Forest Single-Frame Remote Sensing Image Super-Resolution Using GANs

被引:0
|
作者
Zhao, Yafeng [1 ]
Zhang, Shuai [1 ]
Hu, Junfeng [1 ]
机构
[1] Northeast Forestry Univ, Coll Comp & Control Engn, Harbin 150040, Peoples R China
来源
FORESTS | 2023年 / 14卷 / 11期
关键词
GANs; super-resolution; multi-scale residual; attention mechanism; activation function;
D O I
10.3390/f14112188
中图分类号
S7 [林业];
学科分类号
0829 ; 0907 ;
摘要
Generative Adversarial Networks (GANs) possess remarkable fitting capabilities and play a crucial role in the field of computer vision. Super-resolution restoration is the process of converting low-resolution images into high-resolution ones, providing more detail and information. This is of paramount importance for monitoring and managing forest resources, enabling the surveillance of vegetation, wildlife, and potential disruptive factors in forest ecosystems. In this study, we propose an image super-resolution model based on Generative Adversarial Networks. We incorporate Multi-Scale Residual Blocks (MSRB) as the core feature extraction component to obtain image features at different scales, enhancing feature extraction capabilities. We introduce a novel attention mechanism, GAM Attention, which is added to the VGG network to capture more accurate feature dependencies in both spatial and channel domains. We also employ the adaptive activation function Meta ACONC and Ghost convolution to optimize training efficiency and reduce network parameters. Our model is trained on the DIV2K and LOVEDA datasets, and experimental results indicate improvements in evaluation metrics compared to SRGAN, with a PSNR increase of 0.709/2.213 dB, SSIM increase of 0.032/0.142, and LPIPS reduction of 0.03/0.013. The model performs on par with Real-ESRGAN but offers significantly improved speed. Our model efficiently restores single-frame remote sensing images of forests while achieving results comparable to state-of-the-art methods. It overcomes issues related to image distortion and texture details, producing forest remote sensing images that closely resemble high-resolution real images and align more closely with human perception. This research has significant implications on a global scale for ecological conservation, resource management, climate change research, risk management, and decision-making processes.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] Single-frame super-resolution in remote sensing: a practical overview
    Fernandez-Beltran, Ruben
    Latorre-Carmona, Pedro
    Pla, Filiberto
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2017, 38 (01) : 314 - 354
  • [2] Single-Frame Remote Sensing Image Super-resolution Reconstruction with Sub-blocks Noniterative Scheme
    Sun Tao
    Yang Zhigao
    Lin Liyu
    Qin Qianqing
    [J]. 2006 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-8, 2006, : 1382 - +
  • [3] Neighborhood issue in single-frame image super-resolution
    Su, K
    Tian, Q
    Xue, Q
    Sebe, N
    Ma, JS
    [J]. 2005 IEEE International Conference on Multimedia and Expo (ICME), Vols 1 and 2, 2005, : 1123 - 1126
  • [4] Single-frame image super-resolution using learned wavelet coefficients
    Jiji, CV
    Joshi, MV
    Chaudhuri, S
    [J]. INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, 2004, 14 (03) : 105 - 112
  • [5] Single-frame super-resolution for high resolution optical remote-sensing data products
    Wang, Chao
    Zhu Ruifei
    Bai, Yang
    Zhang, Peng
    Fan, Haiyang
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2021, 42 (21) : 8099 - 8123
  • [6] Single-Frame Remote Sensing Image Super-Resolution Reconstruction Algorithm Based on Two-Dimensional Wavelet
    Zhou, Cui
    Zhou, Jinghong
    [J]. 2018 IEEE 3RD INTERNATIONAL CONFERENCE ON IMAGE, VISION AND COMPUTING (ICIVC), 2018, : 360 - 363
  • [7] Single-frame image super-resolution inspired by perceptual criteria
    Zhou, Fei
    Liao, Qingmin
    [J]. IET IMAGE PROCESSING, 2015, 9 (01) : 1 - 11
  • [8] Single-frame image super-resolution through contourlet learning
    Jiji, C. V.
    Chaudhuri, Subhasis
    [J]. EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING, 2006, 2006 (1)
  • [9] Single-Frame Image Super-resolution through Contourlet Learning
    CV Jiji
    Subhasis Chaudhuri
    [J]. EURASIP Journal on Advances in Signal Processing, 2006
  • [10] A Single-Frame and Multi-Frame Cascaded Image Super-Resolution Method
    Sun, Jing
    Yuan, Qiangqiang
    Shen, Huanfeng
    Li, Jie
    Zhang, Liangpei
    [J]. SENSORS, 2024, 24 (17)