Degradable inference for energy autonomous vision applications

Alessandro Montanari, Mohammed Alloulah, Fahim Kawsar

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

Mobile vision systems, often battery-powered, are now incredibly powerful in capturing, analyzing, and understanding real-world events uncovering interminable opportunities for new applications in the areas of life-logging, cognitive augmentation, security, safety, wildlife surveillance, etc. There are two complementary challenges in the design of a mobile vision system today - improving the recognition accuracy at the expense of minimum energy consumption. In this work, we posit that best-effort sensing with degradable featurization and an elastic inference pipeline offers an interesting avenue to bring energy autonomy to mobile vision systems while ensuring acceptable recognition performance. Borrowing principles from Intermittent Computing, and Numerical Computing we propose such best-effort sensing using a Degradable-Inference pipeline supported by a parameterized Discrete Cosine Transformation (DCT) based featurization and an Anytime Deep Neural Network. These two principles aim at extending the lifetime of a mobile vision system while minimizing compute and communication cost without compromising recognition performance. We report the design and early characterization of our proposed solution.

Original languageEnglish
Title of host publicationUbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers
EditorsRobert Harle, Katayoun Farrahi, Nicholas Lane
PublisherAssociation for Computing Machinery (ACM)
Pages592-597
Number of pages6
ISBN (Electronic)978-1-4503-6869-8
DOIs
Publication statusPublished - 2019
Event2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2019 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2019 - London, United Kingdom
Duration: 9 Sep 201913 Sep 2019

Conference

Conference2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2019 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2019
CountryUnited Kingdom
CityLondon
Period9/09/1913/09/19

Keywords

  • Anytime algorithms
  • Energy autonomous
  • Neural networks

Fingerprint Dive into the research topics of 'Degradable inference for energy autonomous vision applications'. Together they form a unique fingerprint.

Cite this