Abstract

Many computer vision applications involve algorithms that can be de- composed in two main steps. In a first step, events or objects are detected and, in a second step, detections are assigned to classes. Examples of such “detection plus classi fication” problems can be found in human pose classi fication, object recognition or action classi fication among others. In this paper, we focus on a special case: depth ordering on single images. In this problem, the detection step consists of the image segmentation, and the classi fication step assigns a depth gra- dient to each contour or a depth order to each region. We discuss the limitations of the classical Precision-Recall evaluation framework for these kind of prob- lems and define an extended framework called “Precision-Recall-Classfication” (PRC). Then, we apply this framework to depth ordering problems and design two speci fic PRC measures to evaluate both the local and the global depth consis- tencies. We use these measures to evaluate precisely state of the art depth ordering systems for monocular images. We also propose an extension to the method of [2] applying an optimal graph cut on a hierarchical segmentation structure. The resulting system is proven to provide better results than state of the art algorithms.