Study And Realization Of Remotely Sensed Information Extraction Based On Object-Oriented

Remotely sensed image is the most immediate and abundant carrier of integrated information for ground target. Extracting terrain and thematic information from it automatically is an impending and complicated problem for remote sensing and GIS. Along with the quick development of remotely sensed obtaining technology in outer space, which provides more and more data, study personnel can get little effective information synchronously yet. Automatic extraction of thematic information from remotely sensed data has become bottleneck in remotely sensed information production flow. Extraction method based on spectral character and single target figure character has been developed many years, but interpretation impact is short of anticipation desire despite of getting some evolution.This paper studied remotely sensed information expression of object' manifold recognition characters, put forward the technology of intellectual Object- oriented remotely sensed information extraction based on multi-scale. Method of Object-oriented is not analyzes single pixel, but it is analyzed by pixel muster. So it can be taken into account relationship between the object and environment sufficiently, and use character knowledge storeroom of the object to achieve extraction of remotely sensed image.First we can segment image by multi-scale, and extract character such as straight-line, texture, spectral. Second we can extract objects that we have concerned such as residential area, road, water system and vegetation by rule specially. Last we can use interrelated information of ground target to build expert knowledge storeroom and then by analyzing character to come into being information of ground target so as to offer assistance to users.This paper was divided into seven chapters as follows: The first chapter summarized the present study and development direction about remotely sensed information extraction, and then explained the main study contents, significance, aims and study method in this paper. The second chapter described the Algorithms of Object- oriented remotely sensed information extraction based on multi-scale and character expression of remotely sensed image. The third chapter introduced the principle of segmentation by multi-scale based on fuzzy muster. The fourth chapter introduced the principle of object-oriented classify. The fifth chapter expatiated on testing result by using this method. The sixth chapter introduced Summary and expectation.