This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by userspecified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications.

This paper presents a nonparametric approach to labeling of local image regions that is inspired by recent developments in information-theoretic denoising. The chief novelty of this approach rests in its ability to derive an unsupervised contextual prior over image classes from unlabeled test data. Labeled training data is needed only to learn a local appearance model for image patches (although additional supervisory information can optionally be incorporated when it is available). Instead of assuming a parametric prior such as a Markov random field for the class labels, the proposed approach uses the empirical Bayes technique of statistical inversion to recover a contextual model directly from the test data, either as a spatially varying or as a globally constant prior distribution over the classes in the image. Results on two challenging datasets convincingly demonstrate that useful contextual information can indeed be learned from unlabeled data. 1.

Abstract—Reconstruction of 3D scene geometry is an important element for scene understanding, autonomous vehicle and robot navigation, visual inspection and 3D television. We propose accounting for the inherent structure of the visual world when trying to solve the scene reconstruction problem. Consequently, we identify scene categorization as the first step towards robust and efficient depth estimation from single images. We introduce 15 typical 3D scene geometries called stages, each with a unique depth profile, which roughly correspond to a large majority of all images. Stage information serves as the first approximation of global depth, narrowing down the search space in depth estimation and object localization. We propose different sets of low-level features for depth estimation, and perform stage classification on two diverse datasets of television broadcasts. Classification results demonstrate that stages can be efficiently learned from low-dimensional image representations. Index Terms—scene geometry, scene structure, depth estimation, scene categorization, stages 1

In this paper, we address two closely related visual tracking problems: 1) localizing a target’s position in low or moderate resolution videos and 2) segmenting a target’s image support in moderate to high resolution videos. Both tasks are treated as an online binary classification problem using dynamic foreground/background appearance models. Our major contribution is a novel nonparametric approach that successfully maintains a temporally changing appearance model for both foreground and background. The appearance models are formulated as “bags of image patches ” that approximate the true two-class appearance distributions. They are maintained using a temporaladaptive importance resampling procedure that is based on simple nonparametric statistics of the appearance patch bags. The overall framework is independent of an specific foreground/background classification process and thus offers the freedom to use different classifiers. We demonstrate the effectiveness of our approach with extensive comparative experimental results on sequences from previous visual tracking [1, 12] and video matting [4] work as well as our own data. 1.

We identify scene categorization as the first step towards efficient and robust depth estimation from single images. Categorizing the scene into one of the geometric classes greatly reduces the possibilities in subsequent phases. To that end, we introduce 15 typical 3D scene geometries, called stages, each having a unique depth profile and roughly corresponding to a large majority of all images. In this work, we do not attempt to derive a precise depth map, but only to decide on the appropriate stage. The subsequent phase of parameter estimation would result in a more detailed background depth profile. Index Terms — Depth estimation, 2D to 3D conversion, scene geometry, scene classification, surface layout, stages 1.

Abstract—For scenery character detection, we introduce environmental context, which is modeled by scene components, such as sky and building. Environmental context is expected to regulate the probability of character existence at a specific region in a scenery image. For example, if a region looks like a part of a building, the region has a higher probability than another region like a part of the sky. In this paper, environmental context is represented by state-of-the-art texture and color features and utilized in two different ways. Through experimental results, it was clearly shown that the environmental context has an effect of improving detection accuracy. Keywords-scenery character detection, environmental context, feature, random forest I.

Abstract—This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by userspecified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications. 1