AeroRunway: Diverse Weather and Time of Day Aerial Dataset for Autonomous Landing Training

Nesil Bor; Nergis Pervan Akman; Ali Berkol

Makale detayları

AeroRunway: Diverse Weather and Time of Day Aerial Dataset for Autonomous Landing Training

Yazarlar:

Nesil Bor | Nergis Pervan Akman | Ali Berkol

Yayıncı:

Çanakkale Onsekiz Mart University

Ana Başlıklar:

Image Processing | Deep Learning | Graph | Social and Multimedia Data | Data Models | Storage and Indexing | Data Engineering and Data Science | Data Management and Data Science (Other)

Dergi:

Journal of Advanced Research in Natural and Applied Sciences Vol.10 Issue 3, pp.735-746

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001328955

pISSN:

2757-5195

Anahtar kelimeler:

Özet:

 Acquiring a sufficient amount of diverse and accurate real-world data poses a significant challenge in advancing autonomous systems, which are becoming increasingly popular. Despite the aerospace industrys keen practical and economic interest in autonomous landing systems, readily available open-source datasets containing aerial photographs are scarce. To address this issue, we present a dataset named AeroRunway, comprising high-quality aerial photos designed to aid in runway recognition during the approach and landing stages. The dataset is composed of images using X-Plane, a flight simulator software developed by Laminar Research. It is a highly realistic and detailed flight simulation program that allows users to experience the sensation of piloting various aircraft in a virtual environment. These synthetic images were collected mostly in variable weather conditions above 5000 feet to supplement existing satellite imagery that can be used for extreme situations. This dataset was created from 28 different airports in different weather conditions, such as foggy and rainy, at various times of the day, such as day and night, and consists of 3880 images and is approximately 13.3 GB in size.

 Acquiring a sufficient amount of diverse and accurate real-world data poses a significant challenge in advancing autonomous systems, which are becoming increasingly popular. Despite the aerospace industrys keen practical and economic interest in autonomous landing systems, readily available open-source datasets containing aerial photographs are scarce. To address this issue, we present a dataset named AeroRunway, comprising high-quality aerial photos designed to aid in runway recognition during the approach and landing stages. The dataset is composed of images using X-Plane, a flight simulator software developed by Laminar Research. It is a highly realistic and detailed flight simulation program that allows users to experience the sensation of piloting various aircraft in a virtual environment. These synthetic images were collected mostly in variable weather conditions above 5000 feet to supplement existing satellite imagery that can be used for extreme situations. This dataset was created from 28 different airports in different weather conditions, such as foggy and rainy, at various times of the day, such as day and night, and consists of 3880 images and is approximately 13.3 GB in size.

 Acquiring a sufficient amount of diverse and accurate real-world data poses a significant challenge in advancing autonomous systems, which are becoming increasingly popular. Despite the aerospace industrys keen practical and economic interest in autonomous landing systems, readily available open-source datasets containing aerial photographs are scarce. To address this issue, we present a dataset named AeroRunway, comprising high-quality aerial photos designed to aid in runway recognition during the approach and landing stages. The dataset is composed of images using X-Plane, a flight simulator software developed by Laminar Research. It is a highly realistic and detailed flight simulation program that allows users to experience the sensation of piloting various aircraft in a virtual environment. These synthetic images were collected mostly in variable weather conditions above 5000 feet to supplement existing satellite imagery that can be used for extreme situations. This dataset was created from 28 different airports in different weather conditions, such as foggy and rainy, at various times of the day, such as day and night, and consists of 3880 images and is approximately 13.3 GB in size.

 Acquiring a sufficient amount of diverse and accurate real-world data poses a significant challenge in advancing autonomous systems, which are becoming increasingly popular. Despite the aerospace industrys keen practical and economic interest in autonomous landing systems, readily available open-source datasets containing aerial photographs are scarce. To address this issue, we present a dataset named AeroRunway, comprising high-quality aerial photos designed to aid in runway recognition during the approach and landing stages. The dataset is composed of images using X-Plane, a flight simulator software developed by Laminar Research. It is a highly realistic and detailed flight simulation program that allows users to experience the sensation of piloting various aircraft in a virtual environment. These synthetic images were collected mostly in variable weather conditions above 5000 feet to supplement existing satellite imagery that can be used for extreme situations. This dataset was created from 28 different airports in different weather conditions, such as foggy and rainy, at various times of the day, such as day and night, and consists of 3880 images and is approximately 13.3 GB in size.

Makale detayları

AeroRunway: Diverse Weather and Time of Day Aerial Dataset for Autonomous Landing Training

Yazarlar:

Nesil Bor | Nergis Pervan Akman | Ali Berkol

Yayıncı:

Çanakkale Onsekiz Mart University

Ana Başlıklar:

Image Processing | Deep Learning | Graph | Social and Multimedia Data | Data Models | Storage and Indexing | Data Engineering and Data Science | Data Management and Data Science (Other)

Dergi:

Journal of Advanced Research in Natural and Applied Sciences Vol.10 Issue 3, pp.735-746

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001328955

pISSN:

2757-5195

Aerodrome detection

spatial awareness

artificial intelligence

deep learning

machine learning

Sayı

Makale detayları

AeroRunway: Diverse Weather and Time of Day Aerial Dataset for Autonomous Landing Training

Yazarlar: Nesil Bor | Nergis Pervan Akman | Ali Berkol

Yayıncı: Çanakkale Onsekiz Mart University

Ana Başlıklar: Image Processing | Deep Learning | Graph | Social and Multimedia Data | Data Models | Storage and Indexing | Data Engineering and Data Science | Data Management and Data Science (Other)

Dergi: Journal of Advanced Research in Natural and Applied Sciences Vol.10 Issue 3, pp.735-746

Belge Tipi: Makale

Yayın Tarihi: 9/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001328955

pISSN: 2757-5195

Aerodrome detection

spatial awareness

artificial intelligence

deep learning

machine learning

Sayı

Yazarlar:

Nesil Bor | Nergis Pervan Akman | Ali Berkol

Yayıncı:

Çanakkale Onsekiz Mart University

Ana Başlıklar:

Image Processing | Deep Learning | Graph | Social and Multimedia Data | Data Models | Storage and Indexing | Data Engineering and Data Science | Data Management and Data Science (Other)

Dergi:

Journal of Advanced Research in Natural and Applied Sciences Vol.10 Issue 3, pp.735-746

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001328955

pISSN:

2757-5195