Monocular right-angle building hypothesis generation in regularized urban areas by pose clustering

A complexity reduction in monocular building extraction from aerial imagery may be achieved by decomposing the extraction problem into three sequential steps. This paper focuses on the first of these steps, the selection process, during which an image subset likely to contain a single building is extracted. One of the means to realize this is by pose clustering. Based on vote accumulation, pose clustering can offer some advantages, such as reduced complexity and a false alarm rate prediction capability. This paper describes a voting scheme for right-angle flat-roof buildings, from which image space building location hypotheses (ISBLHs) may be efficiently generated for regularized urban areas. The proposed scheme incorporates weights, constraints, and uncertainties that should be implemented due to the nature Of aerial imagery. Additionally, based on an occupancy model, a random vote accumulation and threshold analysis of the proposed voting scheme is presented. This scheme was tested on both simulated and real imagery, and the obtained results are discussed and analyzed.