Influence of Water Droplet Contamination for Transparency Segmentation

TL;DR

This paper investigates how water droplet contamination affects the segmentation of transparent objects in computer vision, introducing a new dataset and demonstrating improved segmentation with contamination severity detection.

Contribution

It presents a novel dataset with water droplet contamination levels and shows that contamination can improve segmentation and be used to assess severity.

Findings

Contaminated transparent objects are easier to segment.

State-of-the-art models can distinguish contamination severity levels.

Contamination detection can enhance system resilience and maintenance.

Abstract

Computer vision techniques are on the rise for industrial applications, like process supervision and autonomous agents, e.g., in the healthcare domain and dangerous environments. While the general usability of these techniques is high, there are still challenging real-world use-cases. Especially transparent structures, which can appear in the form of glass doors, protective casings or everyday objects like glasses, pose a challenge for computer vision methods. This paper evaluates the combination of transparent objects in conjunction with (naturally occurring) contamination through environmental effects like hazing. We introduce a novel publicly available dataset containing 489 images incorporating three grades of water droplet contamination on transparent structures and examine the resulting influence on transparency handling. Our findings show, that contaminated transparent objects are easier to segment and that we are able to distinguish between different severity levels of contamination with a current state-of-the art machine-learning model. This in turn opens up the possibility to enhance computer vision systems regarding resilience against, e.g., datashifts through contaminated protection casings or implement an automated cleaning alert.