Hybrid Attention Based Residual Network for Pansharpening

Remote Sensing

Sicong Liu¹  Letong Han²  Weiqi Li²  Rui Tan²  Hongfei Fan²  Hongming Zhu²  Qin Liu²  Bowen Du² 

[1] School of Geodesy and Geomatics, Tongji University, 1239 Siping Road Yangpu District, Shanghai 200082, China;School of Software Engineering, Tongji University, 4800 Caoan Road Jiading District, Shanghai 201804, China;

关键词: deep learning;    HARNN;    hybrid attention mechanism;    image fusion;    remote sensing;   

DOI  :  10.3390/rs13101962

来源: DOAJ

【 摘 要 】

Pansharpening aims at fusing the rich spectral information of multispectral (MS) images and the spatial details of panchromatic (PAN) images to generate a fused image with both high resolutions. In general, the existing pansharpening methods suffer from the problems of spectral distortion and lack of spatial detail information, which might prevent the accuracy computation for ground object identification. To alleviate these problems, we propose a Hybrid Attention mechanism-based Residual Neural Network (HARNN). In the proposed network, we develop an encoder attention module in the feature extraction part to better utilize the spectral and spatial features of MS and PAN images. Furthermore, the fusion attention module is designed to alleviate spectral distortion and improve contour details of the fused image. A series of ablation and contrast experiments are conducted on GF-1 and GF-2 datasets. The fusion results with less distorted pixels and more spatial details demonstrate that HARNN can implement the pansharpening task effectively, which outperforms the state-of-the-art algorithms.

【 授权许可】

Unknown