High resolution ratio satellite remote-sensing image architecture profile extraction method

Abstract

The utility model discloses an extracting method of building contour in a high resolution remote sensing image of satellite, comprising the following steps: (1) the image is pretreated to improve the definition of the image; (2) a parameter of the split minimum area is defined by the size of the extracted building, the split of the high solution remote sensing image is performed based on the objective; (3) the edge of the split image is fitted using the dynamic contour model calculation based on the gradual vector flow; (4) vectorization; (5) optimizing processing. The utility model has advantages that the method is able to reflect the actual contour of the building and the output is of vector format, which is able to update the vector data of GIS directly.

Description

technical field [0001] The invention relates to a method for extracting the outline of a structure in a high-resolution satellite remote sensing image, and belongs to the application field of high-resolution satellite remote sensing image processing and information extraction technology. Background technique [0002] Automatic recognition of object types from remote sensing images and accurate measurement of their shape and size are hotspots and difficulties in remote sensing image information extraction and photogrammetry research, and are also key issues in the eventual highly automated acquisition of basic geographic information from images. At present, the progress of high-resolution remote sensing image data processing and information extraction methods is relatively slow, and manual interpretation and interpretation are still common working methods, which are time-consuming and labor-intensive, and have become the main bottleneck factor restricting the wide application ...

AI Technical Summary

Problems solved by technology

At present, the traditional single-scale image information extraction method based on pixel spectral features has obvious defects in the extraction of artificial ground objects in high-resolution satellite remote sensing images.

For example, in the process of image segmentation, due to noise or small differences in gray levels, adjacent pixels belonging to different types of features will be easily merged into one area object during segmentation, resulting in wrong or missed extraction of ground features.

Images