Motion Feature Retrieval in Basketball Match Video Based on Multisource Motion Feature Fusion
Both the human body and its motion are three-dimensional information, while the traditional feature description method of two-person interaction based on RGB video has a low degree of discrimination due to the lack of depth information. According to the respective advantages and complementary charac...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Advances in Mathematical Physics |
| Online Access: | http://dx.doi.org/10.1155/2022/9965764 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832567477109784576 |
|---|---|
| author | Biao Ma Minghui Ji |
| author_facet | Biao Ma Minghui Ji |
| author_sort | Biao Ma |
| collection | DOAJ |
| description | Both the human body and its motion are three-dimensional information, while the traditional feature description method of two-person interaction based on RGB video has a low degree of discrimination due to the lack of depth information. According to the respective advantages and complementary characteristics of RGB video and depth video, a retrieval algorithm based on multisource motion feature fusion is proposed. Firstly, the algorithm uses the combination of spatiotemporal interest points and word bag model to represent the features of RGB video. Then, the directional gradient histogram is used to represent the feature of the depth video frame. The statistical features of key frames are introduced to represent the histogram features of depth video. Finally, the multifeature image fusion algorithm is used to fuse the two video features. The experimental results show that multisource feature fusion can greatly improve the retrieval accuracy of motion features. |
| format | Article |
| id | doaj-art-c5863eaf1a944c418cd8a4ed7eb2e893 |
| institution | Kabale University |
| issn | 1687-9139 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Mathematical Physics |
| spelling | doaj-art-c5863eaf1a944c418cd8a4ed7eb2e8932025-02-03T01:01:29ZengWileyAdvances in Mathematical Physics1687-91392022-01-01202210.1155/2022/9965764Motion Feature Retrieval in Basketball Match Video Based on Multisource Motion Feature FusionBiao Ma0Minghui Ji1School of Physical EducationSchool of Physical EducationBoth the human body and its motion are three-dimensional information, while the traditional feature description method of two-person interaction based on RGB video has a low degree of discrimination due to the lack of depth information. According to the respective advantages and complementary characteristics of RGB video and depth video, a retrieval algorithm based on multisource motion feature fusion is proposed. Firstly, the algorithm uses the combination of spatiotemporal interest points and word bag model to represent the features of RGB video. Then, the directional gradient histogram is used to represent the feature of the depth video frame. The statistical features of key frames are introduced to represent the histogram features of depth video. Finally, the multifeature image fusion algorithm is used to fuse the two video features. The experimental results show that multisource feature fusion can greatly improve the retrieval accuracy of motion features.http://dx.doi.org/10.1155/2022/9965764 |
| spellingShingle | Biao Ma Minghui Ji Motion Feature Retrieval in Basketball Match Video Based on Multisource Motion Feature Fusion Advances in Mathematical Physics |
| title | Motion Feature Retrieval in Basketball Match Video Based on Multisource Motion Feature Fusion |
| title_full | Motion Feature Retrieval in Basketball Match Video Based on Multisource Motion Feature Fusion |
| title_fullStr | Motion Feature Retrieval in Basketball Match Video Based on Multisource Motion Feature Fusion |
| title_full_unstemmed | Motion Feature Retrieval in Basketball Match Video Based on Multisource Motion Feature Fusion |
| title_short | Motion Feature Retrieval in Basketball Match Video Based on Multisource Motion Feature Fusion |
| title_sort | motion feature retrieval in basketball match video based on multisource motion feature fusion |
| url | http://dx.doi.org/10.1155/2022/9965764 |
| work_keys_str_mv | AT biaoma motionfeatureretrievalinbasketballmatchvideobasedonmultisourcemotionfeaturefusion AT minghuiji motionfeatureretrievalinbasketballmatchvideobasedonmultisourcemotionfeaturefusion |