Change detection using weighted features for image-based localization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00344049" target="_blank" >RIV/68407700:21230/21:00344049 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/21:00344049

Výsledek na webu

<a href="https://doi.org/10.1016/j.robot.2020.103676" target="_blank" >https://doi.org/10.1016/j.robot.2020.103676</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.robot.2020.103676" target="_blank" >10.1016/j.robot.2020.103676</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Change detection using weighted features for image-based localization

Popis výsledku v původním jazyce

Autonomous mobile robots are becoming increasingly important in many industrial and domesticenvironments.Dealingwithunforeseensituationsisadifficultproblemthatmustbetackledtoachievelong-term robot autonomy. In vision-based localization and navigation methods, one of the majorissues is the scene dynamics. The autonomous operation of the robot may become unreliable if thechanges occurring in dynamic environments are not detected and managed. Moving chairs, openingand closing doors or windows, replacing objects and other changes make many conventional methodsfail. To deal with these challenges, we present a novel method for change detection based on weightedlocal visual features. The core idea of the algorithm is to distinguish the valuable information in stableregions of the scene from the potentially misleading information in the regions that are changing. Weevaluate the change detection algorithm in a visual localization framework based on feature matchingby performing a series of long-term localization experiments in various real-world environments. Theresults show that the change detection method yields an improvement in the localization accuracy,compared to the baseline method without change detection. In addition, an experimental evaluationon a public long-term localization data set with more than 10000 images reveals that the proposedmethod outperforms two alternative localization methods on images recorded several months afterthe initial mapping

Název v anglickém jazyce

Change detection using weighted features for image-based localization

Popis výsledku anglicky

Autonomous mobile robots are becoming increasingly important in many industrial and domesticenvironments.Dealingwithunforeseensituationsisadifficultproblemthatmustbetackledtoachievelong-term robot autonomy. In vision-based localization and navigation methods, one of the majorissues is the scene dynamics. The autonomous operation of the robot may become unreliable if thechanges occurring in dynamic environments are not detected and managed. Moving chairs, openingand closing doors or windows, replacing objects and other changes make many conventional methodsfail. To deal with these challenges, we present a novel method for change detection based on weightedlocal visual features. The core idea of the algorithm is to distinguish the valuable information in stableregions of the scene from the potentially misleading information in the regions that are changing. Weevaluate the change detection algorithm in a visual localization framework based on feature matchingby performing a series of long-term localization experiments in various real-world environments. Theresults show that the change detection method yields an improvement in the localization accuracy,compared to the baseline method without change detection. In addition, an experimental evaluationon a public long-term localization data set with more than 10000 images reveals that the proposedmethod outperforms two alternative localization methods on images recorded several months afterthe initial mapping

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

<a href="/cs/project/EF15_003%2F0000470" target="_blank" >EF15_003/0000470: Robotika pro Průmysl 4.0</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Robotics and Autonomous Systems

ISSN

0921-8890

e-ISSN

1872-793X

Svazek periodika

135

Číslo periodika v rámci svazku

January

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

—

Kód UT WoS článku

000595253700003

EID výsledku v databázi Scopus

2-s2.0-85095916049