Simulating Refractive Distortions and Weather-Induced Artifacts for Resource-Constrained Autonomous Perception

2025-07-07

AI Summary

Autonomous driving perception in resource-constrained regions—particularly Africa—is hindered by scarce labeled data and the absence of benchmark datasets covering diverse road types (urban, rural, unpaved) and adverse weather conditions. Method: This paper introduces the first Africa-specific procedural image augmentation pipeline, combining physics-informed refractive distortion modeling (thin-plate splines with divergence-free warping), Perlin-noise-driven dynamic fog simulation (uniform and non-uniform), and lens flare synthesis—all operating on low-cost monocular dashcam footage to generate high-fidelity corrupted samples. Contribution/Results: We release an open-source augmentation toolkit, annotated data shards, and a standardized benchmark evaluating three representative image restoration models. Experiments demonstrate significant improvements in model robustness under complex, low-quality environmental conditions. The framework provides a reproducible, scalable foundation for autonomous perception research in low-resource settings.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The scarcity of autonomous vehicle datasets from developing regions, particularly across Africa's diverse urban, rural, and unpaved roads, remains a key obstacle to robust perception in low-resource settings. We present a procedural augmentation pipeline that enhances low-cost monocular dashcam footage with realistic refractive distortions and weather-induced artifacts tailored to challenging African driving scenarios. Our refractive module simulates optical effects from low-quality lenses and air turbulence, including lens distortion, Perlin noise, Thin-Plate Spline (TPS), and divergence-free (incompressible) warps. The weather module adds homogeneous fog, heterogeneous fog, and lens flare. To establish a benchmark, we provide baseline performance using three image restoration models. To support perception research in underrepresented African contexts, without costly data collection, labeling, or simulation, we release our distortion toolkit, augmented dataset splits, and benchmark results.

Problem

• Lack of autonomous vehicle datasets from developing regions
• Simulating realistic refractive distortions and weather artifacts
• Enhancing perception in low-resource African driving scenarios

Innovation

• Procedural augmentation pipeline for dashcam footage
• Simulates refractive distortions and weather artifacts
• Includes lens distortion, fog, and flare effects