Demo: Distributed Real-Time Generative 3D Hand Tracking using Edge GPGPU Acceleration

Ammar Qammaz; Sokol Kosta; Nikolaos Kyriazis; Antonis Argyros

doi:10.1145/3210240.3211112

Demo: Distributed Real-Time Generative 3D Hand Tracking using Edge GPGPU Acceleration

Ammar Qammaz, Sokol Kosta, Nikolaos Kyriazis, Antonis Argyros

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

Abstrakt

This work demonstrates a real-time 3D hand tracking application that runs via computation offloading. The proposed framework enables the application to run on low-end mobile devices such as laptops and tablets, despite the fact that they lack the sufficient hardware to perform the required computations locally. The network connection takes the place of a GPGPU accelerator and sharing resources with a larger workstation becomes the acceleration mechanism. The unique properties of a generative optimizer are examined and constitute a challenging use-case, since the requirement for real-time performance makes it very latency-sensitive.

Originalsprog	Engelsk
Titel	MobiSys '18 - International Conference on Mobile Systems, Applications and Services
Antal sider	1
Udgivelses sted	Munich, Germany
Forlag	Association for Computing Machinery
Publikationsdato	10 jun. 2018
Sider	540-540
ISBN (Trykt)	978-1-4503-5720-3
ISBN (Elektronisk)	9781450357203
DOI	https://doi.org/10.1145/3210240.3211112
Status	Udgivet - 10 jun. 2018
Begivenhed	16th ACM International Conference on Mobile Systems, Applications, and Services - Munich, Tyskland Varighed: 10 jun. 2018 → 15 jun. 2018 https://www.sigmobile.org/mobisys/2018/

Konference

Konference	16th ACM International Conference on Mobile Systems, Applications, and Services
Land	Tyskland
By	Munich
Periode	10/06/2018 → 15/06/2018
Internetadresse	https://www.sigmobile.org/mobisys/2018/

Adgang til dokumentet

10.1145/3210240.3211112

http://www.scopus.com/inward/record.url?scp=85051537655&partnerID=8YFLogxK

Fingeraftryk Dyk ned i forskningsemnerne om 'Demo: Distributed Real-Time Generative 3D Hand Tracking using Edge GPGPU Acceleration'. Sammen danner de et unikt fingeraftryk.

Aktiviteter

1 Organisering af eller deltagelse i konference
1 Konferenceoplæg

Demo: Distributed Real-Time Generative 3D Hand Tracking using Edge GPGPU Acceleration

Sokol Kosta (Foredragsholder)

11 jun. 2018

Aktivitet: Foredrag og mundtlige bidrag › Konferenceoplæg

16th ACM International Conference on Mobile Systems, Applications, and Services

Sokol Kosta (Deltager)

9 jun. 2018 → 15 jun. 2018

Aktivitet: Deltagelse i faglig begivenhed › Organisering af eller deltagelse i konference

Citationsformater

Qammaz, A., Kosta, S., Kyriazis, N., & Argyros, A. (2018). Demo: Distributed Real-Time Generative 3D Hand Tracking using Edge GPGPU Acceleration. I MobiSys '18 - International Conference on Mobile Systems, Applications and Services (s. 540-540). Association for Computing Machinery. https://doi.org/10.1145/3210240.3211112

@inproceedings{52fb4831f37c43d8b171d859910cfbde,

title = "Demo: Distributed Real-Time Generative 3D Hand Tracking using Edge GPGPU Acceleration",

abstract = "This work demonstrates a real-time 3D hand tracking application that runs via computation offloading. The proposed framework enables the application to run on low-end mobile devices such as laptops and tablets, despite the fact that they lack the sufficient hardware to perform the required computations locally. The network connection takes the place of a GPGPU accelerator and sharing resources with a larger workstation becomes the acceleration mechanism. The unique properties of a generative optimizer are examined and constitute a challenging use-case, since the requirement for real-time performance makes it very latency-sensitive.",

author = "Ammar Qammaz and Sokol Kosta and Nikolaos Kyriazis and Antonis Argyros",

year = "2018",

month = jun,

day = "10",

doi = "10.1145/3210240.3211112",

language = "English",

isbn = "978-1-4503-5720-3",

pages = "540--540",

booktitle = "MobiSys '18 - International Conference on Mobile Systems, Applications and Services",

publisher = "Association for Computing Machinery",

address = "United States",

note = "16th ACM International Conference on Mobile Systems, Applications, and Services, MobiSys ; Conference date: 10-06-2018 Through 15-06-2018",

url = "https://www.sigmobile.org/mobisys/2018/",

}

Qammaz, A, Kosta, S, Kyriazis, N & Argyros, A 2018, Demo: Distributed Real-Time Generative 3D Hand Tracking using Edge GPGPU Acceleration. i MobiSys '18 - International Conference on Mobile Systems, Applications and Services. Association for Computing Machinery, Munich, Germany, s. 540-540, 16th ACM International Conference on Mobile Systems, Applications, and Services, Munich, Tyskland, 10/06/2018. https://doi.org/10.1145/3210240.3211112

Demo : Distributed Real-Time Generative 3D Hand Tracking using Edge GPGPU Acceleration. / Qammaz, Ammar; Kosta, Sokol; Kyriazis, Nikolaos; Argyros, Antonis.

MobiSys '18 - International Conference on Mobile Systems, Applications and Services. Munich, Germany : Association for Computing Machinery, 2018. s. 540-540.

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Demo

T2 - 16th ACM International Conference on Mobile Systems, Applications, and Services

AU - Qammaz, Ammar

AU - Kosta, Sokol

AU - Kyriazis, Nikolaos

AU - Argyros, Antonis

PY - 2018/6/10

Y1 - 2018/6/10

N2 - This work demonstrates a real-time 3D hand tracking application that runs via computation offloading. The proposed framework enables the application to run on low-end mobile devices such as laptops and tablets, despite the fact that they lack the sufficient hardware to perform the required computations locally. The network connection takes the place of a GPGPU accelerator and sharing resources with a larger workstation becomes the acceleration mechanism. The unique properties of a generative optimizer are examined and constitute a challenging use-case, since the requirement for real-time performance makes it very latency-sensitive.

AB - This work demonstrates a real-time 3D hand tracking application that runs via computation offloading. The proposed framework enables the application to run on low-end mobile devices such as laptops and tablets, despite the fact that they lack the sufficient hardware to perform the required computations locally. The network connection takes the place of a GPGPU accelerator and sharing resources with a larger workstation becomes the acceleration mechanism. The unique properties of a generative optimizer are examined and constitute a challenging use-case, since the requirement for real-time performance makes it very latency-sensitive.

UR - http://www.scopus.com/inward/record.url?scp=85051537655&partnerID=8YFLogxK

U2 - 10.1145/3210240.3211112

DO - 10.1145/3210240.3211112

M3 - Article in proceeding

SN - 978-1-4503-5720-3

SP - 540

EP - 540

BT - MobiSys '18 - International Conference on Mobile Systems, Applications and Services

PB - Association for Computing Machinery

CY - Munich, Germany

Y2 - 10 June 2018 through 15 June 2018

ER -