Lixin Liang's research while affiliated with North China Electric Power University and other places

The public sports culture of colleges is based on the basic skills and strategies of the public sports culture curriculum. The study of public sports culture in colleges focuses on the unity and standardization of teaching forms, structures, contents, methods, assessments, and evaluations. This paper considers the various links that affect the public sports culture of colleges, identifies frequent item sets, and gains support by establishing support and confidence thresholds. The frequent item sets of the degrees and confidence with the rules generated by a decision tree algorithm are compared to identify the key factors that affect the actual effect. This paper fully considers the public sports culture of colleges to comprehensively analyze the relevant factors, verify and compare the rules generated by the decision tree algorithm, and identify the key factors that affect the actual effect. By an example verification, the method of this paper has certain guiding value for the study of public sports culture.

The analysis of moving objects in videos, especially the recognition of human motions and gestures, is attracting increasing emphasis in computer vision area. However, most existing video analysis methods do not take into account the effect of video semantic information. The topological information of the video image plays an important role in describing the association relationship of the image content, which will help to improve the discriminability of the video feature expression. Based on the above considerations, we propose a video semantic feature learning method that integrates image topological sparse coding with dynamic time warping algorithm to improve the gesture recognition in videos. This method divides video feature learning into two phases: semi-supervised video image feature learning and supervised optimization of video sequence features. Next, a distance weighting based dynamic time warping algorithm and K-nearest neighbor algorithm is leveraged to recognize gestures. We conduct comparative experiments on table tennis video dataset. The experimental results show that the proposed method is more discriminative to the expression of video features and can effectively improve the recognition rate of gestures in sports video.