A Cognitive Based Approach for Building Detection from High Resolution Satellite Images

High resolution satellite images are new sources of data for geo-spatial information. In order to automate the process of extraction of information from satellite images emulating human experts, an understanding of the human cognitive processes involved in information extraction from images are required. The objective of this research work is to emulate the human cognitive capabilities by integrating cognitive task analysis for extraction of data from satellite images. Initially, preliminary knowledge about the sequence of cognitive processes which human being utilizes during the interpretation and classification of images was collected. Here, rule based approach for the representation of the knowledge which is obtained from the visual interpretation of image by the human beings. Defined rules are used to determine the buildings in the satellite images using the mixture tuned matched filtering algorithm (MTMF). Further, during knowledge elicitation the domain knowledge is grouped together using support vector classifier. The method is tested using four different sets of high resolution satellite images. The overall average of precision and recall are computed as 99.08% and 75.85%, respectively.