Enabling Image Recognition on Constrained Devices Using Neural Network Pruning and a CycleGAN

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceeding

Abstract

Smart cameras are increasingly used in surveillance solutions in public spaces. Contemporary computer vision applications can be used to recognize events that require intervention by emergency services. Smart cameras can be mounted in locations where citizens feel particularly unsafe, e.g., pathways and underpasses with a history of incidents. One promising approach for smart cameras is edge AI, i.e., deploying AI technology on IoT devices. However, implementing resource-demanding technology such as image recognition using deep neural networks (DNN) on constrained devices is a substantial challenge. In this paper, we explore two approaches to reduce the need for compute in contemporary image recognition in an underpass. First, we showcase successful neural network pruning, i.e., we retain comparable classification accuracy with only 1.1% of the neurons remaining from the state-of-the-art DNN architecture. Second, we demonstrate how a CycleGAN can be used to transform out-of-distribution images to the operational design domain. We posit that both pruning and CycleGANs are promising enablers for efficient edge AI in smart cameras.

Details

Authors
  • August Lidfelt
  • Daniel Isaksson
  • Ludwig Hedlund
  • Simon Åberg
  • Markus Borg
  • Erik Larsson
Organisations
External organisations
  • Research Institutes of Sweden (RISE)
  • Lund University
Research areas and keywords

Subject classification (UKÄ) – MANDATORY

  • Computer Vision and Robotics (Autonomous Systems)

Keywords

  • smart camera, image recognition, neural network pruning, genera- tive adversarial network, edge AI
Original languageEnglish
Title of host publication1st international workshop on Internet of Things for Emergency Management
PublisherAssociation for Computing Machinery (ACM)
Number of pages13
ISBN (Print)9781450388207
Publication statusPublished - 2020
Publication categoryResearch
Peer-reviewedYes
EventFirst international workshop on Internet of Things for Emergency Management (IoT4Emergency) - Malmö, Sweden
Duration: 2020 Oct 62020 Oct 6

Conference

ConferenceFirst international workshop on Internet of Things for Emergency Management (IoT4Emergency)
CountrySweden
CityMalmö
Period2020/10/062020/10/06

Total downloads

No data available

Related projects

Markus Borg & Emelie Engström

2019/05/012021/12/31

Project: ResearchCollaboration with industry, Collaboration with municipalities and county councils

View all (1)