2021/08/25 by WT Alshaibani, M. Helvacı, Al-Shaibani, WT +5
Computer Science · Engineering · Environmental Science · #Advanced Neural Network Applications #Automated Road and Building Extraction #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Remote Sensing and LiDAR Applications #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2108.11118
openalex publication_date 2021/08/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
One of the most difficult jobs in remote sensing is dealing with traffic\nbottlenecks at airports. This fact has been confirmed by several studies\nattempting to resolve this issue. Among a wide range of approaches employed the\nmost successful methods have been based on airplane object recognition using\nsatellite images as datasets for deep learning models. Airplane object\nidentification is not a viable method for resolving traffic congestion. There\nare several types of airplanes at the airport each with its own set of\nrequirements and specifications.Utilizing satellite pictures will require the\nuse of complex equipment which is a financial burden. In this work a universal\nlow-cost and efficient solution for airport traffic congestion is proposed.\nDrone-captured aerial pictures are used to train and assess a Mask Region\nConvolution Neural Network model. This model can detect the presence of any\naircraft in a photograph and pinpoint its location. It also includes mask\nestimations to properly identify each detected airplane type based on the\nestimated surface area and cabin length which are crucial variables in\ndistinguishing planes. The study is conducted using Microsoft Common Object in\nContext COCO metrics average accuracies and a confusion matrix all of which\ndemonstrate the approach's potential in providing valuable aid for dealing with\ntraffic congestion at airports.\n