Enhancement of Ship Type Classification from a Combination of CNN and KNN

Jeon, Ho-Kun; Yang, Chan-Su

doi:10.3390/electronics10101169

Cited by 18 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In view of the problems of an insufficient labeled dataset, an unoptimized polarization image, and noise interference in vessel classification. Jeon et al 21 proposed a method that combined CNN and KNN models to improve the classification efficiency of vessels. To overcome the small number of datasets, Mishra et al 22 conducted a study on the transfer learning method in CNNs and tested it on the AlexNet, VGGNet, and ResNet architectures for ship classification tasks on MARVEL datasets.…”

Section: Introductionmentioning

confidence: 99%

A small fishing vessel recognition method using transfer learning based on laser sensors

Zheng

Chen

Yuan

et al. 2023

Sci Rep

View full text Add to dashboard Cite

The management of small vessels has always been key to maritime administration. This paper presents a novel method for recognizing small fishing vessels based on laser sensors. Using four types of small fishing vessels as targets, a recognition method for small fishing vessels based on Markov transition field (MTF) time-series images and VGG-16 transfer learning is proposed. In contrast to conventional methods, this study uses polynomial fitting to obtain the contours of a fishing vessel and transforms one-dimensional vessel contours into two-dimensional time-series images using the MTF coding method. The VGG-16 model is used for the recognition process, and migration learning is applied to improve the results. The UCR time-series public dataset is used as a transfer learning dataset for the MTF time-series image encoding. The experiment demonstrates that the proposed method exhibits higher accuracy and performance than 1D-CNN and other general neural network models, and the highest accuracy rate is 98.92%.

show abstract

Section: Introductionmentioning

confidence: 99%

A small fishing vessel recognition method using transfer learning based on laser sensors

Zheng

Chen

Yuan

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The continuous development of deep learning, especially convolutional neural networks (CNNs), has significant advantages for the feature extraction of images and other aspects, which provides another efficient solution for the accurate classification of ships. Jeon et al [5] proposed a CNN combined with a k-nearest neighbor (KNN) data enhancement method to improve the classification efficiency of Sentinel-1 dual-polarization data with 10m pixel spacing for possible problems such as insufficiently labeled data in the SAR dataset and compared these data with a separate CNN method. The F1-score improved by 9.3%, but the amount of trained data was small, and the data type of the used dataset was relatively single.…”

Section: Introductionmentioning

confidence: 99%

A Marine Small-Targets Classification Algorithm Based on Improved Convolutional Neural Networks

Guo

Liu

2023

Remote Sensing

View full text Add to dashboard Cite

Deep learning, especially convolutional neural network (CNN) techniques, has been shown to have superior performance in ship classification, as have small-target recognition studies in safety inspections of hydraulic structures such as ports and dams. High-resolution synthetic aperture radar (SAR)-based maritime ship classification plays an increasingly important role in marine surveillance, marine rescue, and maritime ship management. To improve ship classification accuracy and training efficiency, we proposed a CNN-based ship classification method. Firstly, the image characteristics of different ship structures and the materials of ship SAR images were analyzed. We then constructed a ship SAR image dataset and performed preprocessing operations such as averaging. Combined with a classic neural network structure, we created a new convolutional module, namely, the Inception-Residual Controller (IRC) module. A convolutional neural network was built based on the IRC module to extract image features and establish a ship classification model. Finally, we conducted simulation experiments for ship classification and analyzed the experimental results for comparison. The experimental results showed that the average accuracy of ship classification of the model in this paper reached 98.71%, which was approximately 3% more accurate than the traditional network model and approximately 1% more accurate compared with other recently improved models. The new module also performed well in evaluation metrics, such as the recall rate, with accurate classifications. The model could satisfactorily describe different ship types. Therefore, it could be applied to marine ship classification management with the possibility of being extended to hydraulic building target recognition tasks.

show abstract

“…Lin et al [13] integrated a CNN and the k-nearest neighbors (KNN) method to classify ships from dualpolarized data. Jeon et al [14] combined traditional methods of image processing and target recognition methods based on CNNs, supporting the development of AI-based ship vision systems. Li et al [15] summarized traditional algorithms that combined image processing and machine learning with target recognition algorithms based on convolutional neural networks.…”

Section: Introductionmentioning

confidence: 99%

Fine-Grained Ship Classification by Combining CNN and Swin Transformer

Huang

Zhang

2022

Remote Sensing

View full text Add to dashboard Cite

The mainstream algorithms used for ship classification and detection can be improved based on convolutional neural networks (CNNs). By analyzing the characteristics of ship images, we found that the difficulty in ship image classification lies in distinguishing ships with similar hull structures but different equipment and superstructures. To extract features such as ship superstructures, this paper introduces transformer architecture with self-attention into ship classification and detection, and a CNN and Swin transformer model (CNN-Swin model) is proposed for ship image classification and detection. The main contributions of this study are as follows: (1) The proposed approach pays attention to different scale features in ship image classification and detection, introduces a transformer architecture with self-attention into ship classification and detection for the first time, and uses a parallel network of a CNN and a transformer to extract features of images. (2) To exploit the CNN’s performance and avoid overfitting as much as possible, a multi-branch CNN-Block is designed and used to construct a CNN backbone with simplicity and accessibility to extract features. (3) The performance of the CNN-Swin model is validated on the open FGSC-23 dataset and a dataset containing typical military ship categories based on open-source images. The results show that the model achieved accuracies of 90.9% and 91.9% for the FGSC-23 dataset and the military ship dataset, respectively, outperforming the existing nine state-of-the-art approaches. (4) The good extraction effect on the ship features of the CNN-Swin model is validated as the backbone of the three state-of-the-art detection methods on the open datasets HRSC2016 and FAIR1M. The results show the great potential of the CNN-Swin backbone with self-attention in ship detection.

show abstract

Enhancement of Ship Type Classification from a Combination of CNN and KNN

Cited by 18 publications

References 28 publications

A small fishing vessel recognition method using transfer learning based on laser sensors

A small fishing vessel recognition method using transfer learning based on laser sensors

A Marine Small-Targets Classification Algorithm Based on Improved Convolutional Neural Networks

Fine-Grained Ship Classification by Combining CNN and Swin Transformer

Contact Info

Product

Resources

About