A COMPUTER MODEL FOR DETECTING AIRPORT LUGGAGE’S DIMENSIONS USING LOW-COST DEPTH SENSORS¶
Abstract¶
A factor that impacts airlines’ resources is the verification of luggage’s dimensions during the boarding process. To check conformity, companies usually rely on a human operator. To mitigate this issue, companies are investing in automatic self bag drop systems. This process introduces new technological challenges, since, in this scenario, the verification of the conformity of the luggage dimensions is delegated to the passenger, which can lead to errors. In addition, current solutions use specific computing devices, such as laser scanners, that are expressive in size and cost, which may require interventions in the airport infrastructure. In this sense, this work proposes a model to measure luggage through a low-cost depth sensor as an alternative to obtain and verify its dimension. To do so, we developed an algorithm that obtains a 3D point cloud of the luggage surface through a Microsoft Kinect V2 sensor. After that, we generate the minimum polygon that cover these points, a process called convex hull. By doing so, we are able to obtain the luggage’s dimensions. To test our approach, we implemented our model in MATLAB and created a real-world prototype. The results indicate that the mean absolute error is 1.33cm, 1.90cm, and 0.52 cm for the width, length, and depth, respectively, which indicates that this technology has the potential to become an alternative technology to detect the luggage’s dimensions.
Download¶
Citing¶
@inproceedings{SIT149,
author = {VITOR DE ALMEIDA SILVA; MARCOS PAULINO RORIZ JUNIOR; MICHELLE CARVALHO GALVÃO DA SILVA PINTO BANDEIRA},
title = {A COMPUTER MODEL FOR DETECTING AIRPORT LUGGAGE'S DIMENSIONS USING LOW-COST DEPTH SENSORS},
booktitle = {Proceedings of the 2022 Air Transportation Symposium},
series = {SITRAER 2022},
year = {2022},
pages = {355-364},
publisher = {SBTA - Brazilian Air Transportation Research Society},
address = {São José dos Campos, Brazil,}
}
License¶
The contents of this article can be used given that the authors are cited. The reproduction of the whole article in any medium is forbidden, unless authorized by the authors.