| The features of remote sensing images like the large amount of data and the changeful ofterrain feature decide the complexity of the change detection technology. At the base of theconclusions of the change detection technology all over the world, with the QuickBird(HR)images as the main source, around the algorithm of fast change detection on feature libraryof remote sensing imageries, this paper develops several results:(1) Under the high performance colony parallel processing environment, taking theincorporate change detection technical flow and the system frame as the backing, this paperanalyses the features of the representative terrain feature, establishes a feature library, andstudies an algorithm based on the feature library of remote-sensing images.(2) This paper uses the binary mask based on CVA adaptive threshold. This methodthrough the adaptive threshold divided to determine the changes in the scope of the imageriesaccurately first, generating record changes and no-changes binary mask of the imageries, in orderto carry out the first filtration for the imageries. Then, using the mask filter method makes thechange imageries.(3) With the help of multi-type feature library and classify system, match the typicalsamples of the feature library with the object features by full wave bands segmentation andvector analysis, namely, automatically change detection. This paper puts up an improvedalgorithm to match features which is called Multi-criteria rules.(4) With the technical methods and process flow of the change detection based onmulti-type feature library, this paper develops and designs an OBIA intelligent System of HR,besides incorporated the entire job process stream. |
PDF Full Text Request