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

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding


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.


  • August Lidfelt
  • Daniel Isaksson
  • Ludwig Hedlund
  • Simon Åberg
  • Markus Borg
  • Erik Larsson
Enheter & grupper
Externa organisationer
  • Research Institutes of Sweden (RISE)
  • Lund University

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Datorseende och robotik (autonoma system)


Titel på värdpublikation1st international workshop on Internet of Things for Emergency Management
FörlagAssociation for Computing Machinery (ACM)
Antal sidor13
ISBN (tryckt) 978-1-4503-8820-7/20/10
StatusPublished - 2020
Peer review utfördJa
EvenemangFirst international workshop on Internet of Things for Emergency Management (IoT4Emergency) - Malmö, Sverige
Varaktighet: 2020 okt 62020 okt 6


KonferensFirst international workshop on Internet of Things for Emergency Management (IoT4Emergency)


Ingen tillgänglig data