By Topic

Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1

17-21 Oct. 2005

Go

Filter Results

Displaying Results 1 - 25 of 125
  • Efficiently solving dynamic Markov random fields using graph cuts

    Publication Year: 2005, Page(s):922 - 929 Vol. 2
    Cited by:  Papers (68)  |  Patents (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (363 KB) | HTML iconHTML

    In this paper, we present a fast new fully dynamic algorithm for the st-mincut/max-flow problem. We show how this algorithm can be used to efficiently compute MAP estimates for dynamically changing MRF models of labeling problems in computer vision, such as image segmentation. Specifically, given the solution of the max-flow problem on a graph, we show how to efficiently compute the maximum flow i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A shape-based segmentation approach: an improved technique using level sets

    Publication Year: 2005, Page(s):930 - 935 Vol. 2
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (892 KB) | HTML iconHTML

    We propose a novel approach for shape-based segmentation based on a specially designed level set function format. This format permits us to better control the process of object registration which is an important part in the shape-based segmentation framework. The method depends on a set of training shapes used to build a parametric shape model. The color is taken into consideration besides the sha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An iterative optimization approach for unified image segmentation and matting

    Publication Year: 2005, Page(s):936 - 943 Vol. 2
    Cited by:  Papers (116)  |  Patents (21)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1203 KB) | HTML iconHTML

    Separating a foreground object from the background in a static image involves determining both full and partial pixel coverages, also known as extracting a matte. Previous approaches require the input image to be presegmented into three regions: foreground, background and unknown, which are called a trimap. Partial opacity values are then computed only for pixels inside the unknown region. This pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Convex grouping combining boundary and region information

    Publication Year: 2005, Page(s):946 - 953 Vol. 2
    Cited by:  Papers (8)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2434 KB) | HTML iconHTML

    Convexity is an important geometric property of many natural and man-made structures. Prior research has shown that it is imperative to many perceptual-organization and image-understanding tasks. This paper presents a new grouping method for detecting convex structures from noisy images in a globally optimal fashion. Particularly, this method combines both region and boundary information: the dete... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting rotational symmetries

    Publication Year: 2005, Page(s):954 - 961 Vol. 2
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (688 KB) | HTML iconHTML

    We present an algorithm for detecting multiple rotational symmetries in natural images. Given an image, its gradient magnitude field is computed, and information from the gradients is spread using a diffusion process in the form of a gradient vector flow (GVF) field. We construct a graph whose nodes correspond to pixels in tire image, connecting points that are likely to be rotated versions of one... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning nongenerative grammatical models for document analysis

    Publication Year: 2005, Page(s):962 - 969 Vol. 2
    Cited by:  Papers (8)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (317 KB) | HTML iconHTML

    We present a general approach for the hierarchical segmentation and labeling of document layout structures. This approach models document layout as a grammar and performs a global search for the optimal parse based on a grammatical cost function. Our contribution is to utilize machine learning to discriminatively select features and set all parameters in the parsing process. Therefore, and unlike ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Phase field models and higher-order active contours

    Publication Year: 2005, Page(s):970 - 976 Vol. 2
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (340 KB) | HTML iconHTML

    The representation and modelling of regions is an important topic in computer vision. In this paper, we represent a region via a level set of a 'phase field' function. The function is not constrained, e.g. to be a distance function; nevertheless, phase field energies equivalent to classical active contour energies can be defined. They represent an advantageous alternative to other methods: a linea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Globally optimal estimates for geometric reconstruction problems

    Publication Year: 2005, Page(s):978 - 985 Vol. 2
    Cited by:  Papers (21)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (475 KB) | HTML iconHTML

    We introduce a framework for computing statistically optimal estimates of geometric reconstruction problems. While traditional algorithms often suffer from either local minima or nonoptimality - or a combination of both - we pursue the goal of achieving global solutions of the statistically optimal cost-function. Our approach is based on a hierarchy of convex relaxations to solve nonconvex optimiz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Quasiconvex optimization for robust geometric reconstruction

