Research of dynamic gesture recognition based on multi-instance learning of kinematics features
Compared to static gestures,dynamic gestures had some new characteristics.The problems of dynamic gestures recognition was spewed by using kinematics mode,such as divergence modes,curl modes,symmetric and ant-symmetric modes,the second and third principal invariant modes of the gradient tensor,the s...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2017-11-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2017211/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539498278649856 |
|---|---|
| author | Cai-qiu ZHOU Yu-wang YANG Hai-bo PANG |
| author_facet | Cai-qiu ZHOU Yu-wang YANG Hai-bo PANG |
| author_sort | Cai-qiu ZHOU |
| collection | DOAJ |
| description | Compared to static gestures,dynamic gestures had some new characteristics.The problems of dynamic gestures recognition was spewed by using kinematics mode,such as divergence modes,curl modes,symmetric and ant-symmetric modes,the second and third principal invariant modes of the gradient tensor,the second and third principal invariant modes of the strain tensor and the third principal invariant modes of spin tensor; Further,a framework based on multi-instance learning was proposed,organize all these principle modes for each gesture were organized to a dynamic gestures bag-of-words,and the similarity between the mode of unknown type dynamic gestures and the all bag-of-words were calculated.Then,the nearest neighbor method was used to recognize the dynamic gestures.The experimental results show that the dynamic gestures recognition based on multi-instance kinematics features principal mode learning methods can obtain a higher recognition rate. |
| format | Article |
| id | doaj-art-440f887e4ddc427d801550b01b7517c7 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2017-11-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-440f887e4ddc427d801550b01b7517c72025-01-14T07:13:21ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2017-11-013810311059713406Research of dynamic gesture recognition based on multi-instance learning of kinematics featuresCai-qiu ZHOUYu-wang YANGHai-bo PANGCompared to static gestures,dynamic gestures had some new characteristics.The problems of dynamic gestures recognition was spewed by using kinematics mode,such as divergence modes,curl modes,symmetric and ant-symmetric modes,the second and third principal invariant modes of the gradient tensor,the second and third principal invariant modes of the strain tensor and the third principal invariant modes of spin tensor; Further,a framework based on multi-instance learning was proposed,organize all these principle modes for each gesture were organized to a dynamic gestures bag-of-words,and the similarity between the mode of unknown type dynamic gestures and the all bag-of-words were calculated.Then,the nearest neighbor method was used to recognize the dynamic gestures.The experimental results show that the dynamic gestures recognition based on multi-instance kinematics features principal mode learning methods can obtain a higher recognition rate.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2017211/gesture recognitionkinematics featurestemporal axis dimension reductionmulti-instance learning |
| spellingShingle | Cai-qiu ZHOU Yu-wang YANG Hai-bo PANG Research of dynamic gesture recognition based on multi-instance learning of kinematics features Tongxin xuebao gesture recognition kinematics features temporal axis dimension reduction multi-instance learning |
| title | Research of dynamic gesture recognition based on multi-instance learning of kinematics features |
| title_full | Research of dynamic gesture recognition based on multi-instance learning of kinematics features |
| title_fullStr | Research of dynamic gesture recognition based on multi-instance learning of kinematics features |
| title_full_unstemmed | Research of dynamic gesture recognition based on multi-instance learning of kinematics features |
| title_short | Research of dynamic gesture recognition based on multi-instance learning of kinematics features |
| title_sort | research of dynamic gesture recognition based on multi instance learning of kinematics features |
| topic | gesture recognition kinematics features temporal axis dimension reduction multi-instance learning |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2017211/ |
| work_keys_str_mv | AT caiqiuzhou researchofdynamicgesturerecognitionbasedonmultiinstancelearningofkinematicsfeatures AT yuwangyang researchofdynamicgesturerecognitionbasedonmultiinstancelearningofkinematicsfeatures AT haibopang researchofdynamicgesturerecognitionbasedonmultiinstancelearningofkinematicsfeatures |