Abstract
Abstract. There is a great demand for studying the changes of buildings over time. The current trend for building change detection combines the orthophoto and DSM (Digital Surface Models). The pixel-based change detection methods are very sensitive to the quality of the images and DSMs, while the object-based methods are more robust towards these problems. In this paper, we propose a supervised method for building change detection. After a segment-based SVM (Support Vector Machine) classification with features extracted from the orthophoto and DSM, we focus on the detection of the building changes of different periods by measuring their height and texture differences, as well as their shapes. A decision tree analysis is used to assess the probability of change for each building segment and the traffic lighting system is used to indicate the status "change", "non-change" and "uncertain change" for building segments. The proposed method is applied to scanned aerial photos of the city of Zurich in 2002 and 2007, and the results have demonstrated that our method is able to achieve high detection accuracy.
Highlights
Monitoring and assessing the building changes are important tasks. It is a crucial step for updating the geodatabases, on the other hand, the building change itself is of very much interest for urban related application such as building dynamic analysis, building code compliance and building material flow estimation
Change detection techniques using two-dimensional (2D) low resolution images are intensively studied for assessing changes at the landscape level (Rogan et al, 2002; Song et al, 2001)
We have proposed a supervised method for building change detection, and scanned aerial stereo pairs are used for validating our method
Summary
Monitoring and assessing the building changes are important tasks. On one hand, it is a crucial step for updating the geodatabases, on the other hand, the building change itself is of very much interest for urban related application such as building dynamic analysis, building code compliance and building material flow estimation. Tian et al (2013) proposed a region-based method to compare height and image intensity difference on groups of pixels (segments) for detecting the changes of forest and buildings with Cartosat-1 stereo pairs. We propose to pre-classify the ground scene using the image and DSM, and to apply object-based change detection method on the building class, taking into account their height and textural difference, as well as their shape discrepancies. The advantage of this idea lies in the fact that, by knowing the building classes, we are able to consider the shape differences of buildings.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
