Back to search

Cornell University

Holistic Optimization of Embedded Computer Vision Systems

Abstract

dc:description.abstract

Despite strong interest in embedded computer vision, the computational demands of Convolutional Neural Network (CNN) inference far exceed the resources available in embedded devices. Thankfully, the typical embedded device has a number of desirable properties that can be leveraged to significantly reduce the time and energy required for CNN inference. This thesis presents three independent and synergistic methods for optimizing embedded computer vision: 1) Reducing the time and energy needed to capture and preprocess input images by optimizing the image capture pipeline for the needs of CNNs rather than humans. 2) Exploiting temporal redundancy within incoming video streams to perform computationally cheap motion estimation and compensation in lieu of full CNN inference for the majority of frames. 3) Leveraging the sparsity of CNN activations within the frequency domain to significantly reduce the number of operations needed for inference. Collectively these techniques significantly reduce the time and energy needed for computer vision at the edge, enabling a wide variety of exciting new applications.

Degree

thesis:*
Name thesis:degree_name
Ph.D., Electrical and Computer Engineering
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Electrical and Computer Engineering
Grantor
Cornell University
Year dc:date.issued
2019

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Buckler, Mark Andrew
Chair dc:contributor.chair
  • Sampson, Adrian L
Committee members dc:contributor.committeemember
  • Batten, Christopher
  • Hariharan, Bharath
  • De Sa, Christopher Matthew

Subjects

dc:subject × 6

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Dc Identifier Bibid
11050597
Dc Identifier Other
ProQuest Submission ID: 11723
ProQuest Publication ID: 22616460

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Buckler, Mark Andrew. Holistic Optimization of Embedded Computer Vision Systems. Doctor of Philosophy thesis, Cornell University, 2019. https://hdl.handle.net/1813/67614