Multi-label energy minimization for object class segmentation

The task of associating a semantic class to the objects present in an image is challenging because this problem involves the joint segmentation and recognition of the objects. In this work, we use a recent approach embedding several optimization algorithms into a common framework named Power watershed to perform this task. We show how the fast watershed algorithm can be used to minimize an energy function for which the minimizer corresponds to the desired object class segmentation. Higher order potentials are then added to improve label consistency. We also demonstrate that the random walker algorithm can be successfully applied to semantic class segmentation problems. Comparisons with the Graph Cuts algorithm show that the proposed approaches yield better segmentation results, obtained up to twelve times faster on a very challenging indoor scenes dataset.