An ANN supported mathematical morphology based algorithm for lakes extraction from satellite images

Abstract

With advances in remote sensing (RS) technology and platforms, more and more high-quality and fine spatial resolution satellite images are available. Manual method of feature extraction from remote sensing imagery is a tedious and time-consuming process. Thus automated and replicable technique plays vital role in updating lake database to evaluate the spatial and temporal evolution of lakes and ponds especially for vastly growing urban areas. This research work presents an artificial neural network (ANN) computed threshold value-based mathematical morphology (MM)-driven approach for extraction of lakes from satellite imageries with better accuracy. Accuracy of developed methodology has been assessed with the ground truths of the study area revealing better performance with different data-sets compared to existing methods. On an average scale for all data-sets used, the proposed algorithm is able to extract lakes with 99.47% accuracy and 0.9397 correlation coefficient (MCC). The existing classification method exhibited an accuracy of 98.75% and correlation coefficient of 0.89049. Similarly, the existing threshold-driven method has 99.31% accuracy and 0.90374 correlation coefficient. Maintenance of actual size and shape of the lakes, run-time control over structuring elements, semi-automation, faster processing, and single band adaptability are features of this work.