Detection of Fire Zone by Unmanned Aerial Vehicle and Prediction of Fire Intervention with Artificial Intelligence

Mehmet Yücel; Bekir Aksoy

Makale detayları

Detection of Fire Zone by Unmanned Aerial Vehicle and Prediction of Fire Intervention with Artificial Intelligence

Yazarlar:

Mehmet Yücel | Bekir Aksoy

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Devreler ve Sistemler

Dergi:

Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi Vol.28 Issue 3, pp.559-569

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001332878

pISSN:

1308-6529

Anahtar kelimeler:

Özet:

 Abstract: Forest fires are among the most common disasters that threaten living spaces today. The increase in global warming, deterioration of air quality, and decreases in animal and plant diversity are the main damages caused by forest fires. In order to combat the threats posed by forest fires, all states develop various policies and make serious financial expenditures. It is essential to develop technological products used in this fight and to find faster and more definitive solutions to forest fires. In the thesis study conducted, an artificial intelligence-based unmanned aerial vehicle system was developed based on these problems. The developed system has the ability to patrol in a potential fire area and perform autonomous flight and analysis. Images are instantly transferred to the ground unit with the camera on the system and processed. Signs of fire and smoke are searched in the processed images. In the event of a possible fire, the system autonomously flies in the fire area and performs a task to intervene in the fire. In the event of a fire, a horizontal shot estimate is made by processing wind speed, UAV speed, and UAV altitude information with artificial intelligence models. As a result of the estimate, the moment when the fire extinguishing ball should be released while the UAV is moving is calculated. The model estimates how far the horizontal shot will travel on the X axis. The end point of the path to be taken from the X axis is estimated for the fire center. Thus, it is aimed to drop the fire extinguishing ball into the flaming area with a correct shot.

 Abstract: Forest fires are among the most common disasters that threaten living spaces today. The increase in global warming, deterioration of air quality, and decreases in animal and plant diversity are the main damages caused by forest fires. In order to combat the threats posed by forest fires, all states develop various policies and make serious financial expenditures. It is essential to develop technological products used in this fight and to find faster and more definitive solutions to forest fires. In the thesis study conducted, an artificial intelligence-based unmanned aerial vehicle system was developed based on these problems. The developed system has the ability to patrol in a potential fire area and perform autonomous flight and analysis. Images are instantly transferred to the ground unit with the camera on the system and processed. Signs of fire and smoke are searched in the processed images. In the event of a possible fire, the system autonomously flies in the fire area and performs a task to intervene in the fire. In the event of a fire, a horizontal shot estimate is made by processing wind speed, UAV speed, and UAV altitude information with artificial intelligence models. As a result of the estimate, the moment when the fire extinguishing ball should be released while the UAV is moving is calculated. The model estimates how far the horizontal shot will travel on the X axis. The end point of the path to be taken from the X axis is estimated for the fire center. Thus, it is aimed to drop the fire extinguishing ball into the flaming area with a correct shot.

 Abstract: Forest fires are among the most common disasters that threaten living spaces today. The increase in global warming, deterioration of air quality, and decreases in animal and plant diversity are the main damages caused by forest fires. In order to combat the threats posed by forest fires, all states develop various policies and make serious financial expenditures. It is essential to develop technological products used in this fight and to find faster and more definitive solutions to forest fires. In the thesis study conducted, an artificial intelligence-based unmanned aerial vehicle system was developed based on these problems. The developed system has the ability to patrol in a potential fire area and perform autonomous flight and analysis. Images are instantly transferred to the ground unit with the camera on the system and processed. Signs of fire and smoke are searched in the processed images. In the event of a possible fire, the system autonomously flies in the fire area and performs a task to intervene in the fire. In the event of a fire, a horizontal shot estimate is made by processing wind speed, UAV speed, and UAV altitude information with artificial intelligence models. As a result of the estimate, the moment when the fire extinguishing ball should be released while the UAV is moving is calculated. The model estimates how far the horizontal shot will travel on the X axis. The end point of the path to be taken from the X axis is estimated for the fire center. Thus, it is aimed to drop the fire extinguishing ball into the flaming area with a correct shot.

 Özet: Orman yangınları günümüzde, canlı yaşam alanlarını tehdit eden afetlerin başında gelmektedir. Küresel ısınmadaki artış, hava kalitesinin bozulması, hayvan ve bitki çeşitliliğindeki azalmalar, orman yangınlarının oluşturduğu başlıca zararlardır. Orman yangınlarının oluşturduğu tehditler ile mücadele edebilmek için tüm devletler çeşitli politikalar geliştirmekte ve ciddi maddi harcamalar yapmaktadırlar. Bu mücadelede kullanılan teknolojik ürünlerin geliştirilmesi ve orman yangınlarına daha hızlı ve kesin çözümün bulunabilmesi elzemdir. Gerçekleştirilen tez çalışmasında bu sorunlardan hareketle yapay zeka tabanlı bir insansız hava aracı sistemi geliştirilmiştir. Geliştirilen sistem olası yangın bölgesinde devriye gezerek otonom uçuş ve analiz yapma yeteneklerine sahiptir. Sistem üzerinde bulunan kamera ile anlık olarak görüntüler yer birimine aktırılmakta ve işlenmektedir. İşlenen görüntüler de yangın ve duman emareleri aranmaktadır. Olası bir yangın durumunda sistem otonom olarak yangın bölgesinde uçuş gerçekleştirmekte ve yangına müdahale etmek üzere görev icra etmektedir. Yangın anında yapay zeka modelleri ile rüzgar hızı, İHA hızı, İHA irtifası bilgileri işlenerek bir yatay atış tahmini yapılmaktadır. Tahmin sonucunda İHA hareket halinde iken yangın söndürme topunun bırakılması gereken an hesaplanmaktadır. Oluşan yatay atışın X ekseninde ne kadar yol alacacağı model tarafından tahmin edilmektedir. X ekseninden alınacak yolun bitiş noktası yangın merkezi için tahminlenmektedir. Böylece doğru bir atış ile yangın söndürme topunun alevli bölgeye düşürülmesi hedeflenmiştir.

Makale detayları

Detection of Fire Zone by Unmanned Aerial Vehicle and Prediction of Fire Intervention with Artificial Intelligence

Yazarlar:

Mehmet Yücel | Bekir Aksoy

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Devreler ve Sistemler

Dergi:

Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi Vol.28 Issue 3, pp.559-569

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001332878

pISSN:

1308-6529

Deep learning

Machine learning

Image processing

Unmanned aerial vehicle

Forest firesDerin öğrenme

Makine Öğrenmesi

Görüntü işleme

İnsansız Hava Aracı

Orman Yangınları

Sayı

Makale detayları

Yazarlar: Mehmet Yücel | Bekir Aksoy

Yayıncı: Süleyman Demirel University

Ana Başlıklar: Devreler ve Sistemler

Dergi: Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi Vol.28 Issue 3, pp.559-569

Belge Tipi: Makale

Yayın Tarihi: 12/2024

Belge Dili: Türkçe

Document ID (Org No.): 2001332878

pISSN: 1308-6529

Sayı

Yazarlar:

Mehmet Yücel | Bekir Aksoy

Yayıncı:

Süleyman Demirel University

Ana Başlıklar:

Devreler ve Sistemler

Dergi:

Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi Vol.28 Issue 3, pp.559-569

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001332878

pISSN:

1308-6529