Nigade, Vinod ; Winder, Ramon ; Bal, Henri ; Wang, Lin (2021)
Better Never Than Late: Timely Edge Video Analytics Over the Air.
19th ACM Conference on Embedded Networked Sensor Systems. Coimbra, Portugal (15.11.2021-17.11.2021)
doi: 10.1145/3485730.3493446
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Edge video analytics based on deep learning has become an important building block for many modern intelligent applications such as mobile augmented reality and autonomous driving. Various mechanisms have been developed to handle dynamic wireless networks, compute resource availability, and achieve high analytics accuracy via filtering, DNN compression, pruning, and adaptation. So far, limited attention has been paid to timeliness---providing strict service-level objectives (SLO) for edge video analytics pipelines, which is essential for the usability of user-interactive and mission-critical intelligent applications. In this paper, we analyze the challenges in achieving SLO for edge video analytics and present a system design for timely edge video analytics over the air leveraging a simple yet effective idea---feedback control. Our preliminary evaluation based on a system prototype and real-world network traces shows the potential of our design. We also discuss the limitations, calling for future work.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2021 |
| Autor(en): | Nigade, Vinod ; Winder, Ramon ; Bal, Henri ; Wang, Lin |
| Art des Eintrags: | Bibliographie |
| Titel: | Better Never Than Late: Timely Edge Video Analytics Over the Air |
| Sprache: | Englisch |
| Publikationsjahr: | 15 November 2021 |
| Verlag: | ACM |
| Buchtitel: | SenSys '21: Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems |
| Veranstaltungstitel: | 19th ACM Conference on Embedded Networked Sensor Systems |
| Veranstaltungsort: | Coimbra, Portugal |
| Veranstaltungsdatum: | 15.11.2021-17.11.2021 |
| DOI: | 10.1145/3485730.3493446 |
| Kurzbeschreibung (Abstract): | Edge video analytics based on deep learning has become an important building block for many modern intelligent applications such as mobile augmented reality and autonomous driving. Various mechanisms have been developed to handle dynamic wireless networks, compute resource availability, and achieve high analytics accuracy via filtering, DNN compression, pruning, and adaptation. So far, limited attention has been paid to timeliness---providing strict service-level objectives (SLO) for edge video analytics pipelines, which is essential for the usability of user-interactive and mission-critical intelligent applications. In this paper, we analyze the challenges in achieving SLO for edge video analytics and present a system design for timely edge video analytics over the air leveraging a simple yet effective idea---feedback control. Our preliminary evaluation based on a system prototype and real-world network traces shows the potential of our design. We also discuss the limitations, calling for future work. |
| Freie Schlagworte: | SLO guarantee, edge computing, video analytics |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Telekooperation DFG-Sonderforschungsbereiche (inkl. Transregio) DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet > B: Adaptionsmechanismen DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet > B: Adaptionsmechanismen > Teilprojekt B2: Koordination und Ausführung |
| Hinterlegungsdatum: | 21 Apr 2022 07:41 |
| Letzte Änderung: | 21 Apr 2022 07:41 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum