A Cost-Effective and Climate-Resilient Air Pressure System for Rain Effect Reduction on Automated Vehicle Cameras

TL;DR

This paper introduces a low-cost, scalable hardware system for rain mitigation on vehicle cameras, enhancing perception reliability and supporting sustainability in automated transportation.

Contribution

It presents a novel, cost-effective hardware solution compatible with multiple cameras, improving rain resilience without high costs or hardware changes.

Findings

Increased pedestrian detection accuracy from 8.3% to 41.6%.

Compatible with existing camera systems, supporting scalability.

Supports sustainability by reducing resource use and emissions.

Abstract

Recent advances in automated vehicles have focused on improving perception performance under adverse weather conditions; however, research on physical hardware solutions remains limited, despite their importance for perception critical applications such as vehicle platooning. Existing approaches, such as hydrophilic or hydrophobic lenses and sprays, provide only partial mitigation, while industrial protection systems imply high cost and they do not enable scalability for automotive deployment. To address these limitations, this paper presents a cost-effective hardware solution for rainy conditions, designed to be compatible with multiple cameras simultaneously. Beyond its technical contribution, the proposed solution supports sustainability goals in transportation systems. By enabling compatibility with existing camera-based sensing platforms, the system extends the operational reliability of automated vehicles without requiring additional high-cost sensors or hardware replacements. This approach reduces resource consumption, supports modular upgrades, and promotes more cost-efficient deployment of automated vehicle technologies, particularly in challenging weather conditions where system failures would otherwise lead to inefficiencies and increased emissions. The proposed system was able to increase pedestrian detection accuracy of a Deep Learning model from 8.3% to 41.6%.