Synchronized Data Collection for Human Group Recognition
It is commonplace for people to perform various kinds of activities in groups. The recognition of human groups is of importance in many applications including crowd evacuation, teamwork coordination, and advertising. Existing group recognition approaches require snapshots of human trajectories, whic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/21/7094 |
| _version_ | 1797511821148553216 |
|---|---|
| author | Weiping Zhu Lin Xu Yijie Tang Rong Xie |
| author_facet | Weiping Zhu Lin Xu Yijie Tang Rong Xie |
| author_sort | Weiping Zhu |
| collection | DOAJ |
| description | It is commonplace for people to perform various kinds of activities in groups. The recognition of human groups is of importance in many applications including crowd evacuation, teamwork coordination, and advertising. Existing group recognition approaches require snapshots of human trajectories, which is often impossible in the reality due to different data collection start time and frequency, and the inherent time deviations of devices. This study proposes an approach to synchronize the data of people for group recognition. All people’s trajectory data are aligned by using data interpolating. The optimal interpolating points are computed based on our proposed error function. Moreover, the time deviations among devices are estimated and eliminated by message passing. A real-life data set is used to validate the effectiveness of the proposed approach. The results show that 97.7% accuracy of group recognition can be achieved. The approach proposed to deal with time deviations was also proven to lead to better performance compared to that of the existing approaches. |
| first_indexed | 2024-03-10T05:53:26Z |
| format | Article |
| id | doaj.art-ee2a0a9ff6ca4a98ba24dcf097595a62 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:53:26Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ee2a0a9ff6ca4a98ba24dcf097595a622023-11-22T21:36:29ZengMDPI AGSensors1424-82202021-10-012121709410.3390/s21217094Synchronized Data Collection for Human Group RecognitionWeiping Zhu0Lin Xu1Yijie Tang2Rong Xie3School of Computer Science, Wuhan University, Wuhan 430072, ChinaSchool of Computer Science, Wuhan University, Wuhan 430072, ChinaSchool of Computer Science, Wuhan University, Wuhan 430072, ChinaSchool of Computer Science, Wuhan University, Wuhan 430072, ChinaIt is commonplace for people to perform various kinds of activities in groups. The recognition of human groups is of importance in many applications including crowd evacuation, teamwork coordination, and advertising. Existing group recognition approaches require snapshots of human trajectories, which is often impossible in the reality due to different data collection start time and frequency, and the inherent time deviations of devices. This study proposes an approach to synchronize the data of people for group recognition. All people’s trajectory data are aligned by using data interpolating. The optimal interpolating points are computed based on our proposed error function. Moreover, the time deviations among devices are estimated and eliminated by message passing. A real-life data set is used to validate the effectiveness of the proposed approach. The results show that 97.7% accuracy of group recognition can be achieved. The approach proposed to deal with time deviations was also proven to lead to better performance compared to that of the existing approaches.https://www.mdpi.com/1424-8220/21/21/7094group recognitionsynchronizationtrajectory interpolationmessage passing |
| spellingShingle | Weiping Zhu Lin Xu Yijie Tang Rong Xie Synchronized Data Collection for Human Group Recognition Sensors group recognition synchronization trajectory interpolation message passing |
| title | Synchronized Data Collection for Human Group Recognition |
| title_full | Synchronized Data Collection for Human Group Recognition |
| title_fullStr | Synchronized Data Collection for Human Group Recognition |
| title_full_unstemmed | Synchronized Data Collection for Human Group Recognition |
| title_short | Synchronized Data Collection for Human Group Recognition |
| title_sort | synchronized data collection for human group recognition |
| topic | group recognition synchronization trajectory interpolation message passing |
| url | https://www.mdpi.com/1424-8220/21/21/7094 |
| work_keys_str_mv | AT weipingzhu synchronizeddatacollectionforhumangrouprecognition AT linxu synchronizeddatacollectionforhumangrouprecognition AT yijietang synchronizeddatacollectionforhumangrouprecognition AT rongxie synchronizeddatacollectionforhumangrouprecognition |