Skip to Main Content
Hyperspectral remote sensing is a new and fast growing remote sensing technology that is currently being investigated by researchers and scientists. One of the most important hyperspectral image analysis is to decompose a mixed pixel into a collection of endmembers and their corresponding abundance fractions, namely spectral unmixing. However, there is an unprecedented explosion of the hyperspectral remote sensing data. The capability of spectral unmixing with time-critical constraints from a mass hyperspectral remote sensing data has soon been an urgent requirement in many missions. Based on the original Vertex Component Analysis (VCA) endmember extraction algorithm, this paper makes full use of the advantages of Symmetrical Multiprocessing (SMP) cluster parallel environment and proposes a parallel VCA algorithm with two-level data partitioning strategy to overcome the time consuming problem. In experiment, this algorithm demonstrates high performance in hyperspectral remote sensing data exploration.