Wetness and color from a single multispectral image

Mihoko Shimano, Hiroki Okawa, Yuta Asano, Ryoma Bise, Ko Nishino, Imari Sato

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Visual recognition of wet surfaces and their degrees of wetness is important for many computer vision applications. It can inform slippery spots on a road to autonomous vehicles, muddy areas of a trail to humanoid robots, and the freshness of groceries to us. In the past, monochromatic appearance change, the fact that surfaces darken when wet, has been modeled to recognize wet surfaces. In this paper, we show that color change, particularly in its spectral behavior, carries rich information about a wet surface. We derive an analytical spectral appearance model of wet surfaces that expresses the characteristic spectral sharpening due to multiple scattering and absorption in the surface. We derive a novel method for estimating key parameters of this spectral appearance model, which enables the recovery of the original surface color and the degree of wetness from a single observation. Applied to a multispectral image, the method estimates the spatial map of wetness together with the dry spectral distribution of the surface. To our knowledge, this work is the first to model and leverage the spectral characteristics of wet surfaces to revert its appearance. We conduct comprehensive experimental validation with a number of wet real surfaces. The results demonstrate the accuracy of our model and the effectiveness of our method for surface wetness and color estimation.

Original languageEnglish
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages321-329
Number of pages9
ISBN (Electronic)9781538604571
DOIs
Publication statusPublished - Nov 6 2017
Externally publishedYes
Event30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, United States
Duration: Jul 21 2017Jul 26 2017

Publication series

NameProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Volume2017-January

Other

Other30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
CountryUnited States
CityHonolulu
Period7/21/177/26/17

Fingerprint

Color
Multiple scattering
Computer vision
Robots
Recovery

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Shimano, M., Okawa, H., Asano, Y., Bise, R., Nishino, K., & Sato, I. (2017). Wetness and color from a single multispectral image. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 (pp. 321-329). (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CVPR.2017.42

Wetness and color from a single multispectral image. / Shimano, Mihoko; Okawa, Hiroki; Asano, Yuta; Bise, Ryoma; Nishino, Ko; Sato, Imari.

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 321-329 (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shimano, M, Okawa, H, Asano, Y, Bise, R, Nishino, K & Sato, I 2017, Wetness and color from a single multispectral image. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 321-329, 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, United States, 7/21/17. https://doi.org/10.1109/CVPR.2017.42
Shimano M, Okawa H, Asano Y, Bise R, Nishino K, Sato I. Wetness and color from a single multispectral image. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 321-329. (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017). https://doi.org/10.1109/CVPR.2017.42
Shimano, Mihoko ; Okawa, Hiroki ; Asano, Yuta ; Bise, Ryoma ; Nishino, Ko ; Sato, Imari. / Wetness and color from a single multispectral image. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 321-329 (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017).
@inproceedings{cda0f780abf64e84a305001abf693cfb,
title = "Wetness and color from a single multispectral image",
abstract = "Visual recognition of wet surfaces and their degrees of wetness is important for many computer vision applications. It can inform slippery spots on a road to autonomous vehicles, muddy areas of a trail to humanoid robots, and the freshness of groceries to us. In the past, monochromatic appearance change, the fact that surfaces darken when wet, has been modeled to recognize wet surfaces. In this paper, we show that color change, particularly in its spectral behavior, carries rich information about a wet surface. We derive an analytical spectral appearance model of wet surfaces that expresses the characteristic spectral sharpening due to multiple scattering and absorption in the surface. We derive a novel method for estimating key parameters of this spectral appearance model, which enables the recovery of the original surface color and the degree of wetness from a single observation. Applied to a multispectral image, the method estimates the spatial map of wetness together with the dry spectral distribution of the surface. To our knowledge, this work is the first to model and leverage the spectral characteristics of wet surfaces to revert its appearance. We conduct comprehensive experimental validation with a number of wet real surfaces. The results demonstrate the accuracy of our model and the effectiveness of our method for surface wetness and color estimation.",
author = "Mihoko Shimano and Hiroki Okawa and Yuta Asano and Ryoma Bise and Ko Nishino and Imari Sato",
year = "2017",
month = "11",
day = "6",
doi = "10.1109/CVPR.2017.42",
language = "English",
series = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "321--329",
booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",
address = "United States",

}

TY - GEN

T1 - Wetness and color from a single multispectral image

AU - Shimano, Mihoko

AU - Okawa, Hiroki

AU - Asano, Yuta

AU - Bise, Ryoma

AU - Nishino, Ko

AU - Sato, Imari

PY - 2017/11/6

Y1 - 2017/11/6

N2 - Visual recognition of wet surfaces and their degrees of wetness is important for many computer vision applications. It can inform slippery spots on a road to autonomous vehicles, muddy areas of a trail to humanoid robots, and the freshness of groceries to us. In the past, monochromatic appearance change, the fact that surfaces darken when wet, has been modeled to recognize wet surfaces. In this paper, we show that color change, particularly in its spectral behavior, carries rich information about a wet surface. We derive an analytical spectral appearance model of wet surfaces that expresses the characteristic spectral sharpening due to multiple scattering and absorption in the surface. We derive a novel method for estimating key parameters of this spectral appearance model, which enables the recovery of the original surface color and the degree of wetness from a single observation. Applied to a multispectral image, the method estimates the spatial map of wetness together with the dry spectral distribution of the surface. To our knowledge, this work is the first to model and leverage the spectral characteristics of wet surfaces to revert its appearance. We conduct comprehensive experimental validation with a number of wet real surfaces. The results demonstrate the accuracy of our model and the effectiveness of our method for surface wetness and color estimation.

AB - Visual recognition of wet surfaces and their degrees of wetness is important for many computer vision applications. It can inform slippery spots on a road to autonomous vehicles, muddy areas of a trail to humanoid robots, and the freshness of groceries to us. In the past, monochromatic appearance change, the fact that surfaces darken when wet, has been modeled to recognize wet surfaces. In this paper, we show that color change, particularly in its spectral behavior, carries rich information about a wet surface. We derive an analytical spectral appearance model of wet surfaces that expresses the characteristic spectral sharpening due to multiple scattering and absorption in the surface. We derive a novel method for estimating key parameters of this spectral appearance model, which enables the recovery of the original surface color and the degree of wetness from a single observation. Applied to a multispectral image, the method estimates the spatial map of wetness together with the dry spectral distribution of the surface. To our knowledge, this work is the first to model and leverage the spectral characteristics of wet surfaces to revert its appearance. We conduct comprehensive experimental validation with a number of wet real surfaces. The results demonstrate the accuracy of our model and the effectiveness of our method for surface wetness and color estimation.

UR - http://www.scopus.com/inward/record.url?scp=85044339073&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044339073&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2017.42

DO - 10.1109/CVPR.2017.42

M3 - Conference contribution

AN - SCOPUS:85044339073

T3 - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

SP - 321

EP - 329

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -