sis 18: e24

Research Article

Basketball posture recognition based on HOG feature extraction and convolutional neural network

Download756 downloads
  • @ARTICLE{10.4108/eai.5-1-2022.172784,
        author={Jian Gao},
        title={Basketball posture recognition based on HOG feature extraction and convolutional neural network},
        journal={EAI Endorsed Transactions on Scalable Information Systems: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={SIS},
        year={2022},
        month={1},
        keywords={Basketball posture recognition, HOG, convolutional neural network},
        doi={10.4108/eai.5-1-2022.172784}
    }
    
  • Jian Gao
    Year: 2022
    Basketball posture recognition based on HOG feature extraction and convolutional neural network
    SIS
    EAI
    DOI: 10.4108/eai.5-1-2022.172784
Jian Gao1,2,*
  • 1: Physical College, Zhengzhou University of Industrial Technology.
  • 2: No.16, Xueyuan Road, Zhengzhou City, Henan Province, 451150, China
*Contact email: 910675024@qq.com

Abstract

This article has been retracted, and the retraction notice can be found here: http://dx.doi.org/10.4108/eai.8-4-2022.173787. Basketball posture recognition is one of the important research topics in human-computer interaction and physical education, which is of great significance in medical treatment, sports, security and other aspects. With the development of machine learning, the application value of basketball pose recognition in physical education is becoming more and more extensive. This paper constructs a novel convolutional neural network model to recognize basketball posture. The model consists of 11 layers. Convolution and pooling operations are carried out for five basketball postures in the sampled data set. By fusing with the features extracted from HOG, finer features can be obtained. Finally, the data set is trained and recognized by entering the full connection layer for classification. The results show that compared with the traditional machine learning methods, the recognition performance of new model is better.