Object-oriented Information Extraction Technology Research Of High Resolution Remote Sensing

High spatial resolution remote sensing technology in recent years made significantprogress. IKONOST and QuikBird make obtaining high-resolution remote sensing imageseasily. High resolution remote sensing image shows more information of surface features.How to make use of abundant information of high resolution remote sensing image is amuch-needed problem.A new method based on new ideas of object-oriented remote sensing image analysis isused to solve the problem of low accuracy faced by traditional methods. This methodutilized multi-scale and multi-features to optimize information extraction result.PGF filter is a capable method for high-resolution remote sensing imagepre-processing, which remove noise effectively with boundary information preserved.Watershed algorithm and region-grow algorithm with shape and spectrum combined ashomogeneity measurement can divide raster images into similar objects effective.Classifier, which based on regional characteristics of object-oriented information, istrained with the pre-entered samples features. Information of remote sensing imageclassification is obtained efficiently by this way.This method has achieved the precision of90percent in applications onhigh-resolution remote sensing images. It overcomes the lack of surface texture and shapeinformation in traditional extraction algorithm. It‘s proved to be an effective objectoriented remote sensing image extraction method based on multi-scale and multi-feature.