Demo: Edge-SLAM: Edge-Assisted visual simultaneous localization and mapping

Ali J. Ben Ali; Zakieh Sadat Hashemifar; Karthik Dantu

doi:10.1145/3372224.3417326

Demo: Edge-SLAM: Edge-Assisted visual simultaneous localization and mapping

Ali J. Ben Ali
, Zakieh Sadat Hashemifar
, Karthik Dantu

Department of Computer Science and Engineering

SUNY Buffalo

Research output: Contribution to conference › Paper › peer-review

2 Scopus citations

Abstract

The recent advances in mobile devices have allowed them to run spatial sensing algorithms such as Visual Simultaneous Localization and Mapping (Visual-SLAM). However, the resource requirements of Visual-SLAM prevents long-operation of such algorithm on mobile devices. We demonstrate Edge-SLAM [2], a system that adapts edge computing into Visual-SLAM through a split architecture. Edge-SLAM offloads the compute-intensive modules of Visual-SLAM to the edge without losing accuracy. Our experiments show that Edge-SLAM architecture reduces the use of computation and memory resources on mobile devices and keeps it constant. Thus, enabling long-operation of Visual-SLAM along with other applications services on mobile devices.

Original language	English
Pages	878-880
Number of pages	3
DOIs	https://doi.org/10.1145/3372224.3417326
State	Published - 2020
Event	26th Annual International Conference on Mobile Computing and Networking, MobiCom 2020 - London, United Kingdom Duration: Sep 21 2020 → Sep 25 2020

Conference

Conference	26th Annual International Conference on Mobile Computing and Networking, MobiCom 2020
Country/Territory	United Kingdom
City	London
Period	09/21/20 → 09/25/20

Keywords

edge computing
localization
mapping
mobile systems
split architecture
visual simultaneous localization and mapping

Access to Document

10.1145/3372224.3417326

Cite this

@conference{f5f5cb57a349427994d100813a42440e,

title = "Demo: Edge-SLAM: Edge-Assisted visual simultaneous localization and mapping",

abstract = "The recent advances in mobile devices have allowed them to run spatial sensing algorithms such as Visual Simultaneous Localization and Mapping (Visual-SLAM). However, the resource requirements of Visual-SLAM prevents long-operation of such algorithm on mobile devices. We demonstrate Edge-SLAM [2], a system that adapts edge computing into Visual-SLAM through a split architecture. Edge-SLAM offloads the compute-intensive modules of Visual-SLAM to the edge without losing accuracy. Our experiments show that Edge-SLAM architecture reduces the use of computation and memory resources on mobile devices and keeps it constant. Thus, enabling long-operation of Visual-SLAM along with other applications services on mobile devices.",

keywords = "edge computing, localization, mapping, mobile systems, split architecture, visual simultaneous localization and mapping",

author = "\{Ben Ali\}, \{Ali J.\} and Hashemifar, \{Zakieh Sadat\} and Karthik Dantu",

note = "Publisher Copyright: {\textcopyright} 2020 Owner/Author.; 26th Annual International Conference on Mobile Computing and Networking, MobiCom 2020 ; Conference date: 21-09-2020 Through 25-09-2020",

year = "2020",

doi = "10.1145/3372224.3417326",

language = "English",

pages = "878--880",

}

TY - CONF

T1 - Demo

T2 - 26th Annual International Conference on Mobile Computing and Networking, MobiCom 2020

AU - Ben Ali, Ali J.

AU - Hashemifar, Zakieh Sadat

AU - Dantu, Karthik

PY - 2020

Y1 - 2020

N2 - The recent advances in mobile devices have allowed them to run spatial sensing algorithms such as Visual Simultaneous Localization and Mapping (Visual-SLAM). However, the resource requirements of Visual-SLAM prevents long-operation of such algorithm on mobile devices. We demonstrate Edge-SLAM [2], a system that adapts edge computing into Visual-SLAM through a split architecture. Edge-SLAM offloads the compute-intensive modules of Visual-SLAM to the edge without losing accuracy. Our experiments show that Edge-SLAM architecture reduces the use of computation and memory resources on mobile devices and keeps it constant. Thus, enabling long-operation of Visual-SLAM along with other applications services on mobile devices.

AB - The recent advances in mobile devices have allowed them to run spatial sensing algorithms such as Visual Simultaneous Localization and Mapping (Visual-SLAM). However, the resource requirements of Visual-SLAM prevents long-operation of such algorithm on mobile devices. We demonstrate Edge-SLAM [2], a system that adapts edge computing into Visual-SLAM through a split architecture. Edge-SLAM offloads the compute-intensive modules of Visual-SLAM to the edge without losing accuracy. Our experiments show that Edge-SLAM architecture reduces the use of computation and memory resources on mobile devices and keeps it constant. Thus, enabling long-operation of Visual-SLAM along with other applications services on mobile devices.

KW - edge computing

KW - localization

KW - mapping

KW - mobile systems

KW - split architecture

KW - visual simultaneous localization and mapping

UR - https://www.scopus.com/pages/publications/85147729271

U2 - 10.1145/3372224.3417326

DO - 10.1145/3372224.3417326

M3 - Paper

AN - SCOPUS:85147729271

SP - 878

EP - 880

Y2 - 21 September 2020 through 25 September 2020

ER -

Demo: Edge-SLAM: Edge-Assisted visual simultaneous localization and mapping

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this