A 33μW 42 GOPS/W 64x64 pixel vision sensor with dynamic background subtraction for scene interpretation

  • Authors:

  • Nicola Cottini;Massimo Gottardi;Nicola Massari;Roberto Passerone;Zeev Smilansky

  • Affiliations:

  • Fondazione Bruno Kessler, Trento, Italy;Fondazione Bruno Kessler, Trento, Italy;Fondazione Bruno Kessler, Trento, Italy;University of Trento, Trento, Italy;Emza Visual Sense Ltd., Kfar Sava, Israel

  • Venue:
  • Proceedings of the 2012 ACM/IEEE international symposium on Low power electronics and design
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

A 64x64 pixel vision sensor performs adaptive background subtraction and event detection at very low power consumption. The chip is based on a VLSI-oriented vision algorithm, implemented at pixel-level, mimicking the basic process of pre-attentive visual perception. Anomalous pixel behaviors are detected and coded into a 2-bit/pixel. Each pixel integrates two programmable Switched-Capacitors Low-Pass Filters and two clocked comparators, which are fundamental blocks for the execution of the vision algorithm. The 45T square pixel has a pitch of 26μm and a fill factor of 12%. The vision sensor consumes 33μW at 13 fps and 3.3V. This turns into a computing performance of 42 GOPS/W and 4 GOPS/mm2, which are values aligned with the most advanced computational vision sensors.