Abstract
Availability of open land area is a key indicator in assessing and planning urban environments. However, accurate uninhabited surface extraction is still a challenge. In this paper an attempt is made to combine the advantages of partial differential equation (PDE) and random forest (RF) method for segmentation of IRS-1C LISS III satellite image for mapping and discrimination of open land areas. Spatial variations of the pixels in the image are analyzed to identify open land pixels. PDE method denoise and conserve finer details simultaneously by using correlation between the spectral bands and directions of the edges. Low-resolution resultant image patch is mapped to high-resolution image patch by linear regression model. Variance of classification is reduced by training many classifiers using interpolated RF method. This methods elevates the accuracy of the direct RF method and achieves 3.35 dB improvement in PSNR and 6.47 reduction in MSE. Further, discrimination of open land areas is done into distinct classes, using inherent spatial information. Accuracy assessment indicates an overall accuracy of 87% over direct RF method.
Disclosure statement
No potential conflict of interest was reported by the authors.
Additional information
Notes on contributors
Rubina Parveen
Rubina Parveen has completed her B.E. (ECE) in 2004 and M.Tech. (Communication systems) in 2008. She is a research scholar from VTU. She is interested in digital image processing, geo-spatial information science, satellite image analysis and geo-spatial feature extraction. Currently, she has published six international conference papers and three international journal papers.
Subhash Kulkarni
Dr Subhash Kulkarni is working as professor and head of ECE department in PESIT Bengaluru, India. He has competed his engineering from PDA College of Engineering and M.Tech. and Ph.D. from IIT. His expertize area is image processing, signal processing and Vedic math. He is a strong believer of art of living.
V. D. Mytri
Dr V. D. Mytri is working as a principal in AIET Gulbarga, India. He has competed his engineering from PDA College of Engineering and M.Tech. from IIT Madras and Ph.D. from IISc Bengaluru. His expertize area is computer vision, machine learning, image processing, and signal processing. He has more than 50 international journal papers published.