A hybrid approach to offloading mobile image classification

J. Hauswald, T. Manville, Q. Zheng, R. Dreslinski, Chaitali Chakrabarti, T. Mudge

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Citations (Scopus)

Abstract

Current mobile devices are unable to execute complex vision applications in a timely and power efficient manner without offloading some of the computation. This paper examines the tradeoffs that arise from executing some of the workload onboard and some remotely. Feature extraction and matching play an essential role in image classification and have the potential to be executed locally. Along with advances in mobile hardware, understanding the computation requirements of these applications is essential to realize their full potential in mobile environments. We analyze the ability of a mobile platform to execute feature extraction and matching, and prediction workloads under various scenarios. The best configuration for optimal runtime (11% faster) executes feature extraction with a GPU onboard and offloads the rest of the pipeline. Alternatively, compressing and sending the image over the network achieves lowest data transferred (2.5× better) and lowest energy usage (3.7× better) than the next best option.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages8375-8379
Number of pages5
ISBN (Print)9781479928927
DOIs
StatePublished - 2014
Event2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy
Duration: May 4 2014May 9 2014

Other

Other2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
CountryItaly
CityFlorence
Period5/4/145/9/14

Fingerprint

Image classification
Feature extraction
Mobile devices
Pipelines
Hardware

Keywords

  • energy management
  • image classification
  • mobile computing
  • offloading

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Hauswald, J., Manville, T., Zheng, Q., Dreslinski, R., Chakrabarti, C., & Mudge, T. (2014). A hybrid approach to offloading mobile image classification. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 8375-8379). [6855235] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2014.6855235

A hybrid approach to offloading mobile image classification. / Hauswald, J.; Manville, T.; Zheng, Q.; Dreslinski, R.; Chakrabarti, Chaitali; Mudge, T.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. p. 8375-8379 6855235.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hauswald, J, Manville, T, Zheng, Q, Dreslinski, R, Chakrabarti, C & Mudge, T 2014, A hybrid approach to offloading mobile image classification. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 6855235, Institute of Electrical and Electronics Engineers Inc., pp. 8375-8379, 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014, Florence, Italy, 5/4/14. https://doi.org/10.1109/ICASSP.2014.6855235
Hauswald J, Manville T, Zheng Q, Dreslinski R, Chakrabarti C, Mudge T. A hybrid approach to offloading mobile image classification. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. p. 8375-8379. 6855235 https://doi.org/10.1109/ICASSP.2014.6855235
Hauswald, J. ; Manville, T. ; Zheng, Q. ; Dreslinski, R. ; Chakrabarti, Chaitali ; Mudge, T. / A hybrid approach to offloading mobile image classification. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 8375-8379
@inproceedings{69ee20a9a09447ca91447a69c54cfa2d,
title = "A hybrid approach to offloading mobile image classification",
abstract = "Current mobile devices are unable to execute complex vision applications in a timely and power efficient manner without offloading some of the computation. This paper examines the tradeoffs that arise from executing some of the workload onboard and some remotely. Feature extraction and matching play an essential role in image classification and have the potential to be executed locally. Along with advances in mobile hardware, understanding the computation requirements of these applications is essential to realize their full potential in mobile environments. We analyze the ability of a mobile platform to execute feature extraction and matching, and prediction workloads under various scenarios. The best configuration for optimal runtime (11{\%} faster) executes feature extraction with a GPU onboard and offloads the rest of the pipeline. Alternatively, compressing and sending the image over the network achieves lowest data transferred (2.5× better) and lowest energy usage (3.7× better) than the next best option.",
keywords = "energy management, image classification, mobile computing, offloading",
author = "J. Hauswald and T. Manville and Q. Zheng and R. Dreslinski and Chaitali Chakrabarti and T. Mudge",
year = "2014",
doi = "10.1109/ICASSP.2014.6855235",
language = "English (US)",
isbn = "9781479928927",
pages = "8375--8379",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A hybrid approach to offloading mobile image classification

AU - Hauswald, J.

AU - Manville, T.

AU - Zheng, Q.

AU - Dreslinski, R.

AU - Chakrabarti, Chaitali

AU - Mudge, T.

PY - 2014

Y1 - 2014

N2 - Current mobile devices are unable to execute complex vision applications in a timely and power efficient manner without offloading some of the computation. This paper examines the tradeoffs that arise from executing some of the workload onboard and some remotely. Feature extraction and matching play an essential role in image classification and have the potential to be executed locally. Along with advances in mobile hardware, understanding the computation requirements of these applications is essential to realize their full potential in mobile environments. We analyze the ability of a mobile platform to execute feature extraction and matching, and prediction workloads under various scenarios. The best configuration for optimal runtime (11% faster) executes feature extraction with a GPU onboard and offloads the rest of the pipeline. Alternatively, compressing and sending the image over the network achieves lowest data transferred (2.5× better) and lowest energy usage (3.7× better) than the next best option.

AB - Current mobile devices are unable to execute complex vision applications in a timely and power efficient manner without offloading some of the computation. This paper examines the tradeoffs that arise from executing some of the workload onboard and some remotely. Feature extraction and matching play an essential role in image classification and have the potential to be executed locally. Along with advances in mobile hardware, understanding the computation requirements of these applications is essential to realize their full potential in mobile environments. We analyze the ability of a mobile platform to execute feature extraction and matching, and prediction workloads under various scenarios. The best configuration for optimal runtime (11% faster) executes feature extraction with a GPU onboard and offloads the rest of the pipeline. Alternatively, compressing and sending the image over the network achieves lowest data transferred (2.5× better) and lowest energy usage (3.7× better) than the next best option.

KW - energy management

KW - image classification

KW - mobile computing

KW - offloading

UR - http://www.scopus.com/inward/record.url?scp=84905227563&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905227563&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2014.6855235

DO - 10.1109/ICASSP.2014.6855235

M3 - Conference contribution

AN - SCOPUS:84905227563

SN - 9781479928927

SP - 8375

EP - 8379

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -