Performance evaluation of land cover change detection algorithms using remotely sensed data

Remote sensing has long been used as a means of detecting and classifying the different types of data attribute present in the land cover. In general, remote sensing is widely used across variety of real-time applications to identify the change information of geographical areas. The Objective of this work is to study three land cover change detection algorithms such as Image Differencing method, Auto-Correlation function method and Distance Analysis method. In this paper, land cover change is obtained by change detection method from the sequence of annual pattern dataset of multi-date temporal datasets. This work presents a performance comparison of change detection algorithms based on performance metrics Change data and False alarm. From the evaluated results, Autocorrelation function method performs better than other Image differencing and Distance analysis method.