Multi-image region growing for integrating disparity maps

Abstract

In this paper, a multi-image region growing algorithm to obtain planar 3-D surfaces in the object space from multiple dense disparity maps, is presented. A surface patch is represented by a plane equation and a set of pixels in multiple images. The union of back projections of all pixels in the set onto the infinite plane, forms the surface patch. Thanks to that hybrid representation of planar surfaces, region growing (both region aggregation and region merging) is performed on all images simultaneously. Planar approximation is done in object space by linear least square estimation using all data points of the region under question in all images. Linear edge segments detected on colour images are used for constraining the region growing during the region aggregation phase as well as for detection of borders of surface patches. Experimental results on disparity maps obtained from high-resolution aerial images of urban areas demonstrate the performance of the algorithm.