Hybrid contrast-aware detection for automotive vision systems

Abstract

en

Modern vehicles are equipped with a wide range of Advanced Driver Assistance Systems (ADAS) that rely heavily on camera-based perception. Reliable visibility estimation – particularly under fog condition – remains a significant challenge. Accurate fog detection can enable proactive system responses, such as automatic activation of fog lights, and enhance operational safety. We present a contrast-aware anomaly detection framework for image-based fog detection. Our algorithm combines multi-scale Difference of Gaussians responses and Gaussian-weighted local Root Mean Squared contrast with a convolutional autoencoder. The model is trained on clear imagery and detects fog as a reconstruction deviation from the learned clear distribution. It provides interpretable basis for visibility-aware systems in automotive environments.

2026-05-04

The Eurographics Association

978-3-03868-300-1

Eurographics 2026 – Posters

2