Neuromorphic implementation of motion detection using oscillation interference

Elishai Ezra Tsur, Michal Rivlin-Etzion

Research output: Contribution to journalArticlepeer-review

Abstract

Motion detection is paramount for computational vision processing. This is however a particularly challenging task for a neuromorphic hardware in which algorithms are based on interconnected spiking entities, as the instantaneous visual stimuli reports merely on luminance change. Here we describe a neuromorphic algorithm, in which an array of neuro-oscillators is utilized to detect motion and its direction over an entire field of view. These oscillators are induced via phase shifted Gabor functions, allowing them to oscillate in response to motion in one predefined direction, and to dump to zero otherwise. We developed the algorithm using the Neural Engineering Framework (NEF), making it applicable for a variety of neuromorphic hardware. Our algorithm extends the existing growing set of approaches aiming at utilizing neuromorphic hardware for vision processing, which enable to minimize energy exploitation and silicon area while enhancing computational capabilities.

Original languageEnglish
Pages (from-to)54-63
Number of pages10
JournalNeurocomputing
Volume374
Early online date27 Sep 2019
DOIs
StatePublished - 21 Jan 2020

Keywords

  • Motion detection
  • Nengo
  • Neural engineering framework
  • Neuromorphic vision sensor
  • Optical flow
  • Spike-based camera emulator

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Neuromorphic implementation of motion detection using oscillation interference'. Together they form a unique fingerprint.

Cite this