MP-Stain-Detector: A Learning-Based Stain Detection Method with a Multispectral Polarization Optical System
Sensors · 08.03.2026 · 26 (5) · 1703
DOI: 10.3390/s26051703 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 08.03.2026. Verfasst von Shun Zou und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Postdoctoral Science Foundation, National Key R&D Program of Hubei Province, National Key R&D Program of Hubei Province.
Abstract (Originalsprache)
Stain detection is crucial for robotic sweepers, enabling them to assess environmental hygiene and execute precise cleaning tasks. However, in complex indoor scenarios, highly accurate stain detection remains a significant challenge, as the visual features of stains are often obscured by ambient light, background textures, and specular reflections. Most existing deep learning methods rely predominantly on standard Red-Green-Blue (RGB) images, which lack sufficient discriminative features to robustly distinguish stains from complex backgrounds or accurately classify diverse contaminants. To address these limitations, we propose a deep learning stain detection framework integrated with a multispectral polarization optical system. First, to extract discriminative optical features, we design a lightweight multispectral polarization optical module tailored for integration into robotic sweepers. It captures rich spectral and polarization features while effectively suppressing specular reflections. Second, to enhance feature representation capabilities, we develop a multispectral polarization (MP)-based stain detector, named MP-stain-detector, which fuses spectral composition data with polarization texture features. Third, to support rigorous model training and evaluation, we construct a comprehensive dataset, the MP-Stain-dataset, collected in real-world home scenarios. Experiments on the MP-Stain-dataset demonstrate that our method improves the overall mean accuracy by 2.44%, and by 5.72% for the challenging light-colored liquid category compared to conventional approaches.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China.
- Wuhan National Laboratory for Optoelectronics, Wuhan 430074, China.
- Hubei Optics Valley Laboratory, Wuhan 430074, China.
- Qingdao Haier Intelligent Technology R&D Co., Qingdao 266103, China.
ORCID-Profile: Shun Zou, Zuyuan Zhu, You Yang
Förderung
- China Postdoctoral Science Foundation
- National Key R&D Program of Hubei Province
- National Key R&D Program of Hubei Province
Zitieren
APA
Zou, S., An, P., Liu, X., Zhu, Z., Song, Y., Song, T., & Yang, Y. (2026). MP-Stain-Detector: A Learning-Based Stain Detection Method with a Multispectral Polarization Optical System. Sensors, 26(5), 1703. https://doi.org/10.3390/s26051703
Vancouver
Zou S, An P, Liu X, Zhu Z, Song Y, Song T, et al. MP-Stain-Detector: A Learning-Based Stain Detection Method with a Multispectral Polarization Optical System. Sensors. 2026;26(5):1703. doi:10.3390/s26051703
BibTeX
@article{Zou2026,
author = {Zou, Shun and An, Pei and Liu, Xiaoming and Zhu, Zuyuan and Song, Yan and Song, Tao and Yang, You},
title = {MP-Stain-Detector: A Learning-Based Stain Detection Method with a Multispectral Polarization Optical System},
journal = {Sensors},
year = {2026},
volume = {26},
number = {5},
pages = {1703},
doi = {10.3390/s26051703}
}
EUVIMED