Augmenting traffic information display in an air traffic tower simulator

• Main Author: Ang, Kai
• Other Authors: Sameer Alam
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision; Engineering::Aeronautical engineering::Accidents and air safety; Engineering::Mechanical engineering
• Online Access: https://hdl.handle.net/10356/150456
• Institution: Nanyang Technological University

Object Detection has been used extensively for identifying and recognizing objects using computer vision. While the object detection algorithm is undeniably able to identify and track objects, there have been few field tests conducted due to the lack of an interface where the algorithm is integrated into the field. It means that an operator cannot utilize object detection without diverting his attention away from his current focus. This report explores the usage of computer vision tasked for drone detection in a Simulated Airport Control Tower environment by Air Traffic Control Officers (ATCOs) where the Microsoft HoloLens 2 is used as the platform. Having an actual drone flying in the vicinity in an airport is a safety violation and against the law, as such, scenarios can only be simulated in a virtual environment. As such, the quality of data extracted for computer vision training affects the outcome of the experiments. The results conclude that there is a room for improvement in developing an algorithm that detects drones at far distances with a moving camera.