pose recognition technology based on deep learning is introduced into this field to realize the intelligence of sports-assisted training. Firstly, we analyze the advantages and limitations of the state-of-the-art human motion pose recognition algorithms in computer vision in specific fields. On this basis, a human motion space recognition method based on periscope neural network is proposed. Firstly, the classical radar signal processing method is used to preprocess the echo signal of human spatial position and generate the frequency image in the process of human spatial position. Then, the periscope neural network (CNN) is constructed, and the time-frequency image is used as the input data of CNN to train the network parameters. Finally, the method is tested by using the open dataset in the network. The experimental results show that the designed CNN can accurately identify four different types of physical motion, and the accuracy coefficient is at least 97%.

Sports dance is a competition project and a kind of sports, with the characteristics of being smooth, generous, leisurely, and comfortable, dance steps, smooth movements, and flowing clouds, and it can give full play to the indoor space. In the light of the new era, sports dance is also playing an increasingly important role. Through the time series data and feature analysis of dance sports movements through machine learning, the internal information is mined to find the trends and laws. Machine learning in the era of big data is widely used in research as the main tool for data analysis and mining. The key difficulty of data mining has always been time series data. Machine learning refers to a method of using the resulting data in a computer to derive a certain model and then using this model to make predictions. The core is “using algorithms to parse data, learn from it, and then make decisions or predictions about new data.”

The detection and tracking of athletes in sports videos is of great importance, as it helps to automate the analysis of sports videos, thus providing advanced tools and instruments for sports training. The Cam Shift algorithm uses the colour information of objects to achieve tracking of moving targets, so it is very important to choose a suitable colour space when obtaining the colour information of objects. To this end, this paper improves the Cam Shift algorithm by converting the visual system mechanism to perceive the colour characteristics of the image processing, i.e., converting the video image from the RGB colour space to the HSV colour space, using the H (hue) component to model the target object. Experiments show that the improved athlete detection and tracking algorithm is more robust in practical applications. The improved tracking algorithm also has better real-time performance, with a processing speed of 20 fps during the experiments.