TY - GEN
T1 - Gradual Deep Residual Network for Remote Sensing Images Fusion
AU - Ilyas Tchenar, Mohammed
AU - Wang, Yunhong
AU - Liu, Qingjie
AU - El Amin Larabi, Mohammed
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/23
Y1 - 2020/10/23
N2 - Remote sensing image fusion (also known as pansharpening) aims to improve the spatial resolution of multispectral (MS) images using high frequency details extracted from Panchromatic (PAN) images. Recently, residual learning (ResNet) exhibits improved performance in many application domains. At the same time, numerous upsampling methods were developed, from the classical interpolation to deep learning based methods. In this paper, the Gradual Deep Residual Network (GDRN) is developed. The principle key of GDRN is that: instead of using one step upsampling layer, we progressively upscale and fuse MS and PAN images at two pyramid levels where each of them consists of a residual block and one step upsampling layer with a scale factor of 2.
AB - Remote sensing image fusion (also known as pansharpening) aims to improve the spatial resolution of multispectral (MS) images using high frequency details extracted from Panchromatic (PAN) images. Recently, residual learning (ResNet) exhibits improved performance in many application domains. At the same time, numerous upsampling methods were developed, from the classical interpolation to deep learning based methods. In this paper, the Gradual Deep Residual Network (GDRN) is developed. The principle key of GDRN is that: instead of using one step upsampling layer, we progressively upscale and fuse MS and PAN images at two pyramid levels where each of them consists of a residual block and one step upsampling layer with a scale factor of 2.
KW - component
KW - multispectral
KW - panchromatic
KW - pansharpening
KW - residual network
UR - https://www.scopus.com/pages/publications/85101113673
U2 - 10.1109/ICSIP49896.2020.9339380
DO - 10.1109/ICSIP49896.2020.9339380
M3 - 会议稿件
AN - SCOPUS:85101113673
T3 - 2020 IEEE 5th International Conference on Signal and Image Processing, ICSIP 2020
SP - 269
EP - 274
BT - 2020 IEEE 5th International Conference on Signal and Image Processing, ICSIP 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE International Conference on Signal and Image Processing, ICSIP 2020
Y2 - 23 October 2020 through 25 October 2020
ER -