Fine-Grained Classification of Optical Remote Sensing Ship Images Based on Deep Convolution Neural Network
Marine activities occupy an important position in human society. The accurate classification of ships is an effective monitoring method. However, traditional image classification has the problem of low classification accuracy, and the corresponding ship dataset also has the problem of long-tail dist...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/18/4566 |
| _version_ | 1797482818685632512 |
|---|---|
| author | Yantong Chen Zhongling Zhang Zekun Chen Yanyan Zhang Junsheng Wang |
| author_facet | Yantong Chen Zhongling Zhang Zekun Chen Yanyan Zhang Junsheng Wang |
| author_sort | Yantong Chen |
| collection | DOAJ |
| description | Marine activities occupy an important position in human society. The accurate classification of ships is an effective monitoring method. However, traditional image classification has the problem of low classification accuracy, and the corresponding ship dataset also has the problem of long-tail distribution. Aimed at solving these problems, this paper proposes a fine-grained classification method of optical remote sensing ship images based on deep convolution neural network. We use three-level images to extract three-level features for classification. The first-level image is the original image as an auxiliary. The specific position of the ship in the original image is located by the gradient-weighted class activation mapping. The target-level image as the second-level image is obtained by threshold processing the class activation map. The third-level image is the midship position image extracted from the target image. Then we add self-calibrated convolutions to the feature extraction network to enrich the output features. Finally, the class imbalance is solved by reweighting the class-balanced loss function. Experimental results show that we can achieve accuracies of 92.81%, 93.54% and 93.97%, respectively, after applying the proposed method on different datasets. Compared with other classification methods, this method has a higher accuracy in optical aerospace remote sensing ship classification. |
| first_indexed | 2024-03-09T22:38:53Z |
| format | Article |
| id | doaj.art-9c54448416c74341ad25e27b7c024ecf |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T22:38:53Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-9c54448416c74341ad25e27b7c024ecf2023-11-23T18:44:46ZengMDPI AGRemote Sensing2072-42922022-09-011418456610.3390/rs14184566Fine-Grained Classification of Optical Remote Sensing Ship Images Based on Deep Convolution Neural NetworkYantong Chen0Zhongling Zhang1Zekun Chen2Yanyan Zhang3Junsheng Wang4Liaoning Key Laboratory of Marine Sensing and Intelligent Detection, Dalian Maritime University, Dalian 116026, ChinaLiaoning Key Laboratory of Marine Sensing and Intelligent Detection, Dalian Maritime University, Dalian 116026, ChinaLiaoning Key Laboratory of Marine Sensing and Intelligent Detection, Dalian Maritime University, Dalian 116026, ChinaLiaoning Key Laboratory of Marine Sensing and Intelligent Detection, Dalian Maritime University, Dalian 116026, ChinaLiaoning Key Laboratory of Marine Sensing and Intelligent Detection, Dalian Maritime University, Dalian 116026, ChinaMarine activities occupy an important position in human society. The accurate classification of ships is an effective monitoring method. However, traditional image classification has the problem of low classification accuracy, and the corresponding ship dataset also has the problem of long-tail distribution. Aimed at solving these problems, this paper proposes a fine-grained classification method of optical remote sensing ship images based on deep convolution neural network. We use three-level images to extract three-level features for classification. The first-level image is the original image as an auxiliary. The specific position of the ship in the original image is located by the gradient-weighted class activation mapping. The target-level image as the second-level image is obtained by threshold processing the class activation map. The third-level image is the midship position image extracted from the target image. Then we add self-calibrated convolutions to the feature extraction network to enrich the output features. Finally, the class imbalance is solved by reweighting the class-balanced loss function. Experimental results show that we can achieve accuracies of 92.81%, 93.54% and 93.97%, respectively, after applying the proposed method on different datasets. Compared with other classification methods, this method has a higher accuracy in optical aerospace remote sensing ship classification.https://www.mdpi.com/2072-4292/14/18/4566optical remote sensing ship imagefine grained classificationconvolutional neural networkgradient-weighted class activation mappingself-calibrated convolutionsclass-balanced loss |
| spellingShingle | Yantong Chen Zhongling Zhang Zekun Chen Yanyan Zhang Junsheng Wang Fine-Grained Classification of Optical Remote Sensing Ship Images Based on Deep Convolution Neural Network Remote Sensing optical remote sensing ship image fine grained classification convolutional neural network gradient-weighted class activation mapping self-calibrated convolutions class-balanced loss |
| title | Fine-Grained Classification of Optical Remote Sensing Ship Images Based on Deep Convolution Neural Network |
| title_full | Fine-Grained Classification of Optical Remote Sensing Ship Images Based on Deep Convolution Neural Network |
| title_fullStr | Fine-Grained Classification of Optical Remote Sensing Ship Images Based on Deep Convolution Neural Network |
| title_full_unstemmed | Fine-Grained Classification of Optical Remote Sensing Ship Images Based on Deep Convolution Neural Network |
| title_short | Fine-Grained Classification of Optical Remote Sensing Ship Images Based on Deep Convolution Neural Network |
| title_sort | fine grained classification of optical remote sensing ship images based on deep convolution neural network |
| topic | optical remote sensing ship image fine grained classification convolutional neural network gradient-weighted class activation mapping self-calibrated convolutions class-balanced loss |
| url | https://www.mdpi.com/2072-4292/14/18/4566 |
| work_keys_str_mv | AT yantongchen finegrainedclassificationofopticalremotesensingshipimagesbasedondeepconvolutionneuralnetwork AT zhonglingzhang finegrainedclassificationofopticalremotesensingshipimagesbasedondeepconvolutionneuralnetwork AT zekunchen finegrainedclassificationofopticalremotesensingshipimagesbasedondeepconvolutionneuralnetwork AT yanyanzhang finegrainedclassificationofopticalremotesensingshipimagesbasedondeepconvolutionneuralnetwork AT junshengwang finegrainedclassificationofopticalremotesensingshipimagesbasedondeepconvolutionneuralnetwork |