Abstract
Spatial regularized sparse unmixing has been proved as an effective spectral unmixing technique, combining spatial information and standard spectral signatures known in advance into the traditional spectral unmixing model in the form of sparse regression. In a spatial regularized sparse unmixing model, spatial consideration acts as an important role and develops from local neighborhood pixels to global structures. However, incorporating spatial relationships will increase the computational complexity, and it is inevitable that some negative influences obtained by inaccurate estimated abundances’ spatial correlations will reduce the accuracy of the algorithms. To obtain a more reliable and efficient spatial regularized sparse unmixing results, a joint local block grouping with noise-adjusted principal component analysis for hyperspectral remote-sensing imagery sparse unmixing is proposed in this paper. In this work, local block grouping is first utilized to gather and classify abundant spatial information in local blocks, and noise-adjusted principal component analysis is used to compress these series of classified local blocks and select the most significant ones. Then the representative spatial correlations are drawn and replace the traditional spatial regularization in the spatial regularized sparse unmixing method. Compared with total variation-based and non-local means-based sparse unmixing algorithms, the proposed approach can yield comparable experimental results with three simulated hyperspectral data cubes and two real hyperspectral remote-sensing images.
Highlights
Hyperspectral unmixing has become an alluring research topic with the development of hyperspectral remote sensors [1,2,3]
Differing from non-local sparse unmixing (NLSU), to obtain a more accurate and efficient SRSU results, a joint local block grouping with noise-adjusted principal component analysis method is used to consider spatial information in a sparse unmixing process
Based on the obtained local block groupings, denoted as XLocal ∈ Rg×(s×s), noise-adjusted principal component analysis (NAPCA) is adopted to select principal reliable local blocks and suppress the existing outliers or noisy points. Arranging all these local blocks in one matrix as XLocal and assuming there existing unreliable components, we develop the basic model as: XLocal = Xreal + Ooutliers where Xreal is represented as the reliable local blocks and Ooutliers is denoted as the outliers’ matrix
Summary
Hyperspectral unmixing has become an alluring research topic with the development of hyperspectral remote sensors [1,2,3]. Differing from NLSU, to obtain a more accurate and efficient SRSU results, a joint local block grouping with noise-adjusted principal component analysis method is used to consider spatial information in a sparse unmixing process. Compared with total variation-based and non-local means-based SRSU algorithms, the proposed joint local block grouping with the NAPCA sparse unmixing method can yield competitive results with state-of-the-art spatial sparse unmixing algorithms using three simulated hyperspectral datasets and two real hyperspectral images. To overcome the weaknesses of aRlegmoortietShemns.s2’0e1ffi, c1i0e, nx cFyORanPdEEmR aRiEnVtaIEiWn the strengths of spatial consideration, a joint local block grou5poifn2g5 with noise-adjusted principal component analysis-based sparse unmixing algorithm is proposed in this pGapenere.rally, non-local spatial information can address much more important spatial correlations thanGfeirnsetr-oalrldye, rnopni-xleolcanlesipgahtbiaolrhinofoodrmsaytsiotenmc,ananaddderxepssermimuechntmalorreesiumltpsoartlasont hspavateiapl rcoovrreedlattihoensse tnhoann-filorcsat-losrpdaetriaplixceolnnseidigehrabtoirohnosohdasvyestaemsig, annifdiceaxnpteproimsietinvtealerfefseuctltosnalSsoRShUavaelpgroorvitehdmtsh.eTseonmonai-nlotacainl stphaetiaadl cvoannstiadgeeraotfionnosnh-alovceaal smigentihfiocdans,t pwoesintieveedefftoecctoomn eSRuSpUwaligthoriatnhomths.erTostmraatiengtayintothiemapdrvoavnetatghee oaflgnoornit-hlomcasl’ mefefitchioendcsy, w. After reorder all these candidates’ distances (ei) in increasing order, if the number of candidates determined by (6) is larger than the gate, the first g candidates are selected, or the local blocks excluded by (6) would be recollected according to the gate and the corresponding ei
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
