Rethinking the imaging pipeline for energy-efficient privacy-preserving continuous mobile vision

Robert LiKamWa, Yunhui Hou, Peter Y. Washington, Lin Zhong

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Current mobile imaging pipelines, provisioned for high quality photography, are ill-suited for wearable vision analytics, due to their high power consumption and privacy concerns, as exemplified by the slow adoption of wearables, such as Google Glass. Rather than constructing incremental improvements, we believe it is necessary to completely redesign a dedicated imaging pipeline for vision analytics. Toward this goal, we study a novel imaging pipeline, revolving around an in-imager analog vision processor that exports a low bandwidth irreversibly encoded signal, generating vision features before analog-to-digital conversion. To produce this signal at low power, we introduce energy-scaling mechanisms into the imager's analog frontend to produce the encoded signal We use these mechanisms to generate a low-power signal that cannot be used to reconstruct the image, yet suffices as input for vision analytics. This imaging pipeline design will simultaneously achieve privacy and efficiency for continuous mobile vision tasks.

Original languageEnglish (US)
Pages (from-to)187-188
Number of pages2
JournalUnknown Journal
Volume46
Issue numberBook 1
StatePublished - Jun 1 2015
Externally publishedYes

Fingerprint

Privacy
Pipelines
Imaging techniques
Image sensors
Analog to digital conversion
Analog-Digital Conversion
Photography
Electric power utilization
Bandwidth
Glass

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Rethinking the imaging pipeline for energy-efficient privacy-preserving continuous mobile vision. / LiKamWa, Robert; Hou, Yunhui; Washington, Peter Y.; Zhong, Lin.

In: Unknown Journal, Vol. 46, No. Book 1, 01.06.2015, p. 187-188.

Research output: Contribution to journalArticle

LiKamWa, R, Hou, Y, Washington, PY & Zhong, L 2015, 'Rethinking the imaging pipeline for energy-efficient privacy-preserving continuous mobile vision', Unknown Journal, vol. 46, no. Book 1, pp. 187-188.
LiKamWa, Robert ; Hou, Yunhui ; Washington, Peter Y. ; Zhong, Lin. / Rethinking the imaging pipeline for energy-efficient privacy-preserving continuous mobile vision. In: Unknown Journal. 2015 ; Vol. 46, No. Book 1. pp. 187-188.
@article{da1ead0ee18444d697f94bfdf9a5c35d,
title = "Rethinking the imaging pipeline for energy-efficient privacy-preserving continuous mobile vision",
abstract = "Current mobile imaging pipelines, provisioned for high quality photography, are ill-suited for wearable vision analytics, due to their high power consumption and privacy concerns, as exemplified by the slow adoption of wearables, such as Google Glass. Rather than constructing incremental improvements, we believe it is necessary to completely redesign a dedicated imaging pipeline for vision analytics. Toward this goal, we study a novel imaging pipeline, revolving around an in-imager analog vision processor that exports a low bandwidth irreversibly encoded signal, generating vision features before analog-to-digital conversion. To produce this signal at low power, we introduce energy-scaling mechanisms into the imager's analog frontend to produce the encoded signal We use these mechanisms to generate a low-power signal that cannot be used to reconstruct the image, yet suffices as input for vision analytics. This imaging pipeline design will simultaneously achieve privacy and efficiency for continuous mobile vision tasks.",
author = "Robert LiKamWa and Yunhui Hou and Washington, {Peter Y.} and Lin Zhong",
year = "2015",
month = "6",
day = "1",
language = "English (US)",
volume = "46",
pages = "187--188",
journal = "Scanning Electron Microscopy",
issn = "0586-5581",
publisher = "Scanning Microscopy International",
number = "Book 1",

}

TY - JOUR

T1 - Rethinking the imaging pipeline for energy-efficient privacy-preserving continuous mobile vision

AU - LiKamWa, Robert

AU - Hou, Yunhui

AU - Washington, Peter Y.

AU - Zhong, Lin

PY - 2015/6/1

Y1 - 2015/6/1

N2 - Current mobile imaging pipelines, provisioned for high quality photography, are ill-suited for wearable vision analytics, due to their high power consumption and privacy concerns, as exemplified by the slow adoption of wearables, such as Google Glass. Rather than constructing incremental improvements, we believe it is necessary to completely redesign a dedicated imaging pipeline for vision analytics. Toward this goal, we study a novel imaging pipeline, revolving around an in-imager analog vision processor that exports a low bandwidth irreversibly encoded signal, generating vision features before analog-to-digital conversion. To produce this signal at low power, we introduce energy-scaling mechanisms into the imager's analog frontend to produce the encoded signal We use these mechanisms to generate a low-power signal that cannot be used to reconstruct the image, yet suffices as input for vision analytics. This imaging pipeline design will simultaneously achieve privacy and efficiency for continuous mobile vision tasks.

AB - Current mobile imaging pipelines, provisioned for high quality photography, are ill-suited for wearable vision analytics, due to their high power consumption and privacy concerns, as exemplified by the slow adoption of wearables, such as Google Glass. Rather than constructing incremental improvements, we believe it is necessary to completely redesign a dedicated imaging pipeline for vision analytics. Toward this goal, we study a novel imaging pipeline, revolving around an in-imager analog vision processor that exports a low bandwidth irreversibly encoded signal, generating vision features before analog-to-digital conversion. To produce this signal at low power, we introduce energy-scaling mechanisms into the imager's analog frontend to produce the encoded signal We use these mechanisms to generate a low-power signal that cannot be used to reconstruct the image, yet suffices as input for vision analytics. This imaging pipeline design will simultaneously achieve privacy and efficiency for continuous mobile vision tasks.

UR - http://www.scopus.com/inward/record.url?scp=84963656304&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963656304&partnerID=8YFLogxK

M3 - Article

VL - 46

SP - 187

EP - 188

JO - Scanning Electron Microscopy

JF - Scanning Electron Microscopy

SN - 0586-5581

IS - Book 1

ER -