Performance Evaluation Of Image Recognition Algorithms On Marine Vessels And Optimum Parameter Selection

Cansu Canbolat; Yasemin Atılgan Şengül; Ahmet Yekta Kayman

Makale detayları

Performance Evaluation Of Image Recognition Algorithms On Marine Vessels And Optimum Parameter Selection

Yazarlar:

Cansu Canbolat | Yasemin Atılgan Şengül | Ahmet Yekta Kayman

Yayıncı:

Duzce University

Ana Başlıklar:

Derin Öğrenme

Dergi:

Düzce Üniversitesi Bilim ve Teknoloji Dergisi Vol.13 Issue 2, pp.752-769

Belge Tipi:

Makale

Yayın Tarihi:

4/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001346569

pISSN:

2148-2446

Anahtar kelimeler:

Özet:

 Today, with the developing sensor technology, image processing models and deep neural network methods, there are significant developments in the field of autonomous driving and also various studies are carried out in this direction both in the private sector and in academia. On the other hand studies on safe driving of autonomous vehicles are still very limited. Mostly the studies have been conducted for land vehicles, and the data sets for the operation of artificial intelligence models were created in this context. In this study, the algorithms for autonomous driving were tested using the original data set created from objects on the sea in order to optimize the navigation of sea vehicles on the sea. Image processing methods have recently gained great importance in terms of recognizing vehicles on the sea and providing autonomous driving. In this study, a high-resolution and wide-ranging original data set consisting of 44965 objects was created to identify objects on the sea. With this data set, analysis and optimizations were made with image processing technology for the recognition and classification of objects, and the best model was tried to be determined among the models. It is aimed to detect and classify objects on the sea surface from a long distance 1000m, to create safe use for sea vehicles and to provide decision support. In order for the created data set to be successfully identified in real-time, the data set was divided into six classes. As a result of the classification process, data labeling was performed according to these classes which are, Cargo_Ship, Tanker_Ship, RoRoFerryPassenger, Boats, Tug_Boats, Speciality_Vessels. The created data set was tested with the most common real-time recognition models, SSD, Faster R-CNN, EfficientDet algorithms under the TensorFlow library. Results were obtained according to six different output parameter values, AP-50, AP-75, Av. Recall, F1-50, F1-75 and LTL, on the models. According to the obtained results, SSD Mobilnet v1 was determined as the most successful algorithm.

 Today, with the developing sensor technology, image processing models and deep neural network methods, there are significant developments in the field of autonomous driving and also various studies are carried out in this direction both in the private sector and in academia. On the other hand studies on safe driving of autonomous vehicles are still very limited. Mostly the studies have been conducted for land vehicles, and the data sets for the operation of artificial intelligence models were created in this context. In this study, the algorithms for autonomous driving were tested using the original data set created from objects on the sea in order to optimize the navigation of sea vehicles on the sea. Image processing methods have recently gained great importance in terms of recognizing vehicles on the sea and providing autonomous driving. In this study, a high-resolution and wide-ranging original data set consisting of 44965 objects was created to identify objects on the sea. With this data set, analysis and optimizations were made with image processing technology for the recognition and classification of objects, and the best model was tried to be determined among the models. It is aimed to detect and classify objects on the sea surface from a long distance 1000m, to create safe use for sea vehicles and to provide decision support. In order for the created data set to be successfully identified in real-time, the data set was divided into six classes. As a result of the classification process, data labeling was performed according to these classes which are, Cargo_Ship, Tanker_Ship, RoRoFerryPassenger, Boats, Tug_Boats, Speciality_Vessels. The created data set was tested with the most common real-time recognition models, SSD, Faster R-CNN, EfficientDet algorithms under the TensorFlow library. Results were obtained according to six different output parameter values, AP-50, AP-75, Av. Recall, F1-50, F1-75 and LTL, on the models. According to the obtained results, SSD Mobilnet v1 was determined as the most successful algorithm.

 Today, with the developing sensor technology, image processing models and deep neural network methods, there are significant developments in the field of autonomous driving and also various studies are carried out in this direction both in the private sector and in academia. On the other hand studies on safe driving of autonomous vehicles are still very limited. Mostly the studies have been conducted for land vehicles, and the data sets for the operation of artificial intelligence models were created in this context. In this study, the algorithms for autonomous driving were tested using the original data set created from objects on the sea in order to optimize the navigation of sea vehicles on the sea. Image processing methods have recently gained great importance in terms of recognizing vehicles on the sea and providing autonomous driving. In this study, a high-resolution and wide-ranging original data set consisting of 44965 objects was created to identify objects on the sea. With this data set, analysis and optimizations were made with image processing technology for the recognition and classification of objects, and the best model was tried to be determined among the models. It is aimed to detect and classify objects on the sea surface from a long distance 1000m, to create safe use for sea vehicles and to provide decision support. In order for the created data set to be successfully identified in real-time, the data set was divided into six classes. As a result of the classification process, data labeling was performed according to these classes which are, Cargo_Ship, Tanker_Ship, RoRoFerryPassenger, Boats, Tug_Boats, Speciality_Vessels. The created data set was tested with the most common real-time recognition models, SSD, Faster R-CNN, EfficientDet algorithms under the TensorFlow library. Results were obtained according to six different output parameter values, AP-50, AP-75, Av. Recall, F1-50, F1-75 and LTL, on the models. According to the obtained results, SSD Mobilnet v1 was determined as the most successful algorithm.

