Jon Ander Iñiguez de Gordoa

Jon Ander Iñiguez de Gordoa, Iker Alkorta, Itziar Urbieta et al.

This paper presents a comprehensive end-to-end evaluation of an infrastructure-assisted collective perception (ICP) system deployed on a highway using ITS-G5 technology. Open-road tests were conducted in the Bizkaia Connected Corridor (BCC), an operational corridor which covers a winding highway, enabling a realistic assessment of system performance in diverse traffic scenarios. The evaluation included three main aspects: (1) end-to-end Vehicle-to-Everything (V2X) communication latency, with a breakdown of delays introduced by each system component; (2) the effective range of ITS-G5 communications between vehicles and infrastructure; and (3) the perception system, using an independent sensor setup for ground truth annotation to account for errors beyond the detection model, such as synchronization, localization, and calibration inaccuracies. The results reveal that object detection and asynchronous transmission of collective perception messages (CPMs) are major latency bottlenecks, with results showing that synchronizing CPM transmission with local perception can reduce delays by up to 33%. Additionally, onboard perception struggles with detecting objects beyond 50 meters, highlighting the importance of collective perception in highway environments, where communication ranges significantly exceed detection limits. The findings provide valuable insights to optimize ICP deployments, supporting safer and more efficient cooperative mobility systems.

Pablo Alonso, Jon Ander Iñiguez de Gordoa, Juan Diego Ortega et al.

Runway and taxiway pavements are exposed to high stress during their projected lifetime, which inevitably leads to a decrease in their condition over time. To make sure airport pavement condition ensure uninterrupted and resilient operations, it is of utmost importance to monitor their condition and conduct regular inspections. UAV-based inspection is recently gaining importance due to its wide range monitoring capabilities and reduced cost. In this work, we propose a vision-based approach to automatically identify pavement distress using images captured by UAVs. The proposed method is based on Deep Learning (DL) to segment defects in the image. The DL architecture leverages the low computational capacities of embedded systems in UAVs by using an optimised implementation of EfficientNet feature extraction and Feature Pyramid Network segmentation. To deal with the lack of annotated data for training we have developed a synthetic dataset generation methodology to extend available distress datasets. We demonstrate that the use of a mixed dataset composed of synthetic and real training images yields better results when testing the training models in real application scenarios.