Random Exploration of the Procedural Space for Single-View 3D Modeling of Buildings
International Journal of Computer Vision
A Bayesian approach for scene interpretation with integrated hierarchical structure
DAGM'11 Proceedings of the 33rd international conference on Pattern recognition
Hi-index | 0.00 |
We use a MRF with asymmetric pairwise compatibility constraints between direct pixel neighbors to solve a constrained binary image segmentation task. The model is constraining shape and alignment of individual contiguous binary segments by introducing auxiliary labels and their pairwise interactions. Such representation is not necessarily unique. We study several ad-hoc labeling models for binary images consisting of nonoverlapping rectangular contiguous regions. Nesting and equivalence of these models are studied. We observed a noticeable increase in performance even in cases when the differences between the models were seemingly insignificant. We use the proposed models for segmentation of windowpanes and windows in orthographically rectified façade images. Segmented window patches are always axis-parallel nonoverlapping rectangles which must also be aligned in our strongest model. We show experimentally that even very weak data model in the MAP formulation of the optimal segmentation problem gives very good segmentation results. © 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 69–79, 2009. A preliminary version of the paper was presented at the 12th International Workshop on Combinatorial Image Analysis (Čech and Šára, 2008).