A probabilistic model for appearance-based robot localization

Kröse, B.J.A.; Vlassis, Nikos; Bunschoten, R.; Motomura, Yoichi

doi:10.1016/s0262-8856(00)00086-x

Cited by 127 publications

(63 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [9] was shown the effectiveness of using a small number of Fourier coefficients to characterize an image: that method both reduce drastically the dimension of the information to be stored and proved to be enough to discriminate different images, without the need of image alignment as in [1] [5] [8].…”

Section: Fourier Signaturementioning

confidence: 99%

Fourier Signature in Log-Polar Images

Gasperin¹,

Ardito²,

Grisan

et al. 2007

Robot Vision

View full text Add to dashboard Cite

Abstract. In image-based robot navigation, the robot localises itself by comparing images taken at its current position with a set of reference images stored in its memory. The problem is then reduced to find a suitable metric to compare images, and then to store and compare efficiently a set of images that grows quickly as the environment widen. The coupling of omnidirectional image with Fouriersignature has been previously proved to be a viable framework for image-based localization task, both with regard to data reduction and to image comparison. In this paper, we investigate the possibility of using a space variant camera, with the photosensitive elements organised in a log polar layout, thus resembling the organization of the primate retina. We show that an omnidirectional camera using this retinal camera, provides a further data compression and excellent image comparison capability, even with very few components in the Fourier signature.

show abstract

Section: Fourier Signaturementioning

confidence: 99%

Fourier Signature in Log-Polar Images

Gasperin¹,

Ardito²,

Grisan

et al. 2007

Robot Vision

View full text Add to dashboard Cite

show abstract

“…Appearance means special regions in an image. Some of these regions are distinguish marks in a transform space [11][12] [13], others are regions matching best with existed templates [14]. The robot extracts these appearances from currently observed images, and corrects the error while executing the commands.…”

Section: Review Of Visual Based Navigationmentioning

confidence: 99%

“…The robot extracts these appearances from currently observed images, and corrects the error while executing the commands. Normally, omni-images [13], panoramic images [11], or stereo visions [14] can provide more information and better performance in these methods.…”

Section: Review Of Visual Based Navigationmentioning

confidence: 99%

Visual Navigation of a Museum Guide Robot

Shen

2006

2006 6th World Congress on Intelligent Control and Automation

View full text Add to dashboard Cite

. Abstract -This paper presents a novel approach to visual navigation of a museum guide robot -ATLAS, which can detect visitors nearby and interact with them via voice and a touching screen. The software architecture of the robot is presented to show how this complex system is organized. Furthermore, a fast and robust multi-sensor based navigation is explained. Some experimental results are presented to show the feasibility and performance of the proposed system.

show abstract

“…Also, to help vision-based robot positioning [55] and activity recognition [51] in the working environment, rich and often non-independent features are necessary to be initially computed from sensory data, without prior knowledge of which features would be critical to the problem at hand. This means that a large number of features may result though not all are essential [26,36]. Besides, the large amount of features generated puts high computational demands on the robot control process [28].…”

Section: Resultsmentioning

confidence: 99%

Feature Selection Ensemble

Shen¹,

Diao²,

Su³

EPiC Series in Computing

View full text Add to dashboard Cite

Many strategies have been exploited for the task of feature selection, in an effort to identify more compact and better quality feature subsets. Such techniques typically involve the use of an individual feature significance evaluation, or a measurement of feature subset consistency, that work together with a search algorithm in order to determine a quality subset. Feature selection ensemble aims to combine the outputs of multiple feature selectors, thereby producing a more robust result for the subsequent classifier learning tasks. In this paper, three novel implementations of the feature selection ensemble concept are introduced, generalising the ensemble approach so that it can be used in conjunction with many subset evaluation techniques, and search algorithms. A recently developed heuristic algorithm: harmony search is employed to demonstrate the approaches. Results of experimental comparative studies are reported in order to highlight the benefits of the present work. The paper ends with a proposal to extend the application of feature selection ensemble to aiding the development of biped robots (inspired by the authors' involvement in the joint celebration of Olympic and the centenary of the birth of Alan Turing).

show abstract

A probabilistic model for appearance-based robot localization

Cited by 127 publications

References 13 publications

Fourier Signature in Log-Polar Images

Fourier Signature in Log-Polar Images

Visual Navigation of a Museum Guide Robot

Feature Selection Ensemble

Contact Info

Product

Resources

About