Evaluating Synthetic Data for Baggage Trolley Detection in Airport Logistics

2026-03-08

AI Summary

This study addresses the challenge of automatic airport baggage cart detection, which is hindered by the scarcity of real-world data and limitations in existing public datasets regarding diversity, scale, and annotation quality. To overcome this, the authors propose the first high-fidelity digital twin framework for synthetic data generation tailored to airport logistics scenarios. Leveraging NVIDIA Omniverse, they construct a detailed virtual replica of Houari Boumediene International Airport with complex cart layouts and generate high-quality synthetic images annotated with oriented bounding boxes. By integrating the YOLO-OBB model with a hybrid training strategy—combining linear probing and full fine-tuning—the approach achieves mAP@50 of 0.94 and mAP@50-95 of 0.77 using only 40% of real annotated data, matching the performance of models trained entirely on real data while reducing annotation costs by 25%–35%. Results demonstrate high reproducibility, with a standard deviation in mAP@50 below 0.01.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Application Domains: Transportation
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Efficient luggage trolley management is critical for reducing congestion and ensuring asset availability in modern airports. Automated detection systems face two main challenges. First, strict security and privacy regulations limit large-scale data collection. Second, existing public datasets lack the diversity, scale, and annotation quality needed to handle dense, overlapping trolley arrangements typical of real-world operations. To address these limitations, we introduce a synthetic data generation pipeline based on a high-fidelity Digital Twin of Algiers International Airport using NVIDIA Omniverse. The pipeline produces richly annotated data with oriented bounding boxes, capturing complex trolley formations, including tightly nested chains. We evaluate YOLO-OBB using five training strategies: real-only, synthetic-only, linear probing, full fine-tuning, and mixed training. This allows us to assess how synthetic data can complement limited real-world annotations. Our results show that mixed training with synthetic data and only 40 percent of real annotations matches or exceeds the full real-data baseline, achieving 0.94 mAP@50 and 0.77 mAP@50-95, while reducing annotation effort by 25 to 35 percent. Multi-seed experiments confirm strong reproducibility with a standard deviation below 0.01 on mAP@50, demonstrating the practical effectiveness of synthetic data for automated trolley detection.

Problem

• synthetic data
• baggage trolley detection
• airport logistics
• data scarcity
• annotation quality

Innovation

• synthetic data
• digital twin
• oriented bounding box
• YOLO-OBB
• mixed training