An unsupervised classification method based on the H/α classifier and artificial immune system (AIS) is proposed to overcome the inefficiencies that arise when traditional classification methods deal with polarimetric synthetic aperture radar (PolSAR) data having large numbers of overlapping pixels and excess polarimetric information. The method is composed of two steps. First, Cloude–Pottier decomposition is used to obtain the entropy H and the scattering angle α . The classification result based on the H/α plane is used to initialize the AIS algorithm. Second, to obtain accurate results, the AIS clonal selection algorithm is used to perform an iterative calculation. As a self-organizing, self-recognizing, and self-optimizing algorithm, the AIS is able to obtain a global optimal solution and better classification results by making use of both the scattering mechanism of ground features and polarimetric scattering characteristics. The effectiveness and feasibility of this method are demonstrated by experiments using a NASA-JPL PolSAR image and a high-resolution PolSAR image of Lingshui autonomous county in Hainan Province.
The Open Geospatial Consortium (OGC) standard-compliant services define a set of standard interfaces for geospatial
Web services to achieve the interoperability in an open distributed computing environment. Grid technology is a
distributed computing infrastructure to allow distributed resources sharing and coordinated problem solving. Based on
the OGC standards for geospatial services and grid technology, we propose the geospatial grid portal to integrate and
interoperate grid-enabled geospatial services. The implementation of the geospatial grid portal is based on a three-tier
architecture which consists of grid-enabled geospatial services tier, grid service portal tier and application tier. The OGC
standard-compliant services are deployed in a grid environment, the so-called grid-enabled geospatial services. Grid
service portals for each type of geospatial services, including WFS, WMS, WCS and CSW, provide a single point of
Web entry to discover and access different types of geospatial information. A resource optimization mechanism is
incorporated into these service portals to optimize the selection of grid nodes. At the top tier, i.e. the application tier, the
client interacts with a semantic middleware for the grid CSW portal, thus allows the semantics-enabled search. The
proposed approach can not only optimize the grid resource selection among multiple grid nodes, but also incorporate the
power of Semantic Web technology into geospatial grid portal to allow the precise discovery of geospatial data.