An image understanding system based on the geometrised histograms method: finding the sky in road scenes

Abstract

In this paper, the technique provided by the geometrized histogram method for segmentation and description of color images is developed and improved in order to analyze the adjacency relation of left and right germs of contrast objects (left and right contrast curves) on theSTG. This adjacency relation involves and generalizes the adjacency relation for regions in classical segmentation methods (the so called RAG). The adjacency relation of left and right germs of contrast objects is based on selecting in each layer of STG a “basic” set of linearly ordered bunches that in some sense covers this layer. Using this order relation, the adjacency relation for left and right germs of contrast objects is established. This order relation is also employed for finding the correspondence between left and right germs with prescribed geometric and color-intensity characteristic that are not adjacent and lay apart at a distance. Based on the adjacency relation proposed, a technique for constructing complex contrast objects with a prescribed geometric shape and color-intensity description is proposed. The developed technique is applied to analyzing road scenes in order to find the sky in video sequences. The results of finding the object in video sequences by a programming complex implementing these ideas are presented and discussed.