Evaluating Synthetic Data for Baggage Trolley Detection in Airport Logistics
This work provides a practical solution for improving automated baggage trolley detection in airports, benefiting airport logistics managers by reducing data annotation costs and overcoming data scarcity issues due to privacy regulations.
This paper addresses the challenge of baggage trolley detection in airports, where data collection is restricted and existing datasets are inadequate. The authors developed a synthetic data generation pipeline using a Digital Twin of Algiers International Airport, producing richly annotated data. They found that training with synthetic data combined with only 40% of real annotations matched or surpassed the performance of using 100% real data, achieving 0.94 mAP@50 and 0.77 mAP@50-95, while reducing annotation effort by 25-35%.
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.