全色胶片
多光谱图像
高光谱成像
锐化
人工智能
图像融合
计算机科学
计算机视觉
均方误差
图像分辨率
图像质量
遥感
图像(数学)
数学
地质学
统计
作者
Hongwen Lin,Anqing Zhang
标识
DOI:10.1109/icivc.2017.7984604
摘要
Hyperspectral image applications have been explored in various areas, but they are often suffered from coarser spatial resolutions. In recent years, many pan-sharpening approaches which are originally used for fusing panchromatic image with multispectral one have been adapted to hyperspectral images. Most of them ignore the fact that the spectral coverage of the panchromatic image does not match the wavelength acquisition range of the hyperspectal one. In this paper, we proposed an improved HySure method which pays more attention to the bands of hyperspectal image that not covered by panchromatic one. HySure method is used twice in our method. First, it is used to fuse the original observed hyperspectal image with the panchromatic one, and the fusion result is used to construct an intermediate multispectral image which has the same spectral coverage as the hyperspectal one. Then the hyperspectal image and the multispectral one are fused by HySure method again. Experimental results show that improved method is superior to the original one in some image quality measurements, such as cross correlation (CC), root-mean-square error (RMSE), spectral angle mapper (SAM), universal image quality index (UIQI), and relative dimensionless global error in synthesis (ERGAS).
科研通智能强力驱动
Strongly Powered by AbleSci AI