Siamese Networks Based Deep Fusion Framework for Multi-Source Satellite Imagery

IEEE Access

Javaria Tahir¹  Syed Sohaib Ali²  M. Mohsin Riaz³  Hannan Adeel⁴ 

[1] Computer Engineering, COMSATS University Islamabad, Islamabad, Pakistan;Centre for Advanced Studies in Telecommunication, COMSATS University Islamabad, Islamabad, Pakistan;Department of Computer Science, COMSATS University Islamabad, Islamabad, Pakistan;Department of Electrical &x0026;

关键词: Pansharpening;    image fusion;    deep-learning;    siamese networks;    remote sensing;    depth-of-field;   

DOI  :  10.1109/ACCESS.2022.3143847

来源: DOAJ

【 摘 要 】

A critical aim of pansharpening is to fuse coherent spatial and spectral features from panchromatic and multispectral images respectively. This study proposes deep siamese network based pansharpening model as a two-stage framework in a multiscale setting. In the first stage, a siamese network learns a common feature space between panchromatic and multispectral bands. The second stage follows by fusing the output feature maps of the siamese network. The parameters of these two stages are shared across scales in order to add spatial information consistently (across scales). The spectral information is preserved by adding appropriate skip connections from input multispectral image. Multi-level network parameters sharing mechanism in pyramidal reconstruction of pansharpened image, better preserves spatial and spectral details simultaneously. Experimental work carried out using deep siamese network in multi-scale setting (to obtain inter-band similarity among different sensor data) outperforms several latest pansharpening methods.

【 授权许可】

Unknown