A NEOTERIC APPROACH FOR SHADOW DETECTION IN HIGH RESOLUTION SATELLITE IMAGES
K. Lakshmi Manasa
M.Tech Student, Department of Electronics and Communication Engineering, Sri Venkateswara University College of Engineering, Tirupati, Andhra Pradesh, India-517502. , IN
G. Umamaheswara Reddy
M.Tech Student, Department of Electronics and Communication Engineering, Sri Venkateswara University College of Engineering, Tirupati, Andhra Pradesh, India-517502. , IN
T.Venkata Krishnamoorthy
M.Tech Student, Department of Electronics and Communication Engineering, Sri Venkateswara University College of Engineering, Tirupati, Andhra Pradesh, India-517502. , IN
Keywords: Histogram, Automatic threshold, Image index, Principal component, Shadow pixels.
Abstract
High resolution multispectral satellite images contain more information and extracting the region of interest from these images may cause some problems due to the presence of the object shadow. There is some state of art methods for these shadow detection, but doesn’t show accurate results due to miss predictions occurs while detecting the shadow regions. In this paper, an image index based on principal component analysis is developed for shadow detection using more than one band. The shadow detector index is used to distinguish between shadow and non shadow pixels based on spectral difference. Shadow pixels are divided from the index histogram by using an automatic threshold identity method. Experimental results show that the proposed method is superior in terms of subjective and objective analysis.
How to Cite
References
NA