Hybrid Contrast-Aware Fog Detection for Automotive Vision Systems
| dc.contributor.author | Procházková, Jana | en_US |
| dc.contributor.author | Mikuláček, Pavel | en_US |
| dc.contributor.author | Štarha, Pavel | en_US |
| dc.contributor.editor | Gerrits, Tim | en_US |
| dc.contributor.editor | Teschner, Matthias | en_US |
| dc.date.accessioned | 2026-04-21T13:52:43Z | |
| dc.date.available | 2026-04-21T13:52:43Z | |
| dc.date.issued | 2026 | |
| dc.description.abstract | 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 exclusively on clear-weather imagery to learn the nominal scene distribution, and visibility degradation is detected as a reconstruction deviation from this learned representation. Evaluation on a separate test set containing clear and fog conditions demonstrates an AUC of 0.91, achieved without using fog samples during training. The framework provides a practical basis for camera-based visibility monitoring in automotive environments. | en_US |
| dc.description.sectionheaders | Posters | |
| dc.description.seriesinformation | Eurographics 2026 - Posters | |
| dc.identifier.doi | 10.2312/egp.20261005 | |
| dc.identifier.isbn | 978-3-03868-300-1 | |
| dc.identifier.issn | 1017-4656 | |
| dc.identifier.pages | 2 pages | |
| dc.identifier.uri | https://doi.org/10.2312/egp.20261005 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.2312/egp20261005 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Computing methodologies → Computer vision; Neural networks | |
| dc.subject | CCS Concepts | |
| dc.subject | Computing methodologies | |
| dc.subject | Computer vision | |
| dc.subject | Neural networks | |
| dc.title | Hybrid Contrast-Aware Fog Detection for Automotive Vision Systems | en_US |