    Publication Year: 2005, Page(s):986 - 993 Vol. 2
    Cited by:  Papers (38)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (284 KB) | HTML iconHTML

    Geometric reconstruction problems in computer vision are often solved by minimizing a cost function that combines the reprojection errors in the 2D images. In this paper, we show that, for various geometric reconstruction problems, their reprojection error functions share a common and quasiconvex formulation. Based on the quasiconvexity, we present a novel quasiconvex optimization framework in whi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shapelets correlated with surface normals produce surfaces

    Publication Year: 2005, Page(s):994 - 1001 Vol. 2
    Cited by:  Papers (49)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2061 KB) | HTML iconHTML

    This paper addresses the problem of deducing the surface shape of an object given just the surface normals. Many shape measurement algorithms such as shape from shading and shape from texture only return the surface normals of an object, often with an ambiguity of pi in the surface tilt. The surface shape has to be inferred from these normals, typically via some integration process. However; recon... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple view geometry and the L-norm

    Publication Year: 2005, Page(s):1002 - 1009 Vol. 2
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (456 KB) | HTML iconHTML

    This paper presents a new framework for solving geometric structure and motion problems based on L-norm. Instead of using the common sum-of-squares cost-function, that is, the L-norm, the model-fitting errors are measured using the L-norm. Unlike traditional methods based on L2 our framework allows for efficient computation of global... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object detection in aerial imagery based on enhanced semi-supervised learning

    Publication Year: 2005, Page(s):1012 - 1017 Vol. 2
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (167 KB) | HTML iconHTML

    Object detection in aerial imagery has been well studied in computer vision for years. However, given the complexity of large variations of the appearance of the object and the background in a typical aerial image, a robust and efficient detection is still considered as an open and challenging problem. In this paper, we present the enhanced semi-supervised learning (ESL) framework and apply this f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new framework for approximate labeling via graph cuts

    Publication Year: 2005, Page(s):1018 - 1025 Vol. 2
    Cited by:  Papers (19)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (289 KB) | HTML iconHTML

    A new framework is presented that uses tools from duality theory of linear programming to derive graph-cut based combinatorial algorithms for approximating NP-hard classification problems. The derived algorithms include alpha-expansion graph cut techniques merely as a special case, have guaranteed optimality properties even in cases where alpha-expansion techniques fail to do so and can provide ve... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Okapi-Chamfer matching for articulate object recognition

    Publication Year: 2005, Page(s):1026 - 1033 Vol. 2
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (593 KB) | HTML iconHTML

    Recent years have witnessed the rise of many effective text information retrieval systems. By treating local visual features as terms, training images as documents and input images as queries, we formulate the problem of object recognition into that of text retrieval. Our formulation opens up the opportunity to integrate some powerful text retrieval tools with computer vision techniques. In this p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Background estimation as a labeling problem

    Publication Year: 2005, Page(s):1034 - 1041 Vol. 2
    Cited by:  Papers (15)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2367 KB) | HTML iconHTML

    We present a new background estimation algorithm that constructs the background of an image sequence with moving objects by copying areas from input frames. The background estimation problem is formulated as an optimal labeling problem in which the label at an output pixel is the frame number from which to copy the background color. The costs of assigning labels encourage seamless copying from reg... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian structural content abstraction for region-level image authentication

    Publication Year: 2005, Page(s):1042 - 1047 Vol. 2
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (533 KB) | HTML iconHTML

    We present a hierarchical representation of image structure and use it for image content authentication. Firstly, we model the image with the Markov pixon random field. Within the Bayesian framework, the optimal label map and regional pixon map can be obtained, based on which we define an undirected graph, namely Bayesian structural content abstraction (BaSCA). This representation captures the spa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A graph cut algorithm for generalized image deconvolution

    Publication Year: 2005, Page(s):1048 - 1054 Vol. 2
    Cited by:  Papers (24)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (382 KB) | HTML iconHTML

