A Integrated Approach For Shadow Detection Of Buildings In Aerial Image Based On DBM And Image Segmentation

With the development of Remote Sensing,high-spatial resolution aerial image was used widely and widely.In urban aerial images,the poor visibility of features in shadowed regions created by buildings prevents recognition of objects.Shadow is one of problem of high resolution aerial image,it brings many difficulties to image processing,and it affects the extraction of object's edge,identification of objects and registration of images.So how to minimize or removal the effect of shadow is one of important problems in aerial image processing.In high resolution aerial image,shadow processing includes shadow detection and shadow removal.In this paper,I studied some main methods of shadow detection and shadow removal and introduced each method's principle at home and abroad now.I reviewed the previous researches and points out their limitations.Focusing on these issues,a new combined technique on Digital Building Model and image processing method has been introduced for shadow detection and shadow removal in high resolution urban aerial image in this paper.We combine image processing technology with the DBM-based geometric method of computing the zenith angle of the sun and the altitude angle of the sun.Then the detected shadow areas are dealt by threshold segmentation and zero-crossing detection.Due to this method can get its own shadow of the building.About the shadow removal,we use the gray value of roofs of buildings in the aerial image as the restored value.Compared with other methods,this method may detect the shadow areas of the buildings more accurately.Besides,the result of shadow removal is better than other methods.