Abstract
Hyperspectral (HS) images usually have high spectral resolution and low spatial resolution (LSR). However, multispectral (MS) images have high spatial resolution (HSR) and low spectral resolution. HS–MS image fusion technology can combine both advantages, which is beneficial for accurate feature classification. Nevertheless, heterogeneous sensors always have temporal differences between LSR-HS and HSR-MS images in the real cases, which means that the classical fusion methods cannot get effective results. For this problem, we present a fusion method via spectral unmixing and image mask. Considering the difference between the two images, we firstly extracted the endmembers and their corresponding positions from the invariant regions of LSR-HS images. Then we can get the endmembers of HSR-MS images based on the theory that HSR-MS images and LSR-HS images are the spectral and spatial degradation from HSR-HS images, respectively. The fusion image is obtained by two result matrices. Series experimental results on simulated and real datasets substantiated the effectiveness of our method both quantitatively and visually.
Highlights
Hyperspectral (HS) images are playing important roles in agriculture, medical science, remote sensing, and other fields because of its high spectral resolution [1]
We propose a new HS–MS fusion method based on linear spectral mixture model (LSMM), which investigates the endmember signatures’ spatial relationship between low spatial resolution (LSR)-HS image and High spatial resolution (HSR)-MS image
The proposed method and other six fusion methods, including coupled nonnegative matrix factorization (CNMF) [23], fast fusion based on Sylvester equation (FUSE) [18], generalized Laplacian pyramid (GLP) [17], Gram–Schmidt adaptive (GSA) [16], HS Superresolution (HySure) [20] and MAPSMM [21] are used to fuse and compare the results (The comparative methods’ codes are download from http://naotoyokoya.com/Download.html)
Summary
Hyperspectral (HS) images are playing important roles in agriculture, medical science, remote sensing, and other fields because of its high spectral resolution [1]. In order to maintain a certain signal-to-noise ratio (SNR), the spatial resolution has to be sacrificed. Multispectral (MS) images often have higher spatial resolution than HS images. High spatial resolution (HSR) information helps to obtain more accurate locations and shapes of ground objects [2], and spectral information helps to identify types of features from images [3]. Fusing low spatial resolution HS (LSR-HS) images and HSR-MS images can obtain HSR-HS images [10], which is very helpful for fine mapping, ground objects identification, and so on
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have