By Topic

2007 IEEE 11th International Conference on Computer Vision

14-21 Oct. 2007

Filter Results

Displaying Results 1 - 25 of 400
  • Table of contents

    Publication Year: 2007, Page(s): nil1
    Request permission for commercial reuse | PDF file iconPDF (33 KB)
    Freely Available from IEEE
  • ICCV Program

    Publication Year: 2007, Page(s):nil2 - nil19
    Request permission for commercial reuse | PDF file iconPDF (660 KB)
    Freely Available from IEEE
  • Workshop on Interactive Computer Vision (ICV 2007)

    Publication Year: 2007, Page(s):nil20 - nil21
    Request permission for commercial reuse | PDF file iconPDF (39 KB)
    Freely Available from IEEE
  • Mathematical Methods in Biomedical Image Analysis (MMBIA 2007)

    Publication Year: 2007, Page(s):nil22 - nil26
    Request permission for commercial reuse | PDF file iconPDF (148 KB)
    Freely Available from IEEE
  • Workshop on Non-rigid Registration and Tracking through Learning - NRTL 2007

    Publication Year: 2007, Page(s):nil27 - nil28
    Request permission for commercial reuse | PDF file iconPDF (46 KB)
    Freely Available from IEEE
  • OMNIVIS 2007 Program

    Publication Year: 2007, Page(s):nil29 - nil30
    Request permission for commercial reuse | PDF file iconPDF (61 KB)
    Freely Available from IEEE
  • Virtual Representations and Modeling of Large-scale environments (VRML)

    Publication Year: 2007, Page(s): nil31
    Request permission for commercial reuse | PDF file iconPDF (27 KB)
    Freely Available from IEEE
  • Workshop On Dymanical Vision ICCV 2007

    Publication Year: 2007, Page(s):nil32 - nil33
    Request permission for commercial reuse | PDF file iconPDF (51 KB)
    Freely Available from IEEE
  • Learning 3-D Scene Structure from a Single Still Image

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (44)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2029 KB) | HTML iconHTML

    We consider the problem of estimating detailed 3D structure from a single still image of an unstructured environment. Our goal is to create 3D models which are both quantitatively accurate as well as visually pleasing. For each small homogeneous patch in the image, we use a Markov random field (MRF) to infer a set of "plane parameters" that capture both the 3D location and 3D orientation of the pa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D object recognition from range images using pyramid matching

    Publication Year: 2007, Page(s):1 - 6
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (8122 KB) | HTML iconHTML

    Recognition of 3D objects from different viewpoints is a difficult problem. In this paper, we propose a new method to recognize 3D range images by matching local surface descriptors. The input 3D surfaces are first converted into a set of local shape descriptors computed on surface patches defined by detected salient features. We compute the similarities between input 3D images by matching their d... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Variable Dimensional Local Shape Descriptors for Object Recognition in Range Data

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (7973 KB) | HTML iconHTML

    We propose a new set of highly descriptive local shape descriptors (LSDs) for model-based object recognition and pose determination in input range data. Object recognition is performed in three phases: point matching, where point correspondences are established between range data and the complete model using local shape descriptors; pose recovery, where a computationally robust algorithm generates... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Depth-From-Recognition: Inferring Meta-data by Cognitive Feedback

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (871 KB) | HTML iconHTML

    Thanks to recent progress in category-level object recognition, we have now come to a point where these techniques have gained sufficient maturity and accuracy to succesfully feed back their output to other processes. This is what we refer to as cognitive feedback. In this paper, we study one particular form of cognitive feedback, where the ability to recognize objects of a given category is explo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting and Localizing 3D Object Classes using Viewpoint Invariant Reference Frames

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1187 KB) | HTML iconHTML

    In this paper, we investigate detection and localization of general 3D object classes by relating local scale-invariant features to a viewpoint invariant reference frame. This can generally be achieved by either a multi-view representation, where features and reference frame are modeled as a collection of distinct views, or by a viewpoint invariant representation, where features and reference fram... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Articulated Shape Matching by Robust Alignment of Embedded Representations

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1191 KB) | HTML iconHTML

    In this paper we propose a general framework to solve the articulated shape matching problem, formulated as finding point-to-point correspondences between two shapes represented by 2-D or 3-D point clouds. The original point- sets are embedded in a spectral representation and the actual matching is carried out in the embedded space. We analyze the advantages of this choice as well as the reasons f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A 3D Teacher for Car Detection in Aerial Images

