In sports, the essence of a complete technical action is a complete information structure pattern and the athlete’s judgment of the action is actually the identification of the movement information structure pattern. Action recognition refers to the ability of the human brain to distinguish a perceived action from other actions and obtain predictive response information when it identifies and confirms it according to the constantly changing motion information on the field. Action recognition mainly includes two aspects: one is to obtain the required action information based on visual observation and the other is to judge the action based on the obtained action information, but the neuropsychological mechanism of this process is still unknown. In this paper, a new key frame extraction method based on the clustering algorithm and multifeature fusion is proposed for sports videos with complex content, many scenes, and rich actions. First, a variety of features are fused, and then, similarity measurement can be used to describe videos with complex content more completely and comprehensively; second, a clustering algorithm is used to cluster sports video sequences according to scenes, eliminating the need for shots in the case of many scenes. It is difficult and complicated to detect segmentation; third, extracting key frames according to the minimum motion standard can more accurately represent the video content with rich actions. At the same time, the clustering algorithm used in this paper is improved to enhance the offline computing efficiency of the key frame extraction system. Based on the analysis of the advantages and disadvantages of the classical convolutional neural network and recurrent neural network algorithms in deep learning, this paper proposes an improved convolutional network and optimization based on the recognition and analysis of human actions under complex scenes, complex actions, and fast motion compared to post-neural network and hybrid neural network algorithm. Experiments show that the algorithm achieves similar human observation of athletes’ training execution and completion. Compared with other algorithms, it has been verified that it has very high learning rate and accuracy for the athlete’s action recognition.

In sports, kinematic image analysis is primarily concerned with the examination of space-time characteristics, such as image analysis of the speed and acceleration of related objects. Software and hardware make up the entire system. The medical scanner, scanning workstation, and DICOM server are all part of the hardware. Our self-developed scanner is used in the medical scanner, which can collect binary, 8-bit gray, 24-bit true color, 16-bit gray, and 48-bit color images. Kinematic image analysis is used to intuitively analyze sports technology, as well as to evaluate and diagnose its rationality. This paper investigates the kinematic-based framework design of a sports image analysis system. Image analyses of displacement, speed, and time are all used in the measurement of sports technology evaluation. Displacement analysis, for example, involves position coordinates, motion displacement, motion trajectory, and so on; speed class analysis, on the other hand, involves average and maximum speed.