Hybrid contrast-aware detection for automotive vision systems

Hybrid contrast-aware detection for automotive vision systems

Abstrakt

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.

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.

PROCHÁZKOVÁ, J.; MIKULÁČEK, P.; ŠTARHA, P.

04.05.2026

The Eurographics Association

978-3-03868-300-1

Eurographics 2026 - Posters

2

https://diglib.eg.org/items/ed91e29c-e637-4311-8f65-3b7ea278f6cb

Poster_EG2026