A Study of Dance Movement Capture and Posture Recognition Method Based on Vision Sensors
With the development of technology, posture recognition methods have been applied in more and more fields. However, there is relatively little research on posture recognition in dance. Therefore, this paper studied the capture and posture recognition of dance movements to understand the usability of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ital Publication
2023-06-01
|
| Series: | HighTech and Innovation Journal |
| Subjects: | |
| Online Access: | https://hightechjournal.org/index.php/HIJ/article/view/390 |
| _version_ | 1797643559999897600 |
|---|---|
| author | Qun Wang Gang Tong Sichao Zhou |
| author_facet | Qun Wang Gang Tong Sichao Zhou |
| author_sort | Qun Wang |
| collection | DOAJ |
| description | With the development of technology, posture recognition methods have been applied in more and more fields. However, there is relatively little research on posture recognition in dance. Therefore, this paper studied the capture and posture recognition of dance movements to understand the usability of the proposed method in dance posture recognition. Firstly, the Kinect V2 visual sensor was used to capture dance movements and obtain human skeletal joint data. Then, a three-dimensional convolutional neural network (3D CNN) model was designed by fusing joint coordinate features with joint velocity features as general features for recognizing different dance postures. Through experiments on NTU60 and self-built dance datasets, it was found that the 3D CNN performed best with a dropout rate of 0.4, a ReLU activation function, and fusion features. Compared to other posture recognition methods, the recognition rates of the 3D CNN on CS and CV in NTU60 were 88.8% and 95.3%, respectively, while the average recognition rate on the dance dataset reached 98.72%, which was higher than others. The experimental results demonstrate the effectiveness of our proposed method for dance posture recognition, providing a new approach for posture recognition research and making contributions to the inheritance of folk dances.
Doi: 10.28991/HIJ-2023-04-02-03
Full Text: PDF |
| first_indexed | 2024-03-11T14:16:40Z |
| format | Article |
| id | doaj.art-e599f947c85b49b283d5b063d51fb639 |
| institution | Directory Open Access Journal |
| issn | 2723-9535 |
| language | English |
| last_indexed | 2024-03-11T14:16:40Z |
| publishDate | 2023-06-01 |
| publisher | Ital Publication |
| record_format | Article |
| series | HighTech and Innovation Journal |
| spelling | doaj.art-e599f947c85b49b283d5b063d51fb6392023-11-01T06:08:24ZengItal PublicationHighTech and Innovation Journal2723-95352023-06-014228329310.28991/HIJ-2023-04-02-03120A Study of Dance Movement Capture and Posture Recognition Method Based on Vision SensorsQun Wang0Gang Tong1Sichao Zhou2Department of Sports and Arts, Hebei Sport University, Shijiazhuang, Hebei 050041,Department of Sports and Arts, Hebei Sport University, Shijiazhuang, Hebei 050041,Department of Sports and Arts, Hebei Sport University, Shijiazhuang, Hebei 050041,With the development of technology, posture recognition methods have been applied in more and more fields. However, there is relatively little research on posture recognition in dance. Therefore, this paper studied the capture and posture recognition of dance movements to understand the usability of the proposed method in dance posture recognition. Firstly, the Kinect V2 visual sensor was used to capture dance movements and obtain human skeletal joint data. Then, a three-dimensional convolutional neural network (3D CNN) model was designed by fusing joint coordinate features with joint velocity features as general features for recognizing different dance postures. Through experiments on NTU60 and self-built dance datasets, it was found that the 3D CNN performed best with a dropout rate of 0.4, a ReLU activation function, and fusion features. Compared to other posture recognition methods, the recognition rates of the 3D CNN on CS and CV in NTU60 were 88.8% and 95.3%, respectively, while the average recognition rate on the dance dataset reached 98.72%, which was higher than others. The experimental results demonstrate the effectiveness of our proposed method for dance posture recognition, providing a new approach for posture recognition research and making contributions to the inheritance of folk dances. Doi: 10.28991/HIJ-2023-04-02-03 Full Text: PDFhttps://hightechjournal.org/index.php/HIJ/article/view/390vision sensordancemovement capturegesture recognitionkinect v2. |
| spellingShingle | Qun Wang Gang Tong Sichao Zhou A Study of Dance Movement Capture and Posture Recognition Method Based on Vision Sensors HighTech and Innovation Journal vision sensor dance movement capture gesture recognition kinect v2. |
| title | A Study of Dance Movement Capture and Posture Recognition Method Based on Vision Sensors |
| title_full | A Study of Dance Movement Capture and Posture Recognition Method Based on Vision Sensors |
| title_fullStr | A Study of Dance Movement Capture and Posture Recognition Method Based on Vision Sensors |
| title_full_unstemmed | A Study of Dance Movement Capture and Posture Recognition Method Based on Vision Sensors |
| title_short | A Study of Dance Movement Capture and Posture Recognition Method Based on Vision Sensors |
| title_sort | study of dance movement capture and posture recognition method based on vision sensors |
| topic | vision sensor dance movement capture gesture recognition kinect v2. |
| url | https://hightechjournal.org/index.php/HIJ/article/view/390 |
| work_keys_str_mv | AT qunwang astudyofdancemovementcaptureandposturerecognitionmethodbasedonvisionsensors AT gangtong astudyofdancemovementcaptureandposturerecognitionmethodbasedonvisionsensors AT sichaozhou astudyofdancemovementcaptureandposturerecognitionmethodbasedonvisionsensors AT qunwang studyofdancemovementcaptureandposturerecognitionmethodbasedonvisionsensors AT gangtong studyofdancemovementcaptureandposturerecognitionmethodbasedonvisionsensors AT sichaozhou studyofdancemovementcaptureandposturerecognitionmethodbasedonvisionsensors |