RT journal article
T1 Low Latency Event-Based Filtering and Feature Extraction for Dynamic Vision Sensors in Real-Time FPGA Applications
A1 Linares Barranco, Alejandro
A1 Pérez Peña, Fernando
A1 Moeys, Diederik Paul
A1 Gómez Rodríguez, Francisco
A1 Jiménez Moreno, Gabriel
A1 Liu, Shin-Chit
A1 Delbruck, Tobi
A2 Ingeniería en AutomáticaElectrónica, Arquitectura y Redes de Computadores
K1 Neuromorphic engineering
K1 address-event-representation (AER)
K1 dynamic vision
K1 framefree vision
K1 event-based processing
K1 event-based lters
K1 eld programmable gate arrays (FPGA)
K1 VHDL
AB Dynamic Vision Sensor (DVS) pixels produce an asynchronous variable-rate address-eventoutput that represents brightness changes at the pixel. Since these sensors produce frame-free output, theyare ideal for real-time dynamic vision applications with real-time latency and power system constraints.Event-based  ltering algorithms have been proposed to post-process the asynchronous event output toreduce sensor noise, extract low level features, and track objects, among others. These postprocessingalgorithms help to increase the performance and accuracy of further processing for tasks such as classi cationusing spike-based learning (ie. ConvNets), stereo vision, and visually-servoed robots, etc. This paperpresents an FPGA-based library of these postprocessing event-based algorithms with implementation details;speci cally background activity (noise)  ltering, pixel masking, object motion detection and object tracking.The latencies of these  lters on the Field Programmable Gate Array (FPGA) platform are below 300ns withan average latency reduction of 188% (maximum of 570%) over the software versions running on a desktopPC CPU. This open-source event-based  lter IP library for FPGA has been tested on two different platformsand scenarios using different synthesis and implementation tools for Lattice and Xilinx vendors.
PB IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
SN 2169-3536
YR 2019
FD 2019
LK http://hdl.handle.net/10498/22164
UL http://hdl.handle.net/10498/22164
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 09-may-2026