Satellite Image Super-Resolution via Multi-Scale Residual Deep Neural Network

• Published in: Remote sensing (Basel, Switzerland) Vol. 11; no. 13; p. 1588
• Main Authors: Lu, Tao, Wang, Jiaming, Zhang, Yanduo, Wang, Zhongyuan, Jiang, Junjun
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2019
• Subjects: Algorithms; Artificial neural networks; Clustering; Computer science; convolutional neural network; image analysis; Image degradation; Image detection; Image resolution; International conferences; Learning algorithms; Machine learning; Mapping; multi-scale image; Neural networks; Object recognition; Pattern recognition; Quality; Remote sensing; residual network; Satellite imagery; Satellites; Scaling factors; super-resolution; Texture recognition; United States > US; China
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs11131588

Recently, the application of satellite remote sensing images is becoming increasingly popular, but the observed images from satellite sensors are frequently in low-resolution (LR). Thus, they cannot fully meet the requirements of object identification and analysis. To utilize the multi-scale characteristics of objects fully in remote sensing images, this paper presents a multi-scale residual neural network (MRNN). MRNN adopts the multi-scale nature of satellite images to reconstruct high-frequency information accurately for super-resolution (SR) satellite imagery. Different sizes of patches from LR satellite images are initially extracted to fit different scale of objects. Large-, middle-, and small-scale deep residual neural networks are designed to simulate differently sized receptive fields for acquiring relative global, contextual, and local information for prior representation. Then, a fusion network is used to refine different scales of information. MRNN fuses the complementary high-frequency information from differently scaled networks to reconstruct the desired high-resolution satellite object image, which is in line with human visual experience (“look in multi-scale to see better”). Experimental results on the SpaceNet satellite image and NWPU-RESISC45 databases show that the proposed approach outperformed several state-of-the-art SR algorithms in terms of objective and subjective image qualities.