Building Detection and Extraction from Monocular Imagery by PoseClustering and Matrix Search Algorithm

摘要

This paper is focused on the task of building extraction from high resolution imagery, which is primarily comprised oftwo steps. The first one is the building location by modified pose clustering, and the second is building extraction usinga novel matrix search algorithm. As a generate-and-test algorithm, pose clustering produces some building hypothesesbased on vote accumulation, aimed at image subsets likely to contain just a building. After building hypothesesverification, some false alarms could be eliminated based on geometric rules. Then we focus on image subsets, each ofwhich is a potential region containing a building. Most buildings are comprised of orthogonal and sequential corners.We classify the corners into four types according to the orientation of corresponding edges. Each type of corners islabeled with a tag for identification, such as ABCD, etc. Building contained in each image subset can be represented asa tag sequence. Based on the tag sequence and the matrix formed by the dominate line sets, we develop an efficientmatrix searching algorithm to address the task of extraction. The experiments carried out in our system show thepromising potential of this scheme.