Ship Classification Based on Improved Convolutional Neural Network Architecture for Intelligent Transport Systems

Abstract

In recent years, deep learning has been used in various applications including the classification of ship targets in inland waterways for enhancing intelligent transport systems. Various researchers introduced different classification algorithms, but they still face the problems of low accuracy and misclassification of other target objects. Hence, there is still a need to do more research on solving the above problems to prevent collisions in inland waterways. In this paper, we introduce a new convolutional neural network classification algorithm capable of classifying five classes of ships, including cargo, military, carrier, cruise and tanker ships, in inland waterways. The game of deep learning ship dataset, which is a public dataset originating from Kaggle, has been used for all experiments. Initially, the five pretrained models (which are AlexNet, VGG, Inception V3 ResNet and GoogleNet) were used on the dataset in order to select the best model based on its performance. Resnet-152 achieved the best model with an accuracy of 90.56%, and AlexNet achieved a lower accuracy of 63.42%. Furthermore, Resnet-152 was improved by adding a classification block which contained two fully connected layers, followed by ReLu for learning new characteristics of our training dataset and a dropout layer to resolve the problem of a diminishing gradient. For generalization, our proposed method was also tested on the MARVEL dataset, which consists of more than 10,000 images and 26 categories of ships. Furthermore, the proposed algorithm was compared with existing algorithms and obtained high performance compared with the others, with an accuracy of 95.8%, precision of 95.83%, recall of 95.80%, specificity of 95.07% and F1 score of 95.81%.

Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR Images

“…The ship classification experiment has been conducted on the OpenSARShip2.0 dataset, which shows that the proposed strategy achieves the performance of the existing mainstream classification models with a smaller number of parameters and much lower energy consumption than the mainstream classification models. In the further work, more effective information (such as prior information such as SAR imaging characteristics) and more effective fusion methods should be conducted, as well as a comparison with other similar approaches [47,48].…”

Explainable Deep Learning to Classify Royal Navy Ships

“…This extensive collection comprises 140,000 distinctly labeled maritime vessel images, spanning 26 diverse classes that encompass both civilian and military ships. In a comparative exploration, [30] introduced a ResNet extension and demonstrated its superior performance when contrasted with AlexNet, VGG, ResNet, and GoogLeNet. Their analysis encompassed a dataset comprising 8,932 images, categorizing ships into five classes, en-compassing both civilian and non-civilian categories, alongside the MARVEL dataset.…”

Rancang Bangun Information Board Berbasis Cloud Digital Signage Platform

“…Di berbagai bidang dan permasalahan dunia nyata teknologi informasi menjadi jawaban dan solusi yang tepat dalam penyelesaiannya. Misalnya pemanfaatan mikrokontroler dan sensor untuk otomatisasi (Stephanus et al, 2022;Tuapatel & Stephanus, 2019), teknologi website untuk membatu pariwisata dan ekonomi (Dahoklory et al, 2022), pemanfaatannya dalam bidang sistem cerdas (Leonidas & Jie, 2021;Wahjudi et al, 2021), hingga ke media informasi digital (Sethi et al, 2015) Informasi merupakan kebutuhan dari setiap manusia. Ketika menerima informasi yang tepat, maka manusia dapat mengambil keputusan yang tepat pula.…”