Translator Disclaimer
14 October 2014 An adaptive PCA fusion method for remote sensing images
Author Affiliations +
Abstract
The principal component analysis (PCA) method is a popular fusion method used for its efficiency and high spatial resolution improvement. However, the spectral distortion is often found in PCA. In this paper, we propose an adaptive PCA method to enhance the spectral quality of the fused image. The amount of spatial details of the panchromatic (PAN) image injected into each band of the multi-spectral (MS) image is appropriately determined by a weighting matrix, which is defined by the edges of the PAN image, the edges of the MS image and the proportions between MS bands. In order to prove the effectiveness of the proposed method, the qualitative visual and quantitative analyses are introduced. The correlation coefficient (CC), the spectral discrepancy (SPD), and the spectral angle mapper (SAM) are used to measure the spectral quality of each fused band image. Q index is calculated to evaluate the global spectral quality of all the fused bands as a whole. The spatial quality is evaluated by the average gradient (AG) and the standard deviation (STD). Experimental results show that the proposed method improves the spectral quality very much comparing to the original PCA method while maintaining the high spatial quality of the original PCA.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Qing Guo, An Li, Hongqun Zhang, and Zhongkui Feng "An adaptive PCA fusion method for remote sensing images", Proc. SPIE 9240, Remote Sensing of the Ocean, Sea Ice, Coastal Waters, and Large Water Regions 2014, 92401H (14 October 2014); https://doi.org/10.1117/12.2074133
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
Back to Top