Heterogeneous Spatio-Spectral-Temporal Image Fusion using DASCNN for Remote Sensing Applications

This paper presents a novel approach for heterogeneous spatiotemporal-spectral image fusion using a A Deep Artistic Sequence-based convolutional neural network (DASCNN) combined with Point-Plane Distance(PPD) method. Our framework effectively integrates spatial, temporal, and spectral information from multisource observationstoproducehigh-qualityfusedimages.Evaluations using Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE), and Pearson Correlation demonstrate significant improvements, with a PSNR increase of 4.08 dB and an MSE reduction of 0.0135 compared to baseline methods. The proposed method achieves a Pearson Correlation coefficient of 0.892, reflectingexcellentfusionquality.Thisapproachoffersa robust and adaptable solution for enhancing remote sensing image quality and information content across various applications.