PERFORMANCE EVALUATION OF YOLOV8 AND YOLOV9 ALGORITHMS IN SHIP DETECTION APPLICATION

Beyzanur Tekindemir; Fatih Ahmet Şenel

Makale detayları

PERFORMANCE EVALUATION OF YOLOV8 AND YOLOV9 ALGORITHMS IN SHIP DETECTION APPLICATION

Yazarlar:

Beyzanur Tekindemir | Fatih Ahmet Şenel

Yayıncı:

Isparta University of Applied Sciences

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Uluslararası Sürdürülebilir Mühendislik ve Teknoloji Dergisi Vol.8 Issue 2, pp.192-199

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001337809

pISSN:

2618-6055

Anahtar kelimeler:

Özet:

 The detection and classification of vessels represents a pivotal challenge in the domain of maritime surveillance and monitoring. Its applications encompass a diverse range of fields, including fisheries management, migrant monitoring, maritime rescue operations, and maritime warfare. The utilisation of remote sensing technologies for the tracking of ships is a consequence of the advantages they offer, including extensive coverage and low-cost accessibility. This study emphasizes the importance of human detection, counting and tracking of objects using computer vision and machine learning methods. In this study, the potential of YOLO architectures as a technology for rapid and precise ship detection and classification is explored. The YOLOv8 and YOLOv9 architectures were employed for the detection of ships utilising remote sensing techniques. This study compares the performance of the YOLOv8 and YOLOv9 architectures using a dataset, referred to as the Ships in Google Earth dataset, which consists of 1658 images for ship detection. The models were evaluated in terms of training and validation losses, precision, recall and average precision, and demonstrated a certain degree of success and learning speed during the training process. Both models were found to provide effective solutions for ship detection. However, the YOLOv9 model exhibited superior performance in terms of faster convergence and overall detection accuracy, particularly at the outset.

 The detection and classification of vessels represents a pivotal challenge in the domain of maritime surveillance and monitoring. Its applications encompass a diverse range of fields, including fisheries management, migrant monitoring, maritime rescue operations, and maritime warfare. The utilisation of remote sensing technologies for the tracking of ships is a consequence of the advantages they offer, including extensive coverage and low-cost accessibility. This study emphasizes the importance of human detection, counting and tracking of objects using computer vision and machine learning methods. In this study, the potential of YOLO architectures as a technology for rapid and precise ship detection and classification is explored. The YOLOv8 and YOLOv9 architectures were employed for the detection of ships utilising remote sensing techniques. This study compares the performance of the YOLOv8 and YOLOv9 architectures using a dataset, referred to as the Ships in Google Earth dataset, which consists of 1658 images for ship detection. The models were evaluated in terms of training and validation losses, precision, recall and average precision, and demonstrated a certain degree of success and learning speed during the training process. Both models were found to provide effective solutions for ship detection. However, the YOLOv9 model exhibited superior performance in terms of faster convergence and overall detection accuracy, particularly at the outset.

 The detection and classification of vessels represents a pivotal challenge in the domain of maritime surveillance and monitoring. Its applications encompass a diverse range of fields, including fisheries management, migrant monitoring, maritime rescue operations, and maritime warfare. The utilisation of remote sensing technologies for the tracking of ships is a consequence of the advantages they offer, including extensive coverage and low-cost accessibility. This study emphasizes the importance of human detection, counting and tracking of objects using computer vision and machine learning methods. In this study, the potential of YOLO architectures as a technology for rapid and precise ship detection and classification is explored. The YOLOv8 and YOLOv9 architectures were employed for the detection of ships utilising remote sensing techniques. This study compares the performance of the YOLOv8 and YOLOv9 architectures using a dataset, referred to as the Ships in Google Earth dataset, which consists of 1658 images for ship detection. The models were evaluated in terms of training and validation losses, precision, recall and average precision, and demonstrated a certain degree of success and learning speed during the training process. Both models were found to provide effective solutions for ship detection. However, the YOLOv9 model exhibited superior performance in terms of faster convergence and overall detection accuracy, particularly at the outset.

 Gemi tespiti ve sınıflandırması, deniz gözetimi ve izleme alanında kritik bir konu olup; balıkçılık yönetimi, göçmen izleme, deniz kurtarma ve deniz savaşlarına kadar geniş bir yelpazede uygulanmaktadır. Uzaktan algılama teknolojileri, geniş kapsama alanı ve düşük maliyetli erişim gibi avantajları nedeniyle gemi izleme için kullanılmaktadır. Bu çalışma, nesnelerin insan tarafından tespiti, sayımı ve takibi süreçlerinin bilgisayarlı görme ve makine öğrenmesi yöntemleri ile gerçekleştirilmesinin önemini vurgulamaktadır. Bu çalışmada, YOLO mimarileri, gemi tespiti ve sınıflandırmasının hızlı ve doğru bir şekilde yapılabilmesi için kullanılan bir teknoloji olarak ele alınmaktadır. YOLOv8 ve YOLOv9 mimarileri ile uzaktan algılama kullanılarak gemi tespiti çalışmaları gerçekleştirilmiştir. Gemi tespiti için 1658 görüntüden oluşan Ships in Google Earth adlı veri seti kullanılarak YOLOv8 ve YOLOv9 mimarilerinin performansını karşılaştırmaktadır. Eğitim ve doğrulama kayıpları, kesinlik, duyarlılık ve ortalama hassasiyet kriterleri açısından değerlendirilen modeller, eğitim sürecinde belirli bir başarı ve öğrenme hızı sergilemiştir. Her iki modelin de gemi tespitinde etkili çözümler sunduğu görülmüştür. Ancak, YOLOv9 modeli, özellikle başlangıçta daha hızlı yakınsama ve genel tespit performansında üstünlük sağlamıştır.

Makale detayları

PERFORMANCE EVALUATION OF YOLOV8 AND YOLOV9 ALGORITHMS IN SHIP DETECTION APPLICATION

Yazarlar:

Beyzanur Tekindemir | Fatih Ahmet Şenel

Yayıncı:

Isparta University of Applied Sciences

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Uluslararası Sürdürülebilir Mühendislik ve Teknoloji Dergisi Vol.8 Issue 2, pp.192-199

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001337809

pISSN:

2618-6055

Convolutional neural network

deep learning

ship detection

yolov8

yolov9Evrişimsel sinir ağı

derin öğrenme

gemi tespiti

yolov8

yolov9

Sayı

Makale detayları

Yazarlar: Beyzanur Tekindemir | Fatih Ahmet Şenel

Yayıncı: Isparta University of Applied Sciences

Ana Başlıklar: Bilgisayar Yazılımı

Dergi: Uluslararası Sürdürülebilir Mühendislik ve Teknoloji Dergisi Vol.8 Issue 2, pp.192-199

Belge Tipi: Makale

Yayın Tarihi: 12/2024

Belge Dili: Türkçe

Document ID (Org No.): 2001337809

pISSN: 2618-6055

Sayı

Yazarlar:

Beyzanur Tekindemir | Fatih Ahmet Şenel

Yayıncı:

Isparta University of Applied Sciences

Ana Başlıklar:

Bilgisayar Yazılımı

Dergi:

Uluslararası Sürdürülebilir Mühendislik ve Teknoloji Dergisi Vol.8 Issue 2, pp.192-199

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001337809

pISSN:

2618-6055