New perception of fluffy surfaces

Alexander Kadyrov; Hui Yu; Honghai Liu

doi:10.1109/SMC.2013.719

New perception of fluffy surfaces

Alexander Kadyrov
, Hui Yu
, Honghai Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

287 Downloads (Pure)

Abstract

Scene material recognition is a valuable perceptual ability for robots. However, current methods fail to provide robust solution for indoor surrounding material recognition. As human beings are able to immediately understand properties of surrounding materials, especially when it concerns smooth fluffy materials, we believe robots should be equipped with similar abilities. In this paper we explore a new idea for fluffy surface perception for robots based on above hypothesis. The aim is to enable robots to distinguish smooth and fluffy surfaces without touching them. This is achieved through calculating image matchability map from video cameras. Through measuring the similarity of images captured from different viewpoints, robots are able to immediately recognize whether it is a fluffy material. The method has been validated by primary experiments. Our results show that robots can have a sense of material properties for fluffy materials without touching them or any prior knowledge

Original language	English
Title of host publication	2013 IEEE International Conference Systems, Man, and Cybernetics
Subtitle of host publication	SMC 2013
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4219-4224
ISBN (Print)	9780769551548
DOIs	https://doi.org/10.1109/SMC.2013.719
Publication status	Published - 2013

Access to Document

10.1109/SMC.2013.719

NewPerception_of_Fluffy_SurfacesAccepted author manuscript (Post-print), 587 KB

Cite this

@inproceedings{94e8c1c6aa004102a75aa0c3882a70bc,

title = "New perception of fluffy surfaces",

abstract = "Scene material recognition is a valuable perceptual ability for robots. However, current methods fail to provide robust solution for indoor surrounding material recognition. As human beings are able to immediately understand properties of surrounding materials, especially when it concerns smooth fluffy materials, we believe robots should be equipped with similar abilities. In this paper we explore a new idea for fluffy surface perception for robots based on above hypothesis. The aim is to enable robots to distinguish smooth and fluffy surfaces without touching them. This is achieved through calculating image matchability map from video cameras. Through measuring the similarity of images captured from different viewpoints, robots are able to immediately recognize whether it is a fluffy material. The method has been validated by primary experiments. Our results show that robots can have a sense of material properties for fluffy materials without touching them or any prior knowledge",

author = "Alexander Kadyrov and Hui Yu and Honghai Liu",

year = "2013",

doi = "10.1109/SMC.2013.719",

language = "English",

isbn = "9780769551548",

pages = "4219--4224",

booktitle = "2013 IEEE International Conference Systems, Man, and Cybernetics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

TY - GEN

T1 - New perception of fluffy surfaces

AU - Kadyrov, Alexander

AU - Yu, Hui

AU - Liu, Honghai

PY - 2013

Y1 - 2013

N2 - Scene material recognition is a valuable perceptual ability for robots. However, current methods fail to provide robust solution for indoor surrounding material recognition. As human beings are able to immediately understand properties of surrounding materials, especially when it concerns smooth fluffy materials, we believe robots should be equipped with similar abilities. In this paper we explore a new idea for fluffy surface perception for robots based on above hypothesis. The aim is to enable robots to distinguish smooth and fluffy surfaces without touching them. This is achieved through calculating image matchability map from video cameras. Through measuring the similarity of images captured from different viewpoints, robots are able to immediately recognize whether it is a fluffy material. The method has been validated by primary experiments. Our results show that robots can have a sense of material properties for fluffy materials without touching them or any prior knowledge

AB - Scene material recognition is a valuable perceptual ability for robots. However, current methods fail to provide robust solution for indoor surrounding material recognition. As human beings are able to immediately understand properties of surrounding materials, especially when it concerns smooth fluffy materials, we believe robots should be equipped with similar abilities. In this paper we explore a new idea for fluffy surface perception for robots based on above hypothesis. The aim is to enable robots to distinguish smooth and fluffy surfaces without touching them. This is achieved through calculating image matchability map from video cameras. Through measuring the similarity of images captured from different viewpoints, robots are able to immediately recognize whether it is a fluffy material. The method has been validated by primary experiments. Our results show that robots can have a sense of material properties for fluffy materials without touching them or any prior knowledge

U2 - 10.1109/SMC.2013.719

DO - 10.1109/SMC.2013.719

M3 - Conference contribution

SN - 9780769551548

SP - 4219

EP - 4224

BT - 2013 IEEE International Conference Systems, Man, and Cybernetics

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway

ER -

New perception of fluffy surfaces

Abstract

Access to Document

Fingerprint

Cite this