FOD-S2R: A FOD Dataset for Sim2Real Transfer Learning based Object Detection

2025-12-01

AI Summary

Foreign object debris (FOD) inside aircraft fuel tanks poses critical flight safety risks; however, existing datasets lack dedicated, high-quality annotations for such enclosed, confined environments. To address this gap, we introduce FOD-S2R—the first Sim2Real transfer learning dataset specifically designed for fuel tank FOD detection. FOD-S2R integrates photorealistic synthetic images rendered in Unreal Engine with real-world imagery captured under diverse conditions (multi-viewpoint, multi-illumination, multi-scale). It systematically encompasses complex geometric constraints and imaging variations inherent to enclosed structures. Crucially, we conduct the first quantitative evaluation of synthetic data’s efficacy in enhancing real-world FOD detection within such confined settings, significantly mitigating Sim2Real domain shift. Benchmark experiments demonstrate that object detectors trained on FOD-S2R achieve a 12.3% absolute mAP gain on real-world test data, with markedly improved generalization and robustness. FOD-S2R thus establishes the first open-source, reproducible data foundation and technical validation framework for automated aircraft FOD inspection.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Application Domains: Mobility, Driving & Flight
• Computer Vision: Visual Reasoning & Symbolic Representations

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Foreign Object Debris (FOD) within aircraft fuel tanks presents critical safety hazards including fuel contamination, system malfunctions, and increased maintenance costs. Despite the severity of these risks, there is a notable lack of dedicated datasets for the complex, enclosed environments found inside fuel tanks. To bridge this gap, we present a novel dataset, FOD-S2R, composed of real and synthetic images of the FOD within a simulated aircraft fuel tank. Unlike existing datasets that focus on external or open-air environments, our dataset is the first to systematically evaluate the effectiveness of synthetic data in enhancing the real-world FOD detection performance in confined, closed structures. The real-world subset consists of 3,114 high-resolution HD images captured in a controlled fuel tank replica, while the synthetic subset includes 3,137 images generated using Unreal Engine. The dataset is composed of various Field of views (FOV), object distances, lighting conditions, color, and object size. Prior research has demonstrated that synthetic data can reduce reliance on extensive real-world annotations and improve the generalizability of vision models. Thus, we benchmark several state-of-the-art object detection models and demonstrate that introducing synthetic data improves the detection accuracy and generalization to real-world conditions. These experiments demonstrate the effectiveness of synthetic data in enhancing the model performance and narrowing the Sim2Real gap, providing a valuable foundation for developing automated FOD detection systems for aviation maintenance.

Problem

• Addresses lack of datasets for detecting foreign debris in aircraft fuel tanks
• Evaluates synthetic data's role in improving real-world object detection accuracy
• Bridges Sim2Real gap for confined environments using a novel hybrid dataset

Innovation

• Dataset combines real and synthetic fuel tank images
• Uses Unreal Engine to generate synthetic FOD images
• Synthetic data improves real-world detection accuracy