Per-Pixel Water Detection on Surfaces with Unknown Reflectance
Summary :
Water detection is important for machine vision applications such as visual inspection and robot motion planning. In this paper, we propose an approach to per-pixel water detection on unknown surfaces with a hyperspectral image. Our proposed method is based on the water spectral characteristics: water is transparent for visible light but translucent/opaque for near-infrared light and therefore the apparent near-infrared spectral reflectance of a surface is smaller than the original one when water is present on it. Specifically, we use a linear combination of a small number of basis vector to approximate the spectral reflectance and estimate the original near-infrared reflectance from the visible reflectance (which does not depend on the presence or absence of water) to detect water. We conducted a number of experiments using real images and show that our method, which estimates near-infrared spectral reflectance based on the visible spectral reflectance, has better performance than existing techniques.
- Publication
- IEICE TRANSACTIONS on Information Vol.E104-D No.10 pp.1555-1562
- Publication Date
- 2021/10/01
- Publicized
- 2021/07/06
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2021PCP0002
- Type of Manuscript
- Special Section PAPER (Special Section on Picture Coding and Image Media Processing)
- Category
Authors
Chao WANG
Kyushu Institute of Technology
Michihiko OKUYAMA
Kyushu Institute of Technology
Ryo MATSUOKA
The University of Kitakyushu
Takahiro OKABE
Kyushu Institute of Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Chao WANG, Michihiko OKUYAMA, Ryo MATSUOKA, Takahiro OKABE, "Per-Pixel Water Detection on Surfaces with Unknown Reflectance" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 10, pp. 1555-1562, October 2021, doi: 10.1587/transinf.2021PCP0002.
Abstract: Water detection is important for machine vision applications such as visual inspection and robot motion planning. In this paper, we propose an approach to per-pixel water detection on unknown surfaces with a hyperspectral image. Our proposed method is based on the water spectral characteristics: water is transparent for visible light but translucent/opaque for near-infrared light and therefore the apparent near-infrared spectral reflectance of a surface is smaller than the original one when water is present on it. Specifically, we use a linear combination of a small number of basis vector to approximate the spectral reflectance and estimate the original near-infrared reflectance from the visible reflectance (which does not depend on the presence or absence of water) to detect water. We conducted a number of experiments using real images and show that our method, which estimates near-infrared spectral reflectance based on the visible spectral reflectance, has better performance than existing techniques.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021PCP0002/_p
Copy
@ARTICLE{e104-d_10_1555,
author={Chao WANG, Michihiko OKUYAMA, Ryo MATSUOKA, Takahiro OKABE, },
journal={IEICE TRANSACTIONS on Information},
title={Per-Pixel Water Detection on Surfaces with Unknown Reflectance},
year={2021},
volume={E104-D},
number={10},
pages={1555-1562},
abstract={Water detection is important for machine vision applications such as visual inspection and robot motion planning. In this paper, we propose an approach to per-pixel water detection on unknown surfaces with a hyperspectral image. Our proposed method is based on the water spectral characteristics: water is transparent for visible light but translucent/opaque for near-infrared light and therefore the apparent near-infrared spectral reflectance of a surface is smaller than the original one when water is present on it. Specifically, we use a linear combination of a small number of basis vector to approximate the spectral reflectance and estimate the original near-infrared reflectance from the visible reflectance (which does not depend on the presence or absence of water) to detect water. We conducted a number of experiments using real images and show that our method, which estimates near-infrared spectral reflectance based on the visible spectral reflectance, has better performance than existing techniques.},
keywords={},
doi={10.1587/transinf.2021PCP0002},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Per-Pixel Water Detection on Surfaces with Unknown Reflectance
T2 - IEICE TRANSACTIONS on Information
SP - 1555
EP - 1562
AU - Chao WANG
AU - Michihiko OKUYAMA
AU - Ryo MATSUOKA
AU - Takahiro OKABE
PY - 2021
DO - 10.1587/transinf.2021PCP0002
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2021
AB - Water detection is important for machine vision applications such as visual inspection and robot motion planning. In this paper, we propose an approach to per-pixel water detection on unknown surfaces with a hyperspectral image. Our proposed method is based on the water spectral characteristics: water is transparent for visible light but translucent/opaque for near-infrared light and therefore the apparent near-infrared spectral reflectance of a surface is smaller than the original one when water is present on it. Specifically, we use a linear combination of a small number of basis vector to approximate the spectral reflectance and estimate the original near-infrared reflectance from the visible reflectance (which does not depend on the presence or absence of water) to detect water. We conducted a number of experiments using real images and show that our method, which estimates near-infrared spectral reflectance based on the visible spectral reflectance, has better performance than existing techniques.
ER -
English
