Enhancing Visual Perception in Foggy Conditions via Multiclass Fog Density Modeling
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors study how self-driving cars can better 'see' in foggy weather by creating fake fog effects on existing driving data. They made separate computer models to handle different levels of fog instead of using one model for all conditions. Their tests showed that models trained specifically for heavy fog did much better at spotting things, especially in very thick fog. This suggests using multiple fog-specific models can help autonomous cars drive safer in bad weather. They plan to try this approach with other sensors and different weather in the future.
autonomous drivingfog simulationperception modeldepth imagesWaymo datasetrecalladverse weatherLiDARradar
Authors
Mohamad Mofeed Chaar, Galia Weidl
Abstract
Autonomous driving (AD) systems have advanced rapidly over the past decade; however, robust perception under adverse weather conditions remains a major challenge, particularly in dense fog. In this work, we investigate fog-aware perception using synthetically generated fog data derived from the Waymo dataset. To support fog simulation, depth images are generated using an iterative learning approach. We consider five fog-density levels: clear, light fog, moderate fog, heavy fog, and very heavy fog. Instead of training a single unified model across all conditions, we train separate perception models for each fog-density level. Experimental results show that density-specific training improves performance in severe fog conditions. In particular, for the very heavy fog class, recall improves from 0.076 to 0.232, corresponding to an absolute gain of 15.6 percentage points. These findings suggest that deploying multiple specialized models, rather than a single general-purpose model, can improve perception robustness for autonomous vehicles under challenging visibility conditions. Future work will extend this strategy to additional sensing modalities, including LiDAR and radar, and evaluate generalization across diverse weather scenarios.