Building change detection from remotely sensed images based on spatial domain analysis and Markov random field

Abstract

With the rapid development of urban areas, construction areas are constantly appearing. Those changed areas require timely monitoring to provide up-to-date information for urban planning and mapping. As a result, it is a challenge to develop an effective change detection technique. In this work, a method for detecting building changes from multitemporal high-resolution aerial images is proposed. Different from traditional methods, which usually depict building changes in the color domain (e.g., using pixel values or its variants as features), this work focuses on analyzing building changes in the spatial domain. Moreover, contextual relations are explored as well, in order to achieve a robust detection result. In detail, corners are first extracted from the image and an irregular Markov random field model is then constructed based on them. Energy terms in the model are appropriately designed for describing the geometric characteristics of the building. Change detection is treated as a classification process, so that the optimal solution indicates corners belonging to changed buildings. Finally, changed areas are illustrated by linking preserved corners followed by postprocessing steps. Experimental results demonstrate the capabilities of the proposed method for change detection.