Combining a Deep Convolutional Neural Network with Transfer Learning for Ship Classification

Zhong, Hui; Chu, Na; Liu, Zhenyu

doi:10.1109/icicta49267.2019.00011

Cited by 5 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[15,16], while various types of ships were classified in Refs. [17–19]. Above all, this work turned out to outperform others in respect of the accuracy.…”

Section: Resultsmentioning

confidence: 74%

“…Similarly, deep-learning models were employed to classify moving targets on sea surface [17][18][19]. The aim in Ref.…”

Section: Introductionmentioning

confidence: 99%

“…[17] was to distinguish fishing from naval vessels, in Ref. [18] was to tell the difference among oil tankers, bulk carriers and container ships, while in Ref. [19] was to tell the difference among fishing boats, sailboats, cargo ships, cruise ships and warships.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Development of Fishing Vessel Identification Model Based on Deep Neural Network

Lin

Chen

et al. 2022

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

This paper presents a deep neural network (DNN)‐based model to recognize fishing vessels. In Taiwan, the vast majority of small fishing vessels are not equipped with an automatic identification system (AIS). As a consequence, the staff in a fishing port administration become heavily loaded when monitoring and managing the fishing vessels accessing a port. The workload is expected to be eased using this work. For the first time in the literature, a captured fishing vessel image was converted to a 128‐dimensional embedding for recognition purposes. The presented model gave a false positive rate (FPR) as low as 1.13% and an accuracy up to 99.47% at threshold = 0.772379. Finally, all the performance metrics, namely, the true positive rate (TPR), the FPR, precision and accuracy, are actually functions of the threshold which can be specified by users to meet specific requirements. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

show abstract

“…[15,16], while various types of ships were classified in Refs. [17–19]. Above all, this work turned out to outperform others in respect of the accuracy.…”

Section: Resultsmentioning

confidence: 74%

“…Similarly, deep-learning models were employed to classify moving targets on sea surface [17][18][19]. The aim in Ref.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of Fishing Vessel Identification Model Based on Deep Neural Network

Lin

Chen

et al. 2022

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

show abstract

“…Where diverse algorithms including a bag of features, support vector machines (SVM), and convolutional neural networks (CNN) are used [6]. On the other hand, VGG19 has presented a better accuracy than capture by the cited technique, reaching a 95.8% rate of accuracy [7]. Furthermore, image processing via CV models can face several problems regarding CV illumination effects, potential occlusion, orientation, scale, and variety of objects [8].…”

Section: Related Workmentioning

confidence: 99%

A Multi-Faceted Approach to Maritime Security: Federated Learning, Computer Vision, and IoT in Edge Computing

Cruz,

Teixeira,

Mafra

et al. 2023

Anais Do XLI Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

Brazil faces several challenges related to maritime monitoring, including illegal fishing, drug trafficking, oil spills, and other environmental hazards. The approach aims to automate the detection and analysis of maritime activity, enabling faster and more accurate decision-making for improved maritime security. The computer vision algorithms used in the approach are designed for object detection and classification, and the federated learning approach is used to train the models while preserving data privacy. The results obtained by the final computer vision model and algorithm are presented, and the challenges faced in developing robust CV models and improving classification accuracy are discussed. The proposed approach offers a promising direction for improving maritime security and inspires further research in this area.

show abstract

“…With this, even if there is an imbalance between the samples of each class, it is possible to improve the model's performance. The work presented in [64], which uses visible light remote sensing images, also suggests that transfer learning solves the limitation of the number of images on datasets and improves the convergence speed of the model. Finally, the last challenge pointed out by the authors in the context of the dataset is about images annotated with precise bounding boxes to provide an effective and available database for training and validation.…”

Section: Datasetsmentioning

confidence: 99%

Literature Review on Ship Localization, Classification, and Detection Methods Based on Optical Sensors and Neural Networks

Teixeira

Araujo

Costa

et al. 2022

Sensors

View full text Add to dashboard Cite

Object detection is a common application within the computer vision area. Its tasks include the classic challenges of object localization and classification. As a consequence, object detection is a challenging task. Furthermore, this technique is crucial for maritime applications since situational awareness can bring various benefits to surveillance systems. The literature presents various models to improve automatic target recognition and tracking capabilities that can be applied to and leverage maritime surveillance systems. Therefore, this paper reviews the available models focused on localization, classification, and detection. Moreover, it analyzes several works that apply the discussed models to the maritime surveillance scenario. Finally, it highlights the main opportunities and challenges, encouraging new research in this area.

show abstract

Combining a Deep Convolutional Neural Network with Transfer Learning for Ship Classification

Cited by 5 publications

References 4 publications

Development of Fishing Vessel Identification Model Based on Deep Neural Network

Development of Fishing Vessel Identification Model Based on Deep Neural Network

A Multi-Faceted Approach to Maritime Security: Federated Learning, Computer Vision, and IoT in Edge Computing

Literature Review on Ship Localization, Classification, and Detection Methods Based on Optical Sensors and Neural Networks

Contact Info

Product

Resources

About