Vision Based Localization under Dynamic Illumination

Localization in dynamically illuminated environments is often difficult due to static objects casting dynamic shadows. Feature extraction algorithms may detect both the objects and their shadows, producing conflict in localization algorithms. This work examines a colour model that separates brightne...

Full description

Bibliographic Details
Main Authors: LeCras, Jared, Paxman, Jonathan, Saracik, Brad
Other Authors: G. Sen Gupta
Format: Conference Paper
Published: IEEE 2011
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/23221
_version_ 1848751090416222208
author LeCras, Jared
Paxman, Jonathan
Saracik, Brad
author2 G. Sen Gupta
author_facet G. Sen Gupta
LeCras, Jared
Paxman, Jonathan
Saracik, Brad
author_sort LeCras, Jared
building Curtin Institutional Repository
collection Online Access
description Localization in dynamically illuminated environments is often difficult due to static objects casting dynamic shadows. Feature extraction algorithms may detect both the objects and their shadows, producing conflict in localization algorithms. This work examines a colour model that separates brightness from chromaticity and applies it to eliminate features caused by dynamic illumination. The colour model is applied in two novel ways. Firstly, the chromaticity distortion of a single feature is used to determine if the feature is the result of illumination alone i.e. a shadow. Secondly, the chromaticity distortion of features matched between images is examined to determine if the monochrome based algorithm has matched them correctly. These two applications are put through a variety of tests in simulated then real world environments to assess their effectiveness in dynamically illuminated scenarios. The results demonstrate a significant reduction in the number of feature mismatches between images with dynamic light sources. The evaluation of the techniques individually in a Simultaneous Localization and Mapping (SLAM) task show substantial improvements in accuracy, with the combination of the two techniques producing a localization result that is highly robust to the environmental lighting.
first_indexed 2025-11-14T07:47:12Z
format Conference Paper
id curtin-20.500.11937-23221
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:47:12Z
publishDate 2011
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-232212023-01-27T05:26:32Z Vision Based Localization under Dynamic Illumination LeCras, Jared Paxman, Jonathan Saracik, Brad G. Sen Gupta Donald Bailey Serge Demidenko Dale Carnegie mining localization dynamic illumination Localization in dynamically illuminated environments is often difficult due to static objects casting dynamic shadows. Feature extraction algorithms may detect both the objects and their shadows, producing conflict in localization algorithms. This work examines a colour model that separates brightness from chromaticity and applies it to eliminate features caused by dynamic illumination. The colour model is applied in two novel ways. Firstly, the chromaticity distortion of a single feature is used to determine if the feature is the result of illumination alone i.e. a shadow. Secondly, the chromaticity distortion of features matched between images is examined to determine if the monochrome based algorithm has matched them correctly. These two applications are put through a variety of tests in simulated then real world environments to assess their effectiveness in dynamically illuminated scenarios. The results demonstrate a significant reduction in the number of feature mismatches between images with dynamic light sources. The evaluation of the techniques individually in a Simultaneous Localization and Mapping (SLAM) task show substantial improvements in accuracy, with the combination of the two techniques producing a localization result that is highly robust to the environmental lighting. 2011 Conference Paper http://hdl.handle.net/20.500.11937/23221 10.1109/ICARA.2011.6144926 IEEE fulltext
spellingShingle mining
localization
dynamic illumination
LeCras, Jared
Paxman, Jonathan
Saracik, Brad
Vision Based Localization under Dynamic Illumination
title Vision Based Localization under Dynamic Illumination
title_full Vision Based Localization under Dynamic Illumination
title_fullStr Vision Based Localization under Dynamic Illumination
title_full_unstemmed Vision Based Localization under Dynamic Illumination
title_short Vision Based Localization under Dynamic Illumination
title_sort vision based localization under dynamic illumination
topic mining
localization
dynamic illumination
url http://hdl.handle.net/20.500.11937/23221