DC Field | Value | Language |
---|---|---|
dc.contributor.author | Nguyen, Thanh-Tung | ko |
dc.contributor.author | Lee, Dongman | ko |
dc.contributor.author | Jang, SiYoung | ko |
dc.contributor.author | Kostadinov, Boyan | ko |
dc.date.accessioned | 2023-11-17T06:00:46Z | - |
dc.date.available | 2023-11-17T06:00:46Z | - |
dc.date.created | 2023-11-17 | - |
dc.date.issued | 2023-03 | - |
dc.identifier.citation | 21st IEEE International Conference on Pervasive Computing and Communications, PerCom 2023, pp.101 - 110 | - |
dc.identifier.issn | 2474-2503 | - |
dc.identifier.uri | http://hdl.handle.net/10203/314805 | - |
dc.description.abstract | Cross-camera real-Time object tracking is one of the important, yet challenging applications of video analytics in edge computing environments. To provide accurate and efficient real-Time tracking, a tracking target's future movements need to be predicted. Particularly, the destination camera and travel time of the target object are to be identified so that tracking duties can be handover-ed seamlessly. In this paper, we propose a collaborative cross-camera tracking system, called PreActo, with two key features: (1) ResNet-based trajectory learning to exploit the rich spatio-Temporal information embedded within objects' moving patterns, which has not been utilized by the existing literature, and (2) collaboration between the edge server and the edge device for real-Time trajectory prediction and tracking handover. To prove the validity of our proposed system, we evaluate PreActo on a video dataset leveraging real-world trajectories. Evaluation results show that the proposed system reduces up to 7 the number of processed frames for handover, with 2 lower latency while providing 1.5 tracking precision improvement compared to the state-of-The-Art. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | PreActo: Efficient Cross-Camera Object Tracking System in Video Analytic Edge Computing | - |
dc.type | Conference | - |
dc.identifier.wosid | 000987122700011 | - |
dc.identifier.scopusid | 2-s2.0-85158031958 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 101 | - |
dc.citation.endingpage | 110 | - |
dc.citation.publicationname | 21st IEEE International Conference on Pervasive Computing and Communications, PerCom 2023 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Atlanta, GA | - |
dc.identifier.doi | 10.1109/PERCOM56429.2023.10099298 | - |
dc.contributor.localauthor | Lee, Dongman | - |
dc.contributor.nonIdAuthor | Kostadinov, Boyan | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.