Research On Shadow Detection Algorithm In High Resolution Remote Sensing Images Based On Multiple Features

Thirty years ago, remote sensing satellites launched. With the rapid development of technology, satellite remote sensing technology has been applied and achieved real benefits in nearly decade. The high-resolution remote sensing images make people exploring and understanding the nature into a new period. Despite the rapid development of remote sensing satellites technology, large size shadows generated by huge trees and building shading the sun light exist in high-resolution remote sensing images. Shadow in high-resolution remote sensing images will affect the interpretation of image information, as well as subsequent image processing. In order to accurately interpretate remote sensing images, shadow of remote sensing image becomes a research hotspot, of which shadow detection is premise and key phase in whole shadow processing.This paper first studies shadow detection of urban remote sensing images. The existing shadow detection of urban remote sensing images algorithms such as adaptive feature selection method, local classification level set method and automatic detection method are analyzed in detail. To aim at the problem that shadow detection algorithms cannot simultaneously well detect partial-bright shadows and shadows in dark object, a kind of high resolution remote sensing images shadow detection method that combine a multiple features is proposed. The algorithm firstly combines principal component analysis, color features and histogram segmentation to construct the detection conditions of various thresholds, then integra various features of remote sensing image for initial detection, finally by analyzing the difference of the RGB models in the shadow and non shadow, uses the color characteristics to detect the shadow region. Experimental results show that the algorithm proposed in this paper can detect partial-bright shadows and shadows in dark object effectively, which makes it applicable for most images. Besides, the whole detection process is completely automatic.Compare with urban remote sensing images, features of snow mountain remote sensing images are more complex. For a better detection of snow mountain shadow, this paper proposes a self-adaptive snow mountain shadow detection method based on blackbody radiation model and adaptive feature selection. The proposed method firstly gets spatial luminance information; secondly, artificial select shadow samples in the image to obtain acquisite color space and threshold information; finally, uses brightness space, color space and threshold to get the candidate shadow and obtains the initial result of shadow detection. Final results are obtained by post-processing. The experimental results prove that the proposed method can get good detection results in snow mountain remote sensing images and part of the city remote sensing images. At the same time, the detection speed is fast.