Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)

15-15 June 2000

Go

Filter Results

Displaying Results 1 - 25 of 116
  • Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)

    Publication Year: 2000
    Request permission for reuse | PDF file iconPDF (660 KB)
    Freely Available from IEEE
  • Learning in Gibbsian fields: how accurate and how fast can it be?

    Publication Year: 2000, Page(s):2 - 9 vol.2
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (722 KB)

    In this article, we present a unified framework for learning Gibbs models from training images. We identify two key factors that determine the accuracy and speed of learning Gibbs models: (1). Fisher information, and (2). The accuracy of Monte Carlo estimate for partition functions. We propose three new learning algorithms under the unified framework. (I). The maximum partial likelihood estimator.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A geometric approach to blind deconvolution with application to shape from defocus

    Publication Year: 2000, Page(s):10 - 17 vol.2
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1025 KB)

    We propose a solution to the generic "bilinear calibration-estimