journal article·2022-04-14Open access

Remote Sensing Scene Data Generation Using Element Geometric Transformation and GAN-Based Texture Synthesis

Zhaoyang Liu, Renxiang Guan, Jingyu Hu, Weitao Chen, Xianju Li

Applied Sciences· Volume 12· Issue 8

Abstract

Classification of remote sensing scene image (RSSI) has been broadly applied and has attracted increasing attention. However, scene classification methods based on convolutional neural networks (CNNs) require a large number of manually labeled samples as training data, which is time-consuming and costly. Therefore, generating labeled data becomes a practical approach. However, conventional scene generation based on generative adversarial networks (GANs) involve some significant limitations, such as distortion and limited size. To solve the mentioned problems, herein, we propose a method of RSSI generation using element geometric transformation and GAN-based texture synthesis. Firstly, we segment the RSSI, extracting the element information in the RSSI. Then, we perform geometric transformations on the elements and extract the texture information in them. After that, we use the GAN-based method to model and generate the texture. Finally, we fuse the transformed elements with the generated texture to obtain the generated RSSI. The geometric transformation increases the complexity of the scene. The GAN-based texture synthesis ensures the generated scene image is not distorted. Experimental results demonstrate that the RSSI generated by our method achieved a better visual effect than a GAN model. In addition, the performance of CNN classifiers was reduced by 0.44–3.41% on the enhanced data set, which is partly attributed to the complexity of the generated samples. The proposed method was able to generate diverse scene data with sufficient fidelity under conditions of small sample size and solve the accuracy saturation issues of the public scene data sets.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Remote Sensing and LiDAR Applications · Remote Sensing in Agriculture · Advanced Image and Video Retrieval Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Computer Science, China University of Geosciences, Wuhan 430074, China

Hubei Key Laboratory of Intelligent Geo-Information Processing, China University of Geosciences, Wuhan 430074, China

Funding

National Natural Science Foundation of China · College Students' Innovative Entrepreneurial Training Plan Program

References (18)

Show source-provided references
1. Karras, T., Aila, T., Laine, S., and Lehtinen, J. (2017). Progressive growing of GANs for improved quality, stability, and variation. arXiv.
2. Zhao, M., Cong, Y., and Carin, L. (2015, January 7–9). On leveraging pretrained GANs for generation with limited data. Proceedings of the 37th International Conference on Machine Learning, Lille, France.
3. Sample generation based on a supervised Wasserstein Generative Adversarial Network for high-resolution remote-sensing scene classification10.1016/j.ins.2020.06.018 ↗
4. A scene images diversity improvement generative adversarial network for remote sensing image scene classification10.1109/LGRS.2019.2953192 ↗
5. Image segmentation and feature extraction10.1109/TSMC.1978.4309944 ↗
6. A comparative study of texture measures for terrain classification10.1109/TSMC.1976.5408777 ↗
7. Texture segmentation using Voronoi polygons10.1109/34.44407 ↗
8. The transport of gallium arsenide in the vapor phase by chemical reaction10.1149/1.2426188 ↗
9. Optical image synthesis (complex amplitude addition and subtraction) by hollographic fourier transformation10.1016/0031-9163(65)90676-1 ↗
10. Efros, A., and Leung, T.K. (1999, January 20–27). Texture synthesis by non-parametric sampling. In Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece.10.1109/ICCV.1999.790383 ↗
11. Zhou, Y., Zhu, Z., Bai, X., Lischinski, D., Cohen-Or, D., and Huang, H. (2018). Non-stationary texture synthesis by adversarial expansion. arXiv.10.1145/3197517.3201285 ↗
12. Jetchev, N., Bergmann, U., and Vollgraf, R. (2016). Texture synthesis with spatial generative adversarial networks. arXiv.
13. AK-means clustering algorithm
14. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., and Bengio, Y. (2014). Generative adversarial networks. arXiv.
15. Imagenet classification with deep convolutional neural networks
16. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
17. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
18. Remote sensing image scene classification: Benchmark and state of the art10.1109/JPROC.2017.2675998 ↗