Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks
Side-scan sonar is widely used in underwater rescue and the detection of undersea targets, such as shipwrecks, aircraft crashes, etc. Automatic object classification plays an important role in the rescue process to reduce the workload of staff and subjective errors caused by visual fatigue. However,...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/15/1823 |
| _version_ | 1797525736983101440 |
|---|---|
| author | Qiang Ge Fengxue Ruan Baojun Qiao Qian Zhang Xianyu Zuo Lanxue Dang |
| author_facet | Qiang Ge Fengxue Ruan Baojun Qiao Qian Zhang Xianyu Zuo Lanxue Dang |
| author_sort | Qiang Ge |
| collection | DOAJ |
| description | Side-scan sonar is widely used in underwater rescue and the detection of undersea targets, such as shipwrecks, aircraft crashes, etc. Automatic object classification plays an important role in the rescue process to reduce the workload of staff and subjective errors caused by visual fatigue. However, the application of automatic object classification in side-scan sonar images is still lacking, which is due to a lack of datasets and the small number of image samples containing specific target objects. Secondly, the real data of side-scan sonar images are unbalanced. Therefore, a side-scan sonar image classification method based on synthetic data and transfer learning is proposed in this paper. In this method, optical images are used as inputs and the style transfer network is employed to simulate the side-scan sonar image to generate “simulated side-scan sonar images”; meanwhile, a convolutional neural network pre-trained on ImageNet is introduced for classification. In this paper, we experimentally demonstrate that the maximum accuracy of target classification is up to 97.32% by fine-tuning the pre-trained convolutional neural network using a training set incorporating “simulated side-scan sonar images”. The results show that the classification accuracy can be effectively improved by combining a pre-trained convolutional neural network and “similar side-scan sonar images”. |
| first_indexed | 2024-03-10T09:17:15Z |
| format | Article |
| id | doaj.art-afb11c0846b04304be4e9239fbdce078 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T09:17:15Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-afb11c0846b04304be4e9239fbdce0782023-11-22T05:31:28ZengMDPI AGElectronics2079-92922021-07-011015182310.3390/electronics10151823Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural NetworksQiang Ge0Fengxue Ruan1Baojun Qiao2Qian Zhang3Xianyu Zuo4Lanxue Dang5Henan Key Laboratory of Big Data Analysis and Processing, School of Computer and Information Engineering, Henan University, Kaifeng 475004, ChinaHenan Key Laboratory of Big Data Analysis and Processing, School of Computer and Information Engineering, Henan University, Kaifeng 475004, ChinaHenan Key Laboratory of Big Data Analysis and Processing, School of Computer and Information Engineering, Henan University, Kaifeng 475004, ChinaThe Institute of Acoustics of the Chinese Academy of Sciences, Chinese Academy of Sciences, Beijing 100190, ChinaHenan Key Laboratory of Big Data Analysis and Processing, School of Computer and Information Engineering, Henan University, Kaifeng 475004, ChinaHenan Key Laboratory of Big Data Analysis and Processing, School of Computer and Information Engineering, Henan University, Kaifeng 475004, ChinaSide-scan sonar is widely used in underwater rescue and the detection of undersea targets, such as shipwrecks, aircraft crashes, etc. Automatic object classification plays an important role in the rescue process to reduce the workload of staff and subjective errors caused by visual fatigue. However, the application of automatic object classification in side-scan sonar images is still lacking, which is due to a lack of datasets and the small number of image samples containing specific target objects. Secondly, the real data of side-scan sonar images are unbalanced. Therefore, a side-scan sonar image classification method based on synthetic data and transfer learning is proposed in this paper. In this method, optical images are used as inputs and the style transfer network is employed to simulate the side-scan sonar image to generate “simulated side-scan sonar images”; meanwhile, a convolutional neural network pre-trained on ImageNet is introduced for classification. In this paper, we experimentally demonstrate that the maximum accuracy of target classification is up to 97.32% by fine-tuning the pre-trained convolutional neural network using a training set incorporating “simulated side-scan sonar images”. The results show that the classification accuracy can be effectively improved by combining a pre-trained convolutional neural network and “similar side-scan sonar images”.https://www.mdpi.com/2079-9292/10/15/1823style transfertarget classificationside-scan sonar imagestransfer learningconvolutional neural network |
| spellingShingle | Qiang Ge Fengxue Ruan Baojun Qiao Qian Zhang Xianyu Zuo Lanxue Dang Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks Electronics style transfer target classification side-scan sonar images transfer learning convolutional neural network |
| title | Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks |
| title_full | Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks |
| title_fullStr | Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks |
| title_full_unstemmed | Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks |
| title_short | Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks |
| title_sort | side scan sonar image classification based on style transfer and pre trained convolutional neural networks |
| topic | style transfer target classification side-scan sonar images transfer learning convolutional neural network |
| url | https://www.mdpi.com/2079-9292/10/15/1823 |
| work_keys_str_mv | AT qiangge sidescansonarimageclassificationbasedonstyletransferandpretrainedconvolutionalneuralnetworks AT fengxueruan sidescansonarimageclassificationbasedonstyletransferandpretrainedconvolutionalneuralnetworks AT baojunqiao sidescansonarimageclassificationbasedonstyletransferandpretrainedconvolutionalneuralnetworks AT qianzhang sidescansonarimageclassificationbasedonstyletransferandpretrainedconvolutionalneuralnetworks AT xianyuzuo sidescansonarimageclassificationbasedonstyletransferandpretrainedconvolutionalneuralnetworks AT lanxuedang sidescansonarimageclassificationbasedonstyletransferandpretrainedconvolutionalneuralnetworks |