Deep learning for multisensor image resolution enhancement
| Autor: | Susan M. Bridges, John Rushing, J. M. Beck, C. Collins, Sara Graves |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
010504 meteorology & atmospheric sciences
Pixel Computer science business.industry Deep learning Computer Science::Neural and Evolutionary Computation Multispectral image 0211 other engineering and technologies Pattern recognition 02 engineering and technology Spectral bands 01 natural sciences Convolutional neural network Panchromatic film Computer Science::Computer Vision and Pattern Recognition Image scaling Computer vision Artificial intelligence business Image resolution 021101 geological & geomatics engineering 0105 earth and related environmental sciences |
| Zdroj: | GeoAI@SIGSPATIAL |
| DOI: | 10.1145/3149808.3149815 |
| Popis: | We describe a deep learning convolutional neural network (CNN) for enhancing low resolution multispectral satellite imagery without the use of a panchromatic image. For training, low resolution images are used as input and corresponding high resolution images are used as the target output (label). The CNN learns to automatically extract hierarchical features that can be used to enhance low resolution imagery. The trained network can then be effectively used for super-resolution enhancement of low resolution multispectral images where no corresponding high resolution image is available. The CNN enhances all four spectral bands of the low resolution image simultaneously and adjusts pixel values of the low resolution to match the dynamic range of the high resolution image. The CNN yields higher quality images than standard image resampling methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|