Hierarchical Activity Recognition Using Smart Watches and RGB-Depth Cameras
Human activity recognition is important for healthcare and lifestyle evaluation. In this paper, a novel method for activity recognition by jointly considering motion sensor data recorded by wearable smart watches and image data captured by RGB-Depth (RGB-D) cameras is presented. A normalized cross c...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/10/1713 |
| _version_ | 1811303572858470400 |
|---|---|
| author | Zhen Li Zhiqiang Wei Lei Huang Shugang Zhang Jie Nie |
| author_facet | Zhen Li Zhiqiang Wei Lei Huang Shugang Zhang Jie Nie |
| author_sort | Zhen Li |
| collection | DOAJ |
| description | Human activity recognition is important for healthcare and lifestyle evaluation. In this paper, a novel method for activity recognition by jointly considering motion sensor data recorded by wearable smart watches and image data captured by RGB-Depth (RGB-D) cameras is presented. A normalized cross correlation based mapping method is implemented to establish association between motion sensor data with corresponding image data from the same person in multi-person situations. Further, to improve the performance and accuracy of recognition, a hierarchical structure embedded with an automatic group selection method is proposed. Through this method, if the number of activities to be classified is changed, the structure will be changed correspondingly without interaction. Our comparative experiments against the single data source and single layer methods have shown that our method is more accurate and robust. |
| first_indexed | 2024-04-13T07:50:29Z |
| format | Article |
| id | doaj.art-81b96e42957745abb782c15812880150 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T07:50:29Z |
| publishDate | 2016-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-81b96e42957745abb782c158128801502022-12-22T02:55:33ZengMDPI AGSensors1424-82202016-10-011610171310.3390/s16101713s16101713Hierarchical Activity Recognition Using Smart Watches and RGB-Depth CamerasZhen Li0Zhiqiang Wei1Lei Huang2Shugang Zhang3Jie Nie4College of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaCollege of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaCollege of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaCollege of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaDepartment of Computer Science and Technology, Tsinghua University, Beijing 100084, ChinaHuman activity recognition is important for healthcare and lifestyle evaluation. In this paper, a novel method for activity recognition by jointly considering motion sensor data recorded by wearable smart watches and image data captured by RGB-Depth (RGB-D) cameras is presented. A normalized cross correlation based mapping method is implemented to establish association between motion sensor data with corresponding image data from the same person in multi-person situations. Further, to improve the performance and accuracy of recognition, a hierarchical structure embedded with an automatic group selection method is proposed. Through this method, if the number of activities to be classified is changed, the structure will be changed correspondingly without interaction. Our comparative experiments against the single data source and single layer methods have shown that our method is more accurate and robust.http://www.mdpi.com/1424-8220/16/10/1713activity recognitionwearable deviceRGB-Dhierarchical structure |
| spellingShingle | Zhen Li Zhiqiang Wei Lei Huang Shugang Zhang Jie Nie Hierarchical Activity Recognition Using Smart Watches and RGB-Depth Cameras Sensors activity recognition wearable device RGB-D hierarchical structure |
| title | Hierarchical Activity Recognition Using Smart Watches and RGB-Depth Cameras |
| title_full | Hierarchical Activity Recognition Using Smart Watches and RGB-Depth Cameras |
| title_fullStr | Hierarchical Activity Recognition Using Smart Watches and RGB-Depth Cameras |
| title_full_unstemmed | Hierarchical Activity Recognition Using Smart Watches and RGB-Depth Cameras |
| title_short | Hierarchical Activity Recognition Using Smart Watches and RGB-Depth Cameras |
| title_sort | hierarchical activity recognition using smart watches and rgb depth cameras |
| topic | activity recognition wearable device RGB-D hierarchical structure |
| url | http://www.mdpi.com/1424-8220/16/10/1713 |
| work_keys_str_mv | AT zhenli hierarchicalactivityrecognitionusingsmartwatchesandrgbdepthcameras AT zhiqiangwei hierarchicalactivityrecognitionusingsmartwatchesandrgbdepthcameras AT leihuang hierarchicalactivityrecognitionusingsmartwatchesandrgbdepthcameras AT shugangzhang hierarchicalactivityrecognitionusingsmartwatchesandrgbdepthcameras AT jienie hierarchicalactivityrecognitionusingsmartwatchesandrgbdepthcameras |