Adaptive Attention with a Neuromorphic Hybrid Frame and Event-based Camera.

Avinoam Bitton, Hadar Cohen Duwek, Elishai Ezra Tsur

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Neuromorphic (brain-inspired) cameras communicate transients in luminance as events, supporting high frame rate, fine temporal resolution, high dynamic range, no motion blur, high signal-To-noise ratio, and power-efficient vision systems. Here, we used a hybrid camera, neuromorphically enhancing frame-based vision with event-driven motion-sensitive adaptive attention. We used spatial-memory and event-driven salient maps to direct a frame camera toward attentive zones. We further implemented a dynamic tolerance mechanism with which attentional zones reallocate, supporting a multiple-object attentional load. Finally, we enhanced our hybrid imaging system using an automatic segmentation performed in fixed time intervals on event-based reconstructed frames, allowing efficient derivation of attentive areas. This hybrid approach demonstrates an efficient coverage of a large field of view.

Original languageAmerican English
Title of host publicationProceedings of 2022 IEEE 21st International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2022
EditorsYingxu Wang, Konstantin N. Plataniotis, Bernard Widrow, Witold Pedrycz, Witold Kinsner, Petros Spachos, Sam Kwong
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages242-247
Number of pages6
ISBN (Electronic)9781665490849
DOIs
StatePublished - 2022
Event21st IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2022 - Toronto, Canada
Duration: 8 Dec 202210 Dec 2022

Publication series

NameProceedings of 2022 IEEE 21st International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2022

Conference

Conference21st IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2022
Country/TerritoryCanada
CityToronto
Period8/12/2210/12/22

Bibliographical note

DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

Keywords

  • attentive clustering
  • DeepLabV3
  • dynamic vision sensors
  • Event-based cameras
  • FireNet
  • MVSEC

Fingerprint

Dive into the research topics of 'Adaptive Attention with a Neuromorphic Hybrid Frame and Event-based Camera.'. Together they form a unique fingerprint.

Cite this