Basketball Action Recognition Method of Deep Neural Network Based on Dynamic Residual Attention Mechanism
Aiming at the problem that the features extracted from the original C3D (Convolutional 3D) convolutional neural network(C3D) were insufficient, and it was difficult to focus on keyframes, which led to the low accuracy of basketball players’ action recognition; hence, a basketball action recognition...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/1/13 |
| _version_ | 1827624780831916032 |
|---|---|
| author | Jiongen Xiao Wenchun Tian Liping Ding |
| author_facet | Jiongen Xiao Wenchun Tian Liping Ding |
| author_sort | Jiongen Xiao |
| collection | DOAJ |
| description | Aiming at the problem that the features extracted from the original C3D (Convolutional 3D) convolutional neural network(C3D) were insufficient, and it was difficult to focus on keyframes, which led to the low accuracy of basketball players’ action recognition; hence, a basketball action recognition method of deep neural network based on dynamic residual attention mechanism was proposed. Firstly, the traditional C3D is improved to a dynamic residual convolution network to extract sufficient feature information. Secondly, the extracted feature information is selected by the improved attention mechanism to obtain the key video frames. Finally, the algorithm is compared with the traditional C3D in order to demonstrate the advance and applicability of the algorithm. Experimental results show that this method can effectively recognize basketball posture, and the average accuracy of posture recognition is more than 97%. |
| first_indexed | 2024-03-09T12:16:27Z |
| format | Article |
| id | doaj.art-0dfaae1c1a224b33b3c57cd2c50dac67 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-09T12:16:27Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-0dfaae1c1a224b33b3c57cd2c50dac672023-11-30T22:46:03ZengMDPI AGInformation2078-24892022-12-011411310.3390/info14010013Basketball Action Recognition Method of Deep Neural Network Based on Dynamic Residual Attention MechanismJiongen Xiao0Wenchun Tian1Liping Ding2International Business School, Guangdong University of Finance and Economics, Guangzhou 510320, ChinaSchool of Electrical and Computer Engineering, Guangzhou Nanfang College, Guangzhou 510970, ChinaElectronic Forensics Laboratory, Guangzhou Institute of Software Application Technology, Guangzhou 511458, ChinaAiming at the problem that the features extracted from the original C3D (Convolutional 3D) convolutional neural network(C3D) were insufficient, and it was difficult to focus on keyframes, which led to the low accuracy of basketball players’ action recognition; hence, a basketball action recognition method of deep neural network based on dynamic residual attention mechanism was proposed. Firstly, the traditional C3D is improved to a dynamic residual convolution network to extract sufficient feature information. Secondly, the extracted feature information is selected by the improved attention mechanism to obtain the key video frames. Finally, the algorithm is compared with the traditional C3D in order to demonstrate the advance and applicability of the algorithm. Experimental results show that this method can effectively recognize basketball posture, and the average accuracy of posture recognition is more than 97%.https://www.mdpi.com/2078-2489/14/1/13behavior recognitiondeep learningC3D convolutionresidual networkattention mechanism |
| spellingShingle | Jiongen Xiao Wenchun Tian Liping Ding Basketball Action Recognition Method of Deep Neural Network Based on Dynamic Residual Attention Mechanism Information behavior recognition deep learning C3D convolution residual network attention mechanism |
| title | Basketball Action Recognition Method of Deep Neural Network Based on Dynamic Residual Attention Mechanism |
| title_full | Basketball Action Recognition Method of Deep Neural Network Based on Dynamic Residual Attention Mechanism |
| title_fullStr | Basketball Action Recognition Method of Deep Neural Network Based on Dynamic Residual Attention Mechanism |
| title_full_unstemmed | Basketball Action Recognition Method of Deep Neural Network Based on Dynamic Residual Attention Mechanism |
| title_short | Basketball Action Recognition Method of Deep Neural Network Based on Dynamic Residual Attention Mechanism |
| title_sort | basketball action recognition method of deep neural network based on dynamic residual attention mechanism |
| topic | behavior recognition deep learning C3D convolution residual network attention mechanism |
| url | https://www.mdpi.com/2078-2489/14/1/13 |
| work_keys_str_mv | AT jiongenxiao basketballactionrecognitionmethodofdeepneuralnetworkbasedondynamicresidualattentionmechanism AT wenchuntian basketballactionrecognitionmethodofdeepneuralnetworkbasedondynamicresidualattentionmechanism AT lipingding basketballactionrecognitionmethodofdeepneuralnetworkbasedondynamicresidualattentionmechanism |