Change detection of multi-temporal oblique aerial images

Due to the rapidly urbanization development, to monitor the change of city environment is more important for urban land resource management. Different to traditional vertical aerial image (VAI), the oblique aerial image (OAI) shows more stereoscopic for manually recognition, and has more information practically on building façade. Various studies has investigated the potential of its applications, such as building seismic damage assessment, performing large area mapping by multi-views image mosaicking, and building objects extraction and classification. In this study, both VAIs and OAIs are collected from airborne and UAV platform in two different periods for change detection purpose. Through photogrammetry techniques including orientation reconstruction and dense image matching, the colored high density 3D point clouds of first period data are generate from both vertical and oblique images. A virtual image has same viewpoint of one selected second period master image can thus be generated by considering hidden points and back-projection. Then, a feature matching scheme is performed on virtual image and master image to find the different area.