Spectral analysis for long-term robotic mapping

Krajník, Tomáš; Fentanes, Jaime Pulido; Cielniak, Grzegorz; Dondrup, Christian; Duckett, Tom

doi:10.1109/icra.2014.6907396

Cited by 61 publications

(78 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sünderhauf and Neubert [34,35] mined a dictionary of superpixel-based visual-terms from long-term data and used this dictionary to translate between the appearance of given locations across seasons. Krajnik et al [36] used Fourier analysis to identify the cyclical changes of the environment states and showed that predicting these states for a particular time improves long-term localization [37].…”

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

Self Cite

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

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…We modified the way to obtain l coefficients in [5] to tackle the aforementioned problem by extracting multi-periodic patterns. To obtain a Fourier spectrum of the raw data, we find a frequency ω k with the highest absolute value, then subtract it from the data and transform it again.…”

Section: Spectral Representation In Fourier Transformmentioning

confidence: 99%

“…F (ω) = F T (λ). In [5], l coefficients with the highest absolute value along with their frequencies ω k (for k = 1, . .…”

Section: Spectral Representation In Fourier Transformmentioning

confidence: 99%

“…Our framework is derived from the Frequency Map Enhancement (FreMEn) technique proposed by Krajnik et al [5] for spatio-temporal environment representations in longterm scenarios. The FreMEn technique is based on Fourier analysis in combination with a Bernoulli distribution to represent the binary state of data.…”

Section: Related Workmentioning

confidence: 99%

“…The temporal pattern of activities is identified by the fluctuating number of humans at particular locations. To learn these temporal patterns in each place, we extend a framework introduced in [5] which is based on Bernoulli distributions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Poisson-spectral model for modelling temporal patterns in human data observed by a robot

Jovan

Wyatt

Hawes

et al. 2016

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

Abstract-The efficiency of autonomous robots depends on how well they understand their operating environment. While most of the traditional environment models focus on the spatial representation, long-term mobile robot operation in human populated environments requires that the robots have a basic model of human behaviour.We present a framework that allows us to retrieve and represent aggregate human behaviour in large, populated environments on extended temporal scales. Our approach, based on time-varying Poisson process models and spectral analysis, efficiently retrieves long-term, re-occurring patterns of human activity from robot-gathered observations and uses these patterns to i) predict human activity level at particular times and places and ii) classify locations based on their periodic patterns of activity.The application of our framework on real-world data, gathered by a mobile robot operating in an indoor environment for one month, indicates that its predictive capabilities outperform other temporal modelling methods while being computationally more efficient. The experiment also demonstrates that spectral signatures act as features that allow us to classify room types which semantically match with humans' expectations.

show abstract