Detecting Large Repetitive Structures with Salient Boundaries

This paper presents a novel robust and efficient framework to analyze large repetitive structures in urban scenes. A particular contribution of the proposed approach is that it finds the salient boundaries of the repeating elements even when the repetition exists along only one direction. A perspective image is rectified based on vanishing points computed jointly from edges and repeated features detected in the original image by maximizing its overall symmetry. Then a feature-based method is used to extract hypotheses of repetition and symmetry from the rectified image, and initial repetition regions are obtained from the supporting features of each repetition interval. To maximize the local symmetry of each element, their boundaries along the repetition direction are determined from the repetition of local symmetry axes. For any image patch, we define its repetition quality for each repetition interval conditionally with a suppression of integer multiples of repetition intervals. We determine the boundary along the non-repeating direction by finding strong decreases of the repetition quality. Experiments demonstrate the robustness and repeatability of our repetition detection.