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (462 KB) | HTML iconHTML

    This paper demonstrates how to reduce the hand labeling effort considerably by 3D information in an object detection task. In particular, we demonstrate how an efficient car detector for aerial images with minimal hand labeling effort can be build. We use an on-line boosting algorithm to incrementally improve the detection results. Initially, we train the classifier with a single positive (car) ex... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D Object Representation Using Transform and Scale Invariant 3D Features

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1655 KB) | HTML iconHTML

    An algorithm is proposed for 3D object representation using generic 3D features which are transformation and scale invariant. Descriptive 3D features and their relations are used to construct a graphical model for the object which is later trained and then used for detection purposes. Descriptive 3D features are the fundamental structures which are extracted from the surface of the 3D scanner outp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Scene Representation Based on Multi-Modal 2D and 3D Features

    Publication Year: 2007, Page(s):1 - 7
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (6917 KB) | HTML iconHTML

    Visually extracted 2D and 3D information have their own advantages and disadvantages that complement each other. Therefore, it is important to be able to switch between the different dimensions according to the requirements of the problem and use them together to combine the reliability of 2D information with the richness of 3D information. In this article, we use 2D and 3D information in a featur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Perspectively Invariant Normal Features

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (17)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3273 KB) | HTML iconHTML

    We extend the successful 2D robust feature concept into the third dimension in that we produce a descriptor for a reconstructed 3D surface region. The descriptor is perspectively invariant if the region can locally be approximated well by a plane. We exploit depth and texture information, which is nowadays available in real-time from video of moving cameras, from stereo systems or PMD cameras (pho... View full abstract»

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

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (21)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1004 KB) | HTML iconHTML

    As a fundamental problem in pattern recognition, graph matching has found a variety of applications in the field of computer vision. In graph matching, patterns are modeled as graphs and pattern recognition amounts to finding a correspondence between the nodes of different graphs. There are many ways in which the problem has been formulated, but most can be cast in general as a quadratic assignmen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (133)  |  Patents (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (446 KB) | HTML iconHTML

    We address the problem of visual category recognition by learning an image-to-image distance function that attempts to satisfy the following property: the distance between images from the same category should be less than the distance between images from different categories. We use patch-based feature vectors common in object recognition work as a basis for our image-to-image distance functions. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Boosting Invariance and Efficiency in Supervised Learning

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1322 KB) | HTML iconHTML

    In this paper we present a novel boosting algorithm for supervised learning that incorporates invariance to data transformations and has high generalization capabilities. While one can incorporate invariance by adding virtual samples to the data (e.g., by jittering), we adopt a much more efficient strategy and work along the lines of vicinal risk minimization and tangent distance methods. As in vi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning to Find Object Boundaries Using Motion Cues

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (30)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2252 KB) | HTML iconHTML

    While great strides have been made in detecting and localizing specific objects in natural images, the bottom-up segmentation of unknown, generic objects remains a difficult challenge. We believe that occlusion can provide a strong cue for object segmentation and "pop-out", but detecting an object's occlusion boundaries using appearance alone is a difficult problem in itself. If the camera or the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • COST: An Approach for Camera Selection and Multi-Object Inference Ordering in Dynamic Scenes

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (572 KB) | HTML iconHTML

    Development of multiple camera based vision systems for analysis of dynamic objects such as humans is challenging due to occlusions and similarity in the appearance of a person with the background and other people- visual "confusion". Since occlusion and confusion depends on the presence of other people in the scene, it leads to a dependency structure where there are often loops in the resulting B... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning priors for calibrating families of stereo cameras

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (3)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1513 KB) | HTML iconHTML

    Online camera recalibration is necessary for long-term deployment of computer vision systems. Existing algorithms assume that the source of recalibration information is a set of features in a general 3D scene; and that enough features are observed that the calibration problem is well-constrained. However; these assumptions are frequently invalid outside the laboratory. Real-world scenes often lack... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Active Learning with Gaussian Processes for Object Categorization

    Publication Year: 2007, Page(s):1 - 8
    Cited by:  Papers (74)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2780 KB) | HTML iconHTML

    Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gaussian Processes (GPs) are powerful regression techniques with explicit uncertainty models; we show here how Gaussian Processes with covariance functions defined based on a Pyramid Match Kernel (PMK) can be used for probabil... View full abstract»

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