# MP-Stain-Detector: A Learning-Based Stain Detection Method with a Multispectral Polarization Optical System

## TL;DR

This paper introduces a new stain detection method for robotic sweepers using a multispectral polarization optical system to improve accuracy in complex indoor environments.

## Contribution

A novel deep learning framework with a lightweight multispectral polarization optical module and a new dataset for stain detection in real-world home scenarios.

## Key findings

- The proposed method improves overall mean accuracy by 2.44% compared to conventional approaches.
- It achieves a 5.72% improvement in accuracy for light-colored liquid stains.
- A new dataset, MP-Stain-dataset, was created for real-world home stain detection evaluation.

## Abstract

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.