We introduce a shape detection framework called Contour Context Selection for detecting objects in cluttered images using only one exemplar. Shape based detection is invariant to changes of object appearance, and can reason with geometrical abstraction of the object. Our approach uses salient contours as integral tokens for shape matching. We seek a maximal, holistic matching of shapes, which checks shape features froma large spatial extent, as well as long-range contextual relationships among object parts. This amounts to finding the correct figure/ ground contour labeling, and optimal correspondences between control points on/around contours. This removes accidental alignments and does not hallucinate objects in background clutter, without negative training examples. We formulate this task as a set-to-set contour matching problem. Naive methods would require searching over 'exponentially' many figure/ground contour labelings. We simplify this task by encoding the shape descriptor algebraically in a linear form of contour figure/ground variables. This allows us to use the reliable optimization technique of Linear Programming. We demonstrate our approach on the challenging task of detecting bottles, swans and other objects in cluttered images. Abstract. We introduce a shape detection framework called Contour Context Selection for detecting objects in cluttered images using only one exemplar. Shape based detection is invariant to changes of object appearance, and can reason with geometrical abstraction of the object. Our approach uses salient contours as integral tokens for shape matching. We seek a maximal, holistic matching of shapes, which checks shape features from a large spatial extent, as well as long-range contextual relationships among object parts. This amounts to finding the correct figure/ground contour labeling, and optimal correspondences between control points on/around contours. This removes accidental alignments and does not hallucinate objects in background clutter, without negative training examples. We formulate this task as a set-to-set contour matching problem. Naive methods would require searching over 'exponentially' many figure/ground contour labelings. We simplify this task by encoding the shape descriptor algebraically in a linear form of contour figure/ground variables. This allows us to use the reliable optimization technique of Linear Programming. We demonstrate our approach on the challenging task of detecting bottles, swans and other objects in cluttered images.

We present an object recognition system that locates an object, identifies its parts, and segments out its contours. A key distinction of our approach is that we use long, salient, bottom-up image contours to learn object shape, and to achieve object detection with the learned shape. Most learning methods rely on one-toone matching of contours to a model. However, bottom-up image contours often fragment unpredictably. We resolve this difficulty by using many-to-one matching of image contours to a model. To learn a descriptive object shape model, we combine bottom-up contours from a few representative images. The goal is to allow most of the contours in the training images to be many-to-one matched to the model. For detection, our challenges are inferring the object contours and part locations, in addition to object location. Because the locations of object parts and matches of contours are not annotated, they appear as latent variables during training. We use the latent SVM learning formulation to discriminatively tune the many-to-one matching score using the max-margin criterion. We evaluate on the challenging ETHZ shape categories dataset and outperform all existing methods DisciplinesComputer Sciences ©2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Digital AbstractWe present an object recognition system that locates an object, identifies its parts, and segments out its contours. A key distinction of our approach is that we use long, salient, bottom-up image contours to learn object shape, and to achieve object detection with the learned shape. Most learning methods rely on one-to-one matching of contours to a model. However, bottom-up image contours often fragment unpredictably. We resolve this difficulty by using many-to-one matching of image contours to a model.To learn a descriptive object shape model, we combine bottom-up contours from a few representative images. The goal is to allow most of the contours in the training images to be many-to-one matched to the model. For detection, our challenges are inferring the object contours and part locations, in addition to object location. Because the locations of object parts and matches of contours are not annotated, they appear as latent variables during training. We use the latent SVM learning formulation to discriminatively tune the many-to-one matching score using the max-margin criterion. We evaluate on the challenging ETHZ shape categories dataset and outperform all existing methods.

We introduce a novel topological formulation for contour grouping. Our grouping criterion, called untangling cycles, exploits the inherent topological 1D structure of salient contours to extract them from the otherwise 2D image clutter. To define a measure for topological classification robust to clutter and broken edges, we use a graph formulation instead of the standard computational topology. The key insight is that a pronounced 1D contour should have a clear ordering of edgels, to which all graph edges adhere, and no long range entanglements persist. Finding the contour grouping by optimizing these topological criteria is challenging. We introduce a novel concept of circular embedding to encode this combinatorial task. Our solution leads to computing the dominant complex eigenvectors/ eigenvalues of the random walk matrix of the contour grouping graph. We demonstrate major improvements over state-of-the-art approaches on challenging real images. Disciplines

In many areas of science and engineering, the problem arises how to discover low dimensional representations of high dimensional data. Recently, a number of researchers have converged on common solutions to this problem using methods from convex optimization. In particular, many results have been obtained by constructing semidefinite programs (SDPs) with low rank solutions. While the rank of matrix variables in SDPs cannot be directly constrained, it has been observed that low rank solutions emerge naturally by computing high variance or maximal trace solutions that respect local distance constraints. In this paper, we show how to solve very large problems of this type by a matrix factorization that leads to much smaller SDPs than those previously studied. The matrix factorization is derived by expanding the solution of the original problem in terms of the bottom eigenvectors of a graph Laplacian. The smaller SDPs obtained from this matrix factorization yield very good approximations to solutions of the original problem. Moreover, these approximations can be further refined by conjugate gradient descent. We illustrate the approach on localization in large scale sensor networks, where optimizations involving tens of thousands of nodes can be solved in just a few minutes.

We address the problem of extracting the road network from large-scale range datasets. Our approach is fully automatic and does not require any inputs other than depth and intensity measurements from the range sensor. Road extraction is important because it provides contextual information for scene analysis and enables automatic content generation for geographic information systems (GIS). In addition to these two applications, road extraction is an intriguing detection problem because robust detection requires integration of local and long-range constraints. Our approach segments the data based on both edge and region properties and then extracts roads using hypothesis testing. Road extraction is formulated as a minimum cover problem