Extended abstract: Efficient image processing for continuous mobile vision

Robert LiKamWa

doi:10.1145/2611166.2611171

Extended abstract: Efficient image processing for continuous mobile vision

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Vision algorithms have enabled our camera-equipped devices to perform powerful tasks, including barcode scanning, object detection,text recognition, and face identification. Unfortunately,these tasks require significant energy to capture,process, and analyze images through the image sensor (imager),image signal processor (ISP), and application processor,limiting the longevity of such applications to short-term, on-demand use. We propose the investigation of an image processing paradigm that uses vision task information to optimize the energy cost of the image capture pipeline. Copyright is held by the owner/author(s). Publication rights licensed to ACM.

Original language	English (US)
Title of host publication	MobiSys 2014 - PhD Forum 2014
Publisher	Association for Computing Machinery
Pages	9-10
Number of pages	2
ISBN (Print)	9781450329408
DOIs	https://doi.org/10.1145/2611166.2611171
State	Published - Jan 1 2014
Externally published	Yes
Event	2014 ACM MobiSys PhD Forum Workshop, PhD Forum 2014 - Bretton Woods, NH, United States Duration: Jun 16 2014 → Jun 16 2014

Publication series

Name	MobiSys 2014 - PhD Forum 2014

Conference

Conference	2014 ACM MobiSys PhD Forum Workshop, PhD Forum 2014
Country/Territory	United States
City	Bretton Woods, NH
Period	6/16/14 → 6/16/14

Keywords

Computer Vision
Energy Efficiency
Image Sensors
Image Signal Processing
Mobile Systems
Operating Systems

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1145/2611166.2611171

Cite this

@inproceedings{a08ff5be9757474bb9065819be797fce,

title = "Extended abstract: Efficient image processing for continuous mobile vision",

abstract = "Vision algorithms have enabled our camera-equipped devices to perform powerful tasks, including barcode scanning, object detection,text recognition, and face identification. Unfortunately,these tasks require significant energy to capture,process, and analyze images through the image sensor (imager),image signal processor (ISP), and application processor,limiting the longevity of such applications to short-term, on-demand use. We propose the investigation of an image processing paradigm that uses vision task information to optimize the energy cost of the image capture pipeline. Copyright is held by the owner/author(s). Publication rights licensed to ACM.",

keywords = "Computer Vision, Energy Efficiency, Image Sensors, Image Signal Processing, Mobile Systems, Operating Systems",

author = "Robert LiKamWa",

year = "2014",

month = jan,

day = "1",

doi = "10.1145/2611166.2611171",

language = "English (US)",

isbn = "9781450329408",

series = "MobiSys 2014 - PhD Forum 2014",

publisher = "Association for Computing Machinery",

pages = "9--10",

booktitle = "MobiSys 2014 - PhD Forum 2014",

note = "2014 ACM MobiSys PhD Forum Workshop, PhD Forum 2014 ; Conference date: 16-06-2014 Through 16-06-2014",

}

TY - GEN

T1 - Extended abstract

T2 - 2014 ACM MobiSys PhD Forum Workshop, PhD Forum 2014

AU - LiKamWa, Robert

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Vision algorithms have enabled our camera-equipped devices to perform powerful tasks, including barcode scanning, object detection,text recognition, and face identification. Unfortunately,these tasks require significant energy to capture,process, and analyze images through the image sensor (imager),image signal processor (ISP), and application processor,limiting the longevity of such applications to short-term, on-demand use. We propose the investigation of an image processing paradigm that uses vision task information to optimize the energy cost of the image capture pipeline. Copyright is held by the owner/author(s). Publication rights licensed to ACM.

AB - Vision algorithms have enabled our camera-equipped devices to perform powerful tasks, including barcode scanning, object detection,text recognition, and face identification. Unfortunately,these tasks require significant energy to capture,process, and analyze images through the image sensor (imager),image signal processor (ISP), and application processor,limiting the longevity of such applications to short-term, on-demand use. We propose the investigation of an image processing paradigm that uses vision task information to optimize the energy cost of the image capture pipeline. Copyright is held by the owner/author(s). Publication rights licensed to ACM.

KW - Computer Vision

KW - Energy Efficiency

KW - Image Sensors

KW - Image Signal Processing

KW - Mobile Systems

KW - Operating Systems

UR - http://www.scopus.com/inward/record.url?scp=84904347262&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904347262&partnerID=8YFLogxK

U2 - 10.1145/2611166.2611171

DO - 10.1145/2611166.2611171

M3 - Conference contribution

AN - SCOPUS:84904347262

SN - 9781450329408

T3 - MobiSys 2014 - PhD Forum 2014

SP - 9

EP - 10

BT - MobiSys 2014 - PhD Forum 2014

PB - Association for Computing Machinery

Y2 - 16 June 2014 through 16 June 2014

ER -

Extended abstract: Efficient image processing for continuous mobile vision

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this