Zhenjiu Xiao
ABSTRACT
Abstract:Aiming at the problem that the existing models are not enough to extract the spatial details and feature channel information of remote sensing images, a super-resolution reconstruction model of remote sensing images is proposed, which integrates the receptive field and the attention mechanism. In the depth feature extraction stage of the model, several cascaded receptive field and coordinate attention blocks (RFCAB) are designed to fully extract the depth features of the image: Firstly, an RFB-CA module is designed inside the residual in residual dense block (RRDB). The model can use convolution of different scales to extract multi-scale spatial features and make both channel and space dimensions get attention. At the same time, in the process of learning features, the model pays more attention to the useful channels for the current task, so as to improve the feature representation ability of the model. In order to further improve the recovery ability of the model to detail information, a multi-scale fusion module (MSFM) was designed to obtain more detailed features by weighted fusion of features at different levels. In the 2x, 3x and 4x overscore reconstruction of DOTA dataset, the PSNR/SSIM value of this model is increased by 0.13dB/0.003, 0.17dB/0.007 and 0.24dB/0.013 compared with ESRGAN, respectively. In the 2x, 3x and 4x over-fraction reconstruction of AID dataset, the PSNR/SSIM value is increased by 0.15dB/0.004, 0.20dB/0.009 and 0.26dB/0.015 compared with ESRGAN, respectively. The experimental results show that the reconstruction effect of this model is better than other classical algorithms, and it has certain practical significance.
- Xue Yi, Li Bo, ZHANG Guangke. Discussion on the status quo and development of satellite remote sensing application in China [J]. China Aerospace,2020(04):51-53.Google Scholar
- Harris, James L.Diffraction and resolving power[J].Journal of the Optical Society of America,1964,54(7):931-936.Google Scholar
- Tsai, R. Y.HuangT.Multiple frame image restoration and registration [M] //Advances in Computer Vision&ImageProcessing.Greenwich,UK:Jai Press Inc.1984:317-339.Google Scholar
- Kim K I, Kwon Y. Single-image super-resolution using sparse regression and natural image prior[J].IEEE transactions on pattern analysis and machine intelligence,2010,32(6):1127-1133.Google Scholar
- Li Xin, Wei Hongwei, Zhang Hongqun. Super-resolution reconstruction of single remote sensing image combined with deep learning [J]. Journal of Image and Graphics,2018,23(02):209-218. (in Chinese)Google Scholar
- Huang Shuo, Hu Yong, Gu Mingjian, Super resolution detection algorithm of infrared remote sensing target based on deep learning [J]. Laser and Optoelectronics Progress, 2019,58(16):288-296. (in Chinese)Google Scholar
- Sun L, Zhang H, Mao X, Detection of strong compression depth forgery video based on super-resolution reconstruction[J].Journal of electronics and information,2021,43(10):2967-2975.Google Scholar
- Zhao H, Qu H, Wang X, Super resolution reconstruction of high speed micro scanning image[J].Optical precision engineering,2021,29(10): 2456-2464.Google Scholar
- Wang Liu H, Liu H, network[J].Foreign electronic Image super-resolution reconstruction based on wavelet depth residual measurement technology,2021,40(09):160-164.Google Scholar
- LeCun Y,BottouL,BengioY,etal.Gradient-basedlearning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.Google ScholarCross Ref
- Dong C, Loy C C, He K, Image super-resolution using deep convolutional networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 38(2): 295-307.Google Scholar
- Kim J,LeeJK,LeeKM.Deeply-recursiveconvolutional network for image super-resolution[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 1637-1645.Google Scholar
- Goodfellow I, Pouget-Abadie J, Mirza M, Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.Google ScholarDigital Library
- Ledig C, Theis L, Huszár F, Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4681-4690.Google Scholar
- Wang X, Yu K, Wu S, Esrgan: Enhanced super-resolution generative adversarial networks[C]//European Conference on Computer Vision.Springer,Cham,2018.Google Scholar
- Li Qiang, Wang Xiyuan, He Jiawei. Improved super resolution reconstruction algorithm of remote sensing image based on generative adversarial network. Advances in Laser and Optoelectronics, 2023, 60(10): 432-439. (in Chinese)Google Scholar
- PAM Mendy. Super-resolution reconstruction of airborne Remote sensing image based on Deep learning [Master's Thesis]. Harbin: Harbin Engineering University, 2020.Google Scholar
- Yin Jue Ze, Zhou Ningning. Image superresolution reconstruction network based on dual regression and attention mechanism. Computer system application, 2023, 32 (2) : 111-118. [doi: 10.15888 / j.carol carroll nki. Csa. 008939]Google Scholar
- Liu S,HuangD.Receptive field block net for accurate and fast object detection[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 385-400.Google Scholar
- Hou QB, Zhou DQ, Feng JS. Coordinate attention for efficient mobile network design. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021. 13708–13717.Google Scholar
- Fukushima K. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological cybernetics, 1980, 36(4): 193-202.Google Scholar
- Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.Google Scholar
- Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions[J]. arXiv preprint arXiv:1511.07122, 2015.Google Scholar
- Chen L C, Papandreou G, Schroff F, Rethinking atrous convolution for semantic image segmentation[J]. arXiv preprint arXiv:1706.05587, 2017.Google Scholar
- Yu F, Wang D, Shelhamer E, Deep layer aggregation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 2403-2412.Google Scholar
- Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.Google Scholar
Index Terms
- Super-resolution reconstruction of remote sensing image by fusion of receptive field and attention
Recommendations
A new framework for remote sensing image super-resolution
Jointly representing an image with different types of features is proposed in feature extraction stage.Multi-type feature dictionaries are obtained in sparse representation stage to capture the different structures of the image.Multiple HR patches can ...
TransRA: transformer and residual attention fusion for single remote sensing image dehazing
AbstractHaze seriously reduces the quality of optical remote sensing images, resulting in poor performance in many applications, such as remote sensing image change detection and classification. In recent years, deep learning models have achieved ...
Remote Sensing Image Super-Resolution Based on Lorentz Fitting
AbstractDue to the effect of the model mismatch error between the point spread function (PSF) and actual blur kernel, the performance of remote sensing image super-resolution (SR) is usually poor. In this paper, we propose a novel remote sensing image ...
Comments