Abstract-Scene labeling consists in labeling each pixel in an image with the category of the object it belongs to. We propose a method that uses a multiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multiple sizes centered on each pixel. The method alleviates the need for engineered features, and produces a powerful representation that captures texture, shape and contextual information. We report results using multiple post-processing methods to produce the final labeling. Among those, we propose a technique to automatically retrieve, from a pool of segmentation components, an optimal set of components that best explain the scene; these components are arbitrary, e.g. they can be taken from a segmentation tree, or from any family of over-segmentations. The system yields record accuracies on the Sift Flow Dataset (33 classes) and the Barcelona Dataset (170 classes) and near-record accuracy on Stanford Background Dataset (8 classes), while being an order of magnitude faster than competing approaches, producing a 320 × 240 image labeling in less than a second, including feature extraction.

No abstract

Abstract-We study the watersheds in edge-weighted graphs. We define the watershed cuts following the intuitive idea of drops of water flowing on a topographic surface. We first establish the consistency of these watersheds: they can be equivalently defined by their "catchment basins" (through a steepest descent property) or by the "dividing lines" separating these catchment basins (through the drop of water principle). Then we prove, through an equivalence theorem, their optimality in terms of minimum spanning forests. Afterward, we introduce a lineartime algorithm to compute them. To the best of our knowledge, similar properties are not verified in other frameworks and the proposed algorithm is the most efficient existing algorithm, both in theory and practice. Finally, the defined concepts are illustrated in image segmentation leading to the conclusion that the proposed approach improves, on the tested images, the quality of watershed-based segmentations.

In this work, we extend a common framework for graph-based image segmentation that includes the graph cuts, random walker, and shortest path optimization algorithms. Viewing an image as a weighted graph, these algorithms can be expressed by means of a common energy function with differing choices of a parameter q acting as an exponent on the differences between neighboring nodes. Introducing a new parameter p that fixes a power for the edge weights allows us to also include the optimal spanning forest algorithm for watershed in this same framework. We then propose a new family of segmentation algorithms that fixes p to produce an optimal spanning forest but varies the power q beyond the usual watershed algorithm, which we term the power watershed. In particular, when q=2, the power watershed leads to a multilabel, scale and contrast invariant, unique global optimum obtained in practice in quasi-linear time. Placing the watershed algorithm in this energy minimization framework also opens new possibilities for using unary terms in traditional watershed segmentation and using watershed to optimize more general models of use in applications beyond image segmentation.

No abstract

The notion of watershed, used in morphological segmentation, has only a digital definition. In this paper, we propose to extend this definition to the continuous plane. Using this continuous definition, we present the watershed differences with classical edge detectors. We then present a metric in the plane for which the watershed is a skeleton by influence zones and show the lower semicontinuous behaviour of the associated skeleton. This theoretical approach suggests an algorithm for solving the eikonal equation: ∇f = g. Finally, we end with some new watershed algorithms, which present the advantage of allowing the use of markers and/or anchor points, thus opening the way towards grey-tone skeletons. RésuméLa notion de ligne de partage des eaux, utilisée en segmentation morphologique dispose uniquement d'une définition digitale. Dans cet article, nous proposons d'étendre la définition de la ligne de partage des eaux au plan

Though conventional coronary angiography (CCA) has been the standard of reference for diagnosing coronary artery disease in the past decades, computed tomography angiography (CTA) has rapidly emerged, and is nowadays widely used in clinical practice. Here, we introduce a standardized evaluation framework to reliably evaluate and compare the performance of the algorithms devised to detect and quantify the coronary artery stenoses, and to segment the coronary artery lumen in CTA data. The objective of this evaluation framework is to demonstrate the feasibility of dedicated algorithms to: (1) (semi-)automatically detect and quantify stenosis on CTA, in comparison with quantitative coronary angiography (QCA) and CTA consensus reading, and (2) (semi-)automatically segment the coronary lumen on CTA, in comparison with expert's manual annotation. A database consisting of 48 multicenter multivendor cardiac CTA datasets with corresponding reference standards are described and made available. The algorithms from 11 research groups were quantitatively evaluated and compared. The results show that (1) some of the current stenosis detection/quantification algorithms may be used for triage or as a second-reader in clinical practice, and that (2) automatic lumen segmentation is possible with a precision similar to that obtained by experts. The framework is open for new submissions through the website, at http://coronary.bigr.nl/stenoses/.

Abstract-We recently introduced watershed cuts, a notion of watershed in edge-weighted graphs. In this paper, our main contribution is a thinning paradigm from which we derive three algorithmic watershed cut strategies: The first one is well suited to parallel implementations, the second one leads to a flexible linear-time sequential implementation, whereas the third one links the watershed cuts and the popular flooding algorithms. We state that watershed cuts preserve a notion of contrast, called connection value, on which several morphological region merging methods are (implicitly) based. We also establish the links and differences between watershed cuts, minimum spanning forests, shortest path forests, and topological watersheds. Finally, we present illustrations of the proposed framework to the segmentation of artwork surfaces and diffusion tensor images.