Under pressure: learning-based analog gauge reading in the wild

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Reitsma, Maurits, Keller, Julian, Blomqvist, Kenneth, Siegwart, Roland
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913314010824704
author Reitsma, Maurits
Keller, Julian
Blomqvist, Kenneth
Siegwart, Roland
author_facet Reitsma, Maurits
Keller, Julian
Blomqvist, Kenneth
Siegwart, Roland
contents We propose an interpretable framework for reading analog gauges that is deployable on real world robotic systems. Our framework splits the reading task into distinct steps, such that we can detect potential failures at each step. Our system needs no prior knowledge of the type of gauge or the range of the scale and is able to extract the units used. We show that our gauge reading algorithm is able to extract readings with a relative reading error of less than 2%.
format Preprint
id arxiv_https___arxiv_org_abs_2404_08785
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Under pressure: learning-based analog gauge reading in the wild
Reitsma, Maurits
Keller, Julian
Blomqvist, Kenneth
Siegwart, Roland
Computer Vision and Pattern Recognition
Machine Learning
Robotics
We propose an interpretable framework for reading analog gauges that is deployable on real world robotic systems. Our framework splits the reading task into distinct steps, such that we can detect potential failures at each step. Our system needs no prior knowledge of the type of gauge or the range of the scale and is able to extract the units used. We show that our gauge reading algorithm is able to extract readings with a relative reading error of less than 2%.
title Under pressure: learning-based analog gauge reading in the wild
topic Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2404.08785