    The goal of deconvolution is to recover an image x from its convolution with a known blurring function. This is equivalent to inverting the linear system y = Hx. In this paper, we consider the generalized problem where the system matrix H is an arbitrary nonnegative matrix. Linear inverse problems can be solved by adding a regularization term to impose spatial smoothness. To avoid oversmoothing, t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reconstructing the geometry of flowing water

    Publication Year: 2005, Page(s):1055 - 1060 Vol. 2
    Cited by:  Papers (14)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (463 KB) | HTML iconHTML

    We present a recording scheme, image formation model and reconstruction method that enables image-based modeling of flowing bodies of water from multivideo input data. The recorded water is dyed with a fluorescent chemical to measure the thickness of a column of water which leads to an image formation model based on integrated emissivities along a viewing ray. This model allows for a photo-consist... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Surface parameterization using Riemann surface structure

    Publication Year: 2005, Page(s):1061 - 1066 Vol. 2
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (403 KB) | HTML iconHTML

    We propose a general method that parameterizes general surfaces with complex (possible branching) topology using Riemann surface structure. Rather than evolve the surface geometry to a plane or sphere, we instead use the fact that all orientable surfaces are Riemann surfaces and admit conformal structures, which induce special curvilinear coordinate systems on the surfaces. We can then automatical... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • When does a camera see rain?

    Publication Year: 2005, Page(s):1067 - 1074 Vol. 2
    Cited by:  Papers (34)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (435 KB) | HTML iconHTML

    Rain produces sharp intensity fluctuations in images and videos, which degrade the performance of outdoor vision systems. These intensity fluctuations depend on various factors, such as the camera parameters, the properties of rain, and the brightness of the scene. We show that the properties of rain - its small drop size, high velocity, and low density - make its visibility strongly dependent on ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Uncalibrated perspective reconstruction of deformable structures

    Publication Year: 2005, Page(s):1075 - 1082 Vol. 2
    Cited by:  Papers (17)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (282 KB) | HTML iconHTML

    Reconstruction of 3D structures from uncalibrated image sequences has a wealthy history. Most work has been focused on rigid objects or static scenes. This paper studies the problem of perspective reconstruction of deformable structures such as dynamic scenes from an uncalibrated image sequence. The task requires decomposing the image measurements into a composition of three factors: 3D deformable... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fitting globally stabilized algebraic surfaces to range data

    Publication Year: 2005, Page(s):1083 - 1088 Vol. 2
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (682 KB) | HTML iconHTML

    Linear fitting of implicit algebraic models to data usually suffers from global stability problems. Complicated object structures can accurately be modeled by closed-bounded surfaces of higher degrees using ridge regression. This paper derives an explicit formula for computing a Euclidean invariant 3D ridge regression matrix and applies it for the global stabilization of a particular linear fittin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Lighting normalization with generic intrinsic illumination subspace for face recognition

    Publication Year: 2005, Page(s):1089 - 1096 Vol. 2
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (387 KB) | HTML iconHTML

    In this paper, we introduce the concept of intrinsic illumination subspace which is based on the intrinsic images. This intrinsic illumination subspace enables an analytic generation of the illumination images under varying lighting conditions. When objects of the same class are concerned, our method allows a class-based generic intrinsic illumination subspace to be constructed in advance. We prop... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Layered active appearance models

    Publication Year: 2005, Page(s):1097 - 1102 Vol. 2
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (517 KB) | HTML iconHTML

    Active appearance models (AAMs) provide a framework for modeling the joint shape and texture of an image. An AAM is a compact representation of both factors in a conditionally linear model. However, the standard AAM framework does not handle images which have missing features, or allow modification of certain structures in the image while leaving neighboring ones undeformed. We introduce the layer... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identifying individuals in video by combining 'generative' and discriminative head models

    Publication Year: 2005, Page(s):1103 - 1110 Vol. 2
    Cited by:  Papers (12)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1287 KB) | HTML iconHTML

    The objective of this work is automatic detection and identification of individuals in unconstrained consumer video, given a minimal number of labelled faces as training data. Whilst much work has been done on (mainly frontal) face detection and recognition, current methods are not sufficiently robust to deal with the wide variations in pose and appearance found in such video. These include variat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.