ARTIFICIAL INTELLIGENCE BASED HELIPAD DETECTION WITH  CONVOLUTIONAL NEURAL NETWORK

Emad   Ahmed Mohammed; Ahmed  J. Ali; Abdullah Mohammed Abdullah

doi:10.56286/ntujet.v3i1.799

Authors

Emad Ahmed Mohammed Northern Technical University
Ahmed J. Ali Northern Technical University
Abdullah Mohammed Abdullah Northern Technical University, Engineering Technical College of Mosul ,IRAQ

DOI:

https://doi.org/10.56286/ntujet.v3i1.799

Keywords:

Helipad detection, YOLOv8, YOLOv5, Landing zone safety.

Abstract

When a malfunction occurs in the helicopter or the pilot faints during a flight or performing a duty, and in order to ensure the safety of the pilot and the helicopter, a system must be available to detect the helicopter landing pads, so that the helicopter can land at the airport. Closest safe place immediately. This study focuses on helicopter landing pad detection using YOLOv8 and YOLOv5 models. A dataset of 1877 images collected from the Internet was used to evaluate the performance of the models. YOLOv8 showed good performance in helipad detection with 96.7% accuracy and 95.8% recall, resulting in an average accuracy (mAP@0.5) of 98.8%. As for YOLOv5, it reached 95.1% precision, 95.8% recall, and 97.5% mAP@0.5. Both models showed good results, but YOLOv8 outperformed it by a small percent.