Near-chip dynamic vision filtering for low-bandwidth pedestrian detection

Anthony Bisulco, Fernando Cladera Ojeda, Volkan Isler, Daniel Dongyuel Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a novel end-to-end system for pedestrian detection using Dynamic Vision Sensors (DVSs). We target applications where multiple sensors transmit data to a local processing unit, which executes a detection algorithm. Our system is composed of (i) a near-chip event filter that compresses and denoises the event stream from the DVS, and (ii) a Binary Neural Network (BNN) detection module that runs on a low-computation edge computing device (in our case a STM32F4 microcontroller). We present the system architecture and provide an end-to-end implementation for pedestrian detection in an office environment. Our implementation reduces transmission size by up to 99.6% compared to transmitting the raw event stream. Our detector is able to perform a detection every 450 ms, with an overall testing F1 score of 83%. The low bandwidth and energy properties of our system make it ideal for IoT applications.

Original languageEnglish (US)
Title of host publicationProceedings - 2020 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2020
PublisherIEEE Computer Society
Pages234-239
Number of pages6
ISBN (Electronic)9781728157757
DOIs
StatePublished - Jul 2020
Externally publishedYes
Event19th IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2020 - Limassol, Cyprus
Duration: Jul 6 2020Jul 8 2020

Publication series

NameProceedings of IEEE Computer Society Annual Symposium on VLSI, ISVLSI
Volume2020-July
ISSN (Print)2159-3469
ISSN (Electronic)2159-3477

Conference

Conference19th IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2020
CountryCyprus
CityLimassol
Period7/6/207/8/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Keywords

  • Binary neural networks
  • Dynamic vision sensors
  • FPGA
  • Pedestrian detection

Fingerprint Dive into the research topics of 'Near-chip dynamic vision filtering for low-bandwidth pedestrian detection'. Together they form a unique fingerprint.

Cite this