Better visual interpretation and high-level feature extraction are always desired for remotely sensed image processing applications. The fulfillment is most prominent when a Multi-Spectral (MS) image fused with a PANchromatic (PAN) image for the same geographic location produces another MS image with added spatial resolution. Development of such fusion algorithms based on approaches like Component Substitution (CS) and Multi-Resolution Analysis (MRA) is continuously researched over the last few decades. In this paper, the authors propose the morphological operator-based image fusion algorithm featuring nonlinear decomposition. Also, the use of morphological operator based spatial filtering is successfully demonstrated for efficiency enhancement of the proposed and a few of the sophisticated image fusion algorithms based on CS, MRA, and state-of-the-art deep learning approach. The potential of the presented work is proved through reduced- and full-resolution assessment procedures utilizing two data sets acquired by WorldView-3 and WorldView-2 satellite sensors.

对于遥感图像处理应用程序而言，始终需要更好的视觉解释和高级特征提取。当针对同一地理位置的多光谱（MS）图像与PAN色度（PAN）图像融合在一起时，产生另一个具有增加的空间分辨率的MS图像时，满足感最为突出。在过去的几十年中，一直在研究基于诸如组件替换（CS）和多分辨率分析（MRA）之类的融合算法。在本文中，作者提出了一种基于非线性非线性分解的基于形态学算子的图像融合算法。此外，还成功展示了基于形态学算子的空间滤波技术对所提出的算法和基于CS，MRA，和最先进的深度学习方法。通过使用WorldView-3和WorldView-2卫星传感器获取的两个数据集，通过降低分辨率和全分辨率的评估程序证明了所提出工作的潜力。