Detection and Compensation of Shadows based on ICA Algorithm in Remote Sensing Image

Abstract

The shadow is one of the basic features of remote sensing images, especially high resolution remote sensing images, and greatly reduces the information of earth targets. The detection and compensation of shadow is important hotspot and difficulty of remote sensing image processing. In view of the present shadow detection and compensation characteristics of remote sensing image, this paper puts forward a mew method by using independent component analysis (ICA) algorithm, grayscale histogram, RGB channels, HIS space transformation and multi-threshold retinex to achieve the shadow detection and compensation. The shadow detection and compensation were verified by the QuickBird remote sensing image, the shadow correct detection rate reached to 80%. The results show that this proposed method with high precision, easy operation, avoided the complex mathematical morphological operation and has good effect of shadow detection and compensation.