A High-Speed Dynamic Measurement Method for Checked Luggage Dimensions

Abstract

Ensuring compliance with stringent luggage size regulations is critical for operational efficiency and cost control in modern airports. However, conventional measurement methods often face a trade-off between speed and accuracy in the dynamic environment of check-in counters. To address these limitations, we propose a real-time luggage dimension and orientation measurement system based on a single RGB-D camera and the YOLOv8 object detection model. As luggage travels at 0.75 m/s along a conveyor, the system first detects and classifies each item, then combines two-dimensional image analysis with three-dimensional point cloud processing to compute length, width, height, and deflection angle. Trained on 7000 annotated images and validated on 100 physical samples, our method achieves average dimensional errors below 4% and angular deviations within 3°, with a mean processing time of 40 ms per item. Comparative experiments demonstrate that, under similar computational constraints, the proposed approach outperforms traditional techniques in both accuracy and robustness, thereby offering a reliable solution for enhancing real-time luggage assessment at airport check-in terminals.