Study on WorldView-2 Image Fusion Method Based on NMF and HCS Transform

Abstract

With the launch and rapid development of a novel satellite WorldView-2, study on fusion of panchromatic and multispectral images from the satellite has become a hot spot. As there are generally a pair of contradictions existing in the panchromatic and multispectral image fusion method: either failure to avoid spectral distortion, or need of introducing a complex and time-consuming frequency decomposition and reconstruction process, a panchromatic and multispectral image fusion method based on non-negative matrix factorization (NMF) and hyperspherical color sharpening (HCS) was proposed in this paper. Owing to the mismatch of special coverage range of Worldview-2 panchromatic and multispectral images, the intensity component I extracted from multispectral images differs greatly from that extracted from panchromatic images (PAN), causing increased spectral distortion. In the component I extraction method based on NMF proposed in this paper, image fusion is conducted using the advantage that NMF can automatically find the hidden mode or trend behind data and further using the WorldView-2 faced HCS transform. The experimental results show that this algorithm can significantly retain the spectral characteristics, and does not contain a frequency decomposition and reconstruction process, in addition, spatial detail information is effectively incorporated, so the algorithm has simple calculation and good real-time property, and has important application reference value for fusion systems that need rapid interactive processing and real-time visualization.