Multi-Level Image Segmentation for Urban Land-Cover Classifications

Abstract

Variation land-cover features, which include natural and man-made objects, lead to the advent of features that are spectrally similar. Object in urban area tend to have spectral similar response that can easily misclassified from one to another for example in the case of tree and grass as well as asphalt building roof and asphalt road. Object based classification approached instead of pixel based will improved the misclassification yet will increase the accuracy of land-cover classification. Using Worldview-2 multispectral satellite image as a primary data, while normalized Digital Surface Model (nDSM) derived from Light Detection and Ranging (LIDAR) data and indices image, the image segmentation process utilizing multiresolution segmentation algorithm and spectral difference was conducted. Before going through classification process, twelve segmentation levels were constructed to create image objects. Three classification algorithm including Support Vector Machine (SVM), BAYES and K-Nearest Neighbour (KNN) were choose to be tested to identify which algorithm gives the best classification result of the urban area target. The results from the study indicate statistically significant difference in classification accuracy between each algorithm: Based on Kappa statistics, user’s and producer’s accuracy, as well as visual examination and overall accuracy performance, BAYES with overall accuracy of 85.51% has depicted to have the best land-cover classification accuracy result.