Landing Runway Suitability Analysis Using Point Cloud Data in Unmanned Aerial Vehicles

Ebru Karaköse; Melike Aksu

Article Details

Landing Runway Suitability Analysis Using Point Cloud Data in Unmanned Aerial Vehicles

Authors:

Ebru Karaköse | Melike Aksu

Publisher:

Fırat University

Main Topics:

Elektrik Mühendisliği (Diğer)

Journal:

Fırat Üniversitesi Mühendislik Bilimleri Dergisi Vol.36 Issue 2, pp.535-551

Document Type:

Article

Publication Date:

9/2024

Document Language:

Turkish

Document ID (Org No.):

2001317062

pISSN:

1308-9072

Keywords:

Abstract:

 With the development of technology in terms of unmanned aerial vehicles UAV, their usage areas and research studies on them are increasing by the time. Although they are called unmanned, UAVs are controlled with the help of a pilot or flight attendant, or their autonomous flights are programmed. In line with the research, it has been determined that most of the problems and accidents occur during the landing of UAVs. In order to reduce this rate, detecting the landing runway with image processing methods and analyzing the obstacles on the runway with the point cloud method during the landing phase is an important step to be taken in this regard. For this reason, this study includes applications that can be used in UAV landing systems and provided with deep learning networks. First of all, the landing runway to be analyzed has been designed. This runway is left in an environment with different vehicles and obstacles around it. Later, real images and video recordings of the runway are taken from different heights and angles with a four-rotor UAV. The captured images have then been used to undergo processing and training stages. UAV landing runway detection has been achieved as a result of taking real images of the runway where the UAV would land, creating a dataset, and processing these images in YOLOv8. After the landing runway has been determined, the presence or absence of obstacles on the runway has been examined and analyzed using the point cloud data. The application has been completed, with depth maps provided in black-and-white and RGB form.

 With the development of technology in terms of unmanned aerial vehicles UAV, their usage areas and research studies on them are increasing by the time. Although they are called unmanned, UAVs are controlled with the help of a pilot or flight attendant, or their autonomous flights are programmed. In line with the research, it has been determined that most of the problems and accidents occur during the landing of UAVs. In order to reduce this rate, detecting the landing runway with image processing methods and analyzing the obstacles on the runway with the point cloud method during the landing phase is an important step to be taken in this regard. For this reason, this study includes applications that can be used in UAV landing systems and provided with deep learning networks. First of all, the landing runway to be analyzed has been designed. This runway is left in an environment with different vehicles and obstacles around it. Later, real images and video recordings of the runway are taken from different heights and angles with a four-rotor UAV. The captured images have then been used to undergo processing and training stages. UAV landing runway detection has been achieved as a result of taking real images of the runway where the UAV would land, creating a dataset, and processing these images in YOLOv8. After the landing runway has been determined, the presence or absence of obstacles on the runway has been examined and analyzed using the point cloud data. The application has been completed, with depth maps provided in black-and-white and RGB form.

 With the development of technology in terms of unmanned aerial vehicles UAV, their usage areas and research studies on them are increasing by the time. Although they are called unmanned, UAVs are controlled with the help of a pilot or flight attendant, or their autonomous flights are programmed. In line with the research, it has been determined that most of the problems and accidents occur during the landing of UAVs. In order to reduce this rate, detecting the landing runway with image processing methods and analyzing the obstacles on the runway with the point cloud method during the landing phase is an important step to be taken in this regard. For this reason, this study includes applications that can be used in UAV landing systems and provided with deep learning networks. First of all, the landing runway to be analyzed has been designed. This runway is left in an environment with different vehicles and obstacles around it. Later, real images and video recordings of the runway are taken from different heights and angles with a four-rotor UAV. The captured images have then been used to undergo processing and training stages. UAV landing runway detection has been achieved as a result of taking real images of the runway where the UAV would land, creating a dataset, and processing these images in YOLOv8. After the landing runway has been determined, the presence or absence of obstacles on the runway has been examined and analyzed using the point cloud data. The application has been completed, with depth maps provided in black-and-white and RGB form.

 İnsansız hava araçları İHA açısından gelişen teknoloji ile birlikte kullanım alanları ve üzerlerinde yapılan araştırma çalışmaları her geçen gün artmaktadır. Her ne kadar insansız olarak adlandırılsalar da İHAlar bir pilotuçuş görevlisi yardımıyla kontrol edilmekte ya da otonom uçuşları programlanmaktadır. Yapılan araştırmalar doğrultusunda, yaşanılan sorunların ve kazaların büyük bir kısmının İHAların inişi sırasında gerçekleştiği belirlenmiştir. Bu oranı azaltacak şekilde iniş aşamasında, iniş pistinin görüntü işleme yöntemleri ile tespit edilmesi ve nokta bulut yöntemiyle pistte bulunan engellerin analiz edilmesi bu konuda atılacak önemli bir adımdır. Bu nedenle bu çalışmada, İHA iniş sistemlerinde kullanılabilecek ve derin öğrenme ağlarıyla sağlanabilecek uygulamalara yer verilmiştir. Öncelikle, analizi gerçekleştirilecek olan iniş pistinin tasarımı yapılmıştır. Bu pist, çevresinde farklı araç ve engellerin de bulunduğu bir ortama bırakılmıştır. Daha sonra, pistin dört rotorlu bir İHA ile farklı yükseklik ve açılardan gerçek görüntüleri ve video kaydı alınmıştır. Alınan görüntüler daha sonra işleme ve eğitim aşamalarına tabi tutulmak için kullanılmıştır. İHAnın iniş yapacağı pistin gerçek görüntülerinin alınması, bir dataset oluşturulması ve alınan bu görüntülerin YOLOv8de işlenmesi sonucunda İHA iniş pisti tespiti sağlanmıştır. İniş pisti tespitinin ardından pist üzerinde engel bulunma ve bulunmama durumları nokta bulut yöntemi kullanılarak incelenmiş ve analizi gerçekleştirilmiştir. Siyah-beyaz ve renkli şekilde verilen derinlik haritaları ile uygulama tamamlanmıştır.

Article Details

Landing Runway Suitability Analysis Using Point Cloud Data in Unmanned Aerial Vehicles

Authors:

Ebru Karaköse | Melike Aksu

Publisher:

Fırat University

Main Topics:

Elektrik Mühendisliği (Diğer)

Journal:

Fırat Üniversitesi Mühendislik Bilimleri Dergisi Vol.36 Issue 2, pp.535-551

Document Type:

Article

Publication Date:

9/2024

Document Language:

Turkish

Document ID (Org No.):

2001317062

pISSN:

1308-9072

Image Processing

UAV Landing System

Point Cloud

RoboFlow

YOLOGörüntü İşleme

İHA İniş Sistemi

Nokta Bulutu

RoboFlow

YOLO

Issues

Article Details

Authors: Ebru Karaköse | Melike Aksu

Publisher: Fırat University

Main Topics: Elektrik Mühendisliği (Diğer)

Journal: Fırat Üniversitesi Mühendislik Bilimleri Dergisi Vol.36 Issue 2, pp.535-551

Document Type: Article

Publication Date: 9/2024

Document Language: Turkish

Document ID (Org No.): 2001317062

pISSN: 1308-9072

Issues

Authors:

Ebru Karaköse | Melike Aksu

Publisher:

Fırat University

Main Topics:

Elektrik Mühendisliği (Diğer)

Journal:

Fırat Üniversitesi Mühendislik Bilimleri Dergisi Vol.36 Issue 2, pp.535-551

Document Type:

Article

Publication Date:

9/2024

Document Language:

Turkish

Document ID (Org No.):

2001317062

pISSN:

1308-9072