 Günümüzde gelişen sensör teknolojisi, görüntü işleme modelleri ve derin sinir ağları yöntemleri ile otonom sürüş alanında da önemli gelişmeler yaşanmakta ve hem özel sektörde hem de akademide bu yönde çeşitli çalışmalar gerçekleştirilmektedir. Sürücüsüz araçların güvenli sürüşüne yönelik bu çalışmalar henüz çok kısıtlıdır. Yapılan çalışmaların temeli kara taşıtları için oluşturulmuş, yapay zekâ modellerinin çalıştırılması için oluşturulan veri setleri bu bağlamda hazırlanmıştır. Bu çalışmada otonom sürüş için kullanılan algoritmalar deniz taşıtlarının deniz üzerinde seyrederken optimize edilmesi için deniz üzerindeki nesnelerden oluşturulan orijinal veri seti kullanılarak test edilmiştir. Görüntü işleme metotları, deniz üzerindeki taşıtların tanınması ve otonom sürüş sağlanması açısından son zamanlarda büyük önem kazanmıştır. Bu çalışmada, deniz üzerindeki nesneleri tanımlamak için, deniz üzerindeki nesnelerden oluşan 44965 adetlik yüksek çözünürlüklü ve geniş kapsamlı orijinal veri seti oluşturulmuştur. Bu veri seti ile deniz üzerindeki nesnelerin tanınma ve sınıflandırılmasına yönelik görüntü işleme teknolojisi ile analiz ve optimizasyonlar yapılarak, modeller arasında en iyi model belirlenmeye çalışılmıştır. Deniz yüzeyindeki nesneleri, uzak mesafeden 1000m tespit edilip sınıflandırılması, deniz araçları için güvenli kullanım oluşturulması ve karar desteği sağlanması hedeflenmektedir. Oluşturulan veri setinin gerçek zamanlı ortamda başarılı şekilde tanımlanabilmesi için veri seti altı adet sınıfa ayrılmıştır. Sınıflandırma işlemi sonucunda oluşturulan; Cargo_Ship, Tanker_Ship, RoRoFerryPassenger, Boats, Tug_Boats, Speciality_Vessels olmak üzere altı adet sınıfa göre veri etiketleme işlemi yapılmıştır. Oluşturulan veri seti, en yaygın gerçek zamanlı tanıma modelleri olan, TensorFlow kütüphanesi altındaki SSD, Faster R-CNN, EfficientDet algoritmaları ile test edilmiştir. Modeller üzerinde de AP-50, AP-75, Av. Recall, F1-50, F1-75 ve LTL olmak üzere altı farklı çıktı parametresi değerine göre sonuçlar elde edilmiştir. Elde edilen sonuçlara göre, SSD Mobilnet v1 en başarılı algoritma olarak tespit edilmiştir.

Makale detayları

Performance Evaluation Of Image Recognition Algorithms On Marine Vessels And Optimum Parameter Selection

Yazarlar:

Cansu Canbolat | Yasemin Atılgan Şengül | Ahmet Yekta Kayman

Yayıncı:

Duzce University

Ana Başlıklar:

Derin Öğrenme

Dergi:

Düzce Üniversitesi Bilim ve Teknoloji Dergisi Vol.13 Issue 2, pp.752-769

Belge Tipi:

Makale

Yayın Tarihi:

4/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001346569

pISSN:

2148-2446

vehicle detection

Image processing

Deep neural network

Autonomous drivingaracı tespiti

Görüntü işleme

Derin sinir ağı

Otonom sürüş

Sayı

Makale detayları

Yazarlar: Cansu Canbolat | Yasemin Atılgan Şengül | Ahmet Yekta Kayman

Yayıncı: Duzce University

Ana Başlıklar: Derin Öğrenme

Dergi: Düzce Üniversitesi Bilim ve Teknoloji Dergisi Vol.13 Issue 2, pp.752-769

Belge Tipi: Makale

Yayın Tarihi: 4/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001346569

pISSN: 2148-2446

Sayı

Yazarlar:

Cansu Canbolat | Yasemin Atılgan Şengül | Ahmet Yekta Kayman

Yayıncı:

Duzce University

Ana Başlıklar:

Derin Öğrenme

Dergi:

Düzce Üniversitesi Bilim ve Teknoloji Dergisi Vol.13 Issue 2, pp.752-769

Belge Tipi:

Makale

Yayın Tarihi:

4/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001346569

pISSN:

2148-2446