Abstract
Deep learning has shown great power in processing remote sensing data, especially for fine-grained remote sensing ship image classification. However, the lack of a large amount of effective training data greatly limits the performance of neural networks. Based on current data augmentation methods, images of ships on the sea generated for remote sensing have the problem of distortion, blurring, and poor diversity. To tackle this problem, we propose a novel progressive remote sensing ship image data augmentation method that combines ship simulation samples and a neural style transfer (NST) based network to generate a large amount of transferred remote sensing ship images. Our method consists of two stages. The first stage uses a visible light imaging simulation system to generate ship simulation samples through three-dimensional models of real images. This stage can significantly increase the diversity of the training dataset. For the second stage, to eliminate the domain gap between real ship images and ship simulation samples, a few real images and a newly designed NST-based network called Sim2RealNet are employed to realize style transfer from simulation samples to real images. The proposed method was applied to a variety of ship targets to verify its effectiveness compared to other data augmentation methods on remote sensing image classification tasks. The experimental results demonstrate the effectiveness of the proposed method.
Highlights
W ITH the rapid improvement of computer technology and GPU computing power, given sufficient data, deep learning has shown a strong dominance in the field of computer vision, such as image classification [1]–[3], object detection [4]–[6], and semantic segmentation [7], [8]
Our method substantially improves the performance of the convolutional neural networks (CNNs) when compared with the improvements obtained by other data augmentation methods
We proposed a progressive data augmentation method that combines simulation samples and neural style transfer (NST) for remote sensing ship image classification
Summary
W ITH the rapid improvement of computer technology and GPU computing power, given sufficient data, deep learning has shown a strong dominance in the field of computer vision, such as image classification [1]–[3], object detection [4]–[6], and semantic segmentation [7], [8]. Following the success of deep learning and the increasing availability of remote sensing data, deep learning has been playing an increasingly. With sufficient remote sensing data for training, researchers have focused on designing convolutional neural networks (CNNs) to perform feature selection [9]–[12], extraction [13], [14], and coding [15] on high-resolution remote sensing images, thereby improving network performance. Remote sensing data bring unprecedented challenges to deep learning. A lack of sufficient data will lead to the CNN overfitting problem
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
