Bird Detection System Design at The Airport Using Artificial Intelligence

Khairul Ummah (ITB)
Muhammad Fadly Hidayat
Denni Kurniawan (Department of Mechanical Engineering, Faculty of Engineering, Universiti Teknologi Brunei, Gadong BE1410, Brunei Darussalam)
Zulhanif Zulhanif
Javensius Sembiring (Faculty of Mechanical and Aerospace Engineering, Institut Teknologi Bandung. Labtek II, Jl. Ganesa 10, Bandung, 40132 Indonesia)

International Journal of Aviation Science and Engineering
Vol. 4, No. 2 (December 2022)

Bird strike is a process of crashing between bird and airplane which occurs in flight phase. Based on data, there are 40 times bird strike occurs every day (FAA, 2019). There are lot of research that already conducted to decrease number of birds at the airport. But it is not given significant changes. Hence, it is needed a model that can detect bird at the airport so that we can decrease the number of birds. Study already conducted by comparing motion detection with object detection and filter which can be used to improve detection quality. Model already developed using YOLOv4 object detection with 71.89% mean average precision. It is expected that object detection can be developed to become a bird repellent system in the future