City shadow detecting and removing method based on high-resolution remote sensing image

Abstract

The invention discloses a city shadow detecting and removing method based on a high-resolution remote sensing image. The method comprises the following steps: firstly calculating an image after the bilateral filtration through a threshold value, to obtain a feature value for executing the shadow detection, and executing the region growing to the result by using a graph cutting method, to obtain ashadow mask; and subtracting by using luminance graphs before and after the bilateral filtration, to obtain a detailed graph, and getting a region with weaker texture, completing the detection of a city water area by combining NDWI, removing the part of the water area in the shadow mask, and dividing a shadow and a non-shadow, calculating a shadow spectrum and texture information, and matching toobtain a homogeneous non-shadow area corresponding to each shadow area; and finally removing the non-water-area and water area shadows by using a moment matching and histogram matching method. The method is capable of, in allusion to the complexity of the city high-resolution image surface, greatly improving the shadow detecting and removing effects, and can be used for improving engineering application problems, such as city change detection and ground-object identification.

Description

technical field [0001] The invention belongs to the technical field of remote sensing and photogrammetry, and relates to a water area detection and urban shadow detection and removal method based on high-resolution remote sensing images, in particular to a shadow detection and removal method based on high-resolution remote sensing image optimization moment matching. Background technique [0002] Shadow detection and removal is a key issue in the analysis and application of high-resolution remote sensing images. With the rapid development of remote sensing technology, the spatial resolution of images has reached a relatively high level. In the analysis of urban remote sensing images, shadow extraction can assist the extraction of elevation information such as buildings. Shadow removal can enrich image information and improve object recognition and change. detection and image matching. [0003] High-resolution urban remote sensing images contain rich ground object information...

AI Technical Summary

Problems solved by technology

[0005] The present invention mainly solves the problems existing in the prior art, such as the high complexity of high-resolution urban remote sensing images, unsatisfactory segmentation results, unsmooth color transitions between segmentation blocks, and low fidelity of spectral features; it provides a The shadow detection and removal method combined with water detection and optimal moment matching can effectively improve the effect of shadow detection and removal in urban high-resolution remote sensing images

Images