Scene Parsing Using Region-Based
Matthew R. Boutell, Jiebo Luo, Christopher M. Brown · 2007
Semantic classification is a challenging problem in computer vision. In contrast to the common approach of using low-level features computed from the whole scene, we propose scene parsing utilizing semantic object detectors (e.g., sky, foliage, and pavement) and region-based scene-configuration models. Because semantic detectors are faulty in practice, it is crit- ical to develop a region-based generative model of outdoor scenes based on characteristic objects in the and spatial relation- ships between them. Since a fully connected configuration model is intractable, we chose to model pairwise relationships between regions and estimate probabilities using loopy belief propagation on a factor graph. We demonstrate the promise of this approach on a set of over 2000 outdoor photographs, comparing it with existing discriminative approaches and those using low-level features.