Shady dealings: Robust, long-term visual localisation using illumination invariance

McManus, Colin; Churchill, Winston; Maddern, William; Stewart, Alexander D.; Newman, Paul

doi:10.1109/icra.2014.6906961

Cited by 121 publications

(88 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Da mesma forma, a transformação adiciona ruídos à imagem de saída (MCMANUS et al, 2014), além do fato de que eventualmente diferentes reflectâncias podem estar confundidas no espaço de cor gerado.…”

Section: Espaço De Cor Invariante à Iluminaçãounclassified

Análise experimental de algoritmos de constância de cor e segmentação para detecção de mudas de plantas

Perissini¹

View full text Add to dashboard Cite

Section: Espaço De Cor Invariante à Iluminaçãounclassified

Análise experimental de algoritmos de constância de cor e segmentação para detecção de mudas de plantas

Perissini¹

View full text Add to dashboard Cite

“…One of the popular methods [22] calculates illumination-invariant images by exploiting the fact that the wavelength distribution of the main outdoor illuminant, the sun, is known. This method improves robot localization and navigation in outdoor environments [23,24,25,26], but can cope only with changes caused by varying outdoor illumination during the day. A recent work by Mount and Milford also reported that low-light cameras [27] can provide images that allow reliable day/night localisation.…”

Section: Visual Navigation In Changing Environmentsmentioning

confidence: 99%

Image features for visual teach-and-repeat navigation in changing environments

Krajník

Cristóforis

Kusumam

et al. 2017

Robotics and Autonomous Systems

View full text Add to dashboard Cite

We present an evaluation of standard image features in the context of long-term visual teach-and-repeat navigation of mobile robots, where the environment exhibits significant changes in appearance caused by seasonal weather variations and daily illumination changes. We argue that for long-term autonomous navigation, the viewpoint-, scaleand rotation-invariance of the standard feature extractors is less important than their robustness to the mid-and longterm environment appearance changes. Therefore, we focus our evaluation on the robustness of image registration to variable lighting and naturally-occurring seasonal changes. We combine detection and description components of different image extractors and evaluate their performance on five datasets collected by mobile vehicles in three different outdoor environments over the course of one year. Moreover, we propose a trainable feature descriptor based on a combination of evolutionary algorithms and Binary Robust Independent Elementary Features, which we call GRIEF (Generated BRIEF). In terms of robustness to seasonal changes, the most promising results were achieved by the SpG/CNN and the STAR/GRIEF feature, which was slightly less robust, but faster to calculate.

show abstract

“…In the papers [4], [3], [5], [6] the method was used to improve long-term localization of mobile robots in outdoor environments that are subject to significant appearance changes due to varying illumination. The paper [3] presents a system that utilizes traditional feature-based visual localization on both standard and intrinsic images and demonstrates the improvement of localization robustness on off-line datasets. The article [4] further elaborates on the method by showing that it improves segmentation and interpretation of outdoor urban scenes.…”

Section: Related Workmentioning

confidence: 99%

“…While the use of intrinsic images for shadow removal in outdoor environments is not novel, the technique has been so far used to improve robustness of vision-based localization [3], [4], [5], [6]. However, our method does not rely on a priori known maps, but simply steers the robot along pathways which are detected in intrinsic images.…”

Section: Introductionmentioning

confidence: 99%

Visual road following using intrinsic images

Krajník

Blazicek

Santos

2015

2015 European Conference on Mobile Robots (ECMR)

View full text Add to dashboard Cite

Abstract-We present a real-time visual-based road following method for mobile robots in outdoor environments. The approach combines an image processing method, that allows to retrieve illumination invariant images, with an efficient path following algorithm. The method allows a mobile robot to autonomously navigate along pathways of different types in adverse lighting conditions using monocular vision.To validate the proposed method, we have evaluated its ability to correctly determine boundaries of pathways in a challenging outdoor dataset. Moreover, the method's performance was tested on a mobile robotic platform that autonomously navigated long paths in urban parks. The experiments demonstrated that the mobile robot was able to identify outdoor pathways of different types and navigate through them despite the presence of shadows that significantly influenced the paths' appearance.

show abstract

Shady dealings: Robust, long-term visual localisation using illumination invariance

Cited by 121 publications

References 15 publications

Análise experimental de algoritmos de constância de cor e segmentação para detecção de mudas de plantas

Análise experimental de algoritmos de constância de cor e segmentação para detecção de mudas de plantas

Image features for visual teach-and-repeat navigation in changing environments

Visual road following using intrinsic images

Contact Info

Product

Resources

About