2020/04/03 by Anthony Bisulco, Fernando Cladera Ojeda, Bisulco, Anthony +5 · 3 citations
Computer Science · Engineering · #Advanced Memory and Neural Computing #Advanced Neural Network Applications #CCD and CMOS Imaging Sensors #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Hardware Architecture (cs.AR) #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2004.01689
openalex publication_date 2020/04/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper presents a novel end-to-end system for pedestrian detection using\nDynamic Vision Sensors (DVSs). We target applications where multiple sensors\ntransmit data to a local processing unit, which executes a detection algorithm.\nOur system is composed of (i) a near-chip event filter that compresses and\ndenoises the event stream from the DVS, and (ii) a Binary Neural Network (BNN)\ndetection module that runs on a low-computation edge computing device (in our\ncase a STM32F4 microcontroller). We present the system architecture and provide\nan end-to-end implementation for pedestrian detection in an office environment.\nOur implementation reduces transmission size by up to 99.6% compared to\ntransmitting the raw event stream. The average packet size in our system is\nonly 1397 bits, while 307.2 kb are required to send an uncompressed DVS time\nwindow. Our detector is able to perform a detection every 450 ms, with an\noverall testing F1 score of 83%. The low bandwidth and energy properties of our\nsystem make it ideal for IoT applications.\n