The scope of urbanization variation due to landscape alterations, profoundly affect the ecological features and decision-making process for built-up standards. In various parts of the globe, urbanization studies have identified a significant correlation between substantial human benefits on quality-of life, quantifiable resource utilization and local climatic parameters. Remote sensing environment has developed techniques to estimate change in spatio-temporal attributes in a georeferenced imagery. The intricate multi-signature classes and massive data interpretation for minute urban change detection for Kancheepuram, Tamilnadu. Supervised Land-use-and-Land-Cover (LULC) classification using Neural Network(NN), Minimum Distance, Support Vector Machine(SVM) & Maximum Likelihood technique to estimate change in urban class is performed. Unsupervised classification, inbuilt programmed distance learning algorithm, with ISO and K-means, is performed on preprocessed and enhanced PCAimage. Support vector machine and ISO classification techniques with enhanced imagery, on the prior basis shows more accuracy (80–85%) amongst mentioned techniques. Thus, following SVM to categorize attributes to classes and performing urban change detection. The discrepancy between new land and barren land via SVM practice remain uncertain.
Remote sensing, Band math, Supervised and unsupervised techniques, Normalized indexing
