Velocity and Color Estimation Using Event-Based Clustering

Xavier Lesage, Rosalie Tran, Stéphane Mancini, Laurent Fesquet, Dan Popescu, Loretta Ichim · 2023

Read Velocity and Color Estimation Using Event-Based Clustering by Xavier Lesage, Rosalie Tran, Stéphane Mancini, Laurent Fesquet, Dan Popescu, Loretta Ichim (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10747939.txt.

Description

Xavier Lesage and co-authors present a 2023 study on event cameras, sensors that report only the pixels that change. Such sensors sip power and suit small embedded devices. A clustering method groups the events from one moving object and reads off its traits as it goes. The team extends that method in two directions.

First, they read the speed of an object from the mean drift of its event cluster. Next, they use a new kind of event that carries the light level at the pixel, letting them guess the rough color of a cluster. Tests ran on fake outdoor scenes from a custom simulator. Speed reads were sound, with a trade between sharpness and settling time. Color reads split: the hue came out well, while raw brightness proved hard. The traits sufficed to sort objects into set classes.

Catalog record

CREATORXavier Lesage, Rosalie Tran, Stéphane Mancini, Laurent Fesquet, Dan Popescu, Loretta Ichim
YEAR2023
COLLECTIONPAPERS
FORMATTXT
FILE SIZE59 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10747939

Browse the full library · About the Tower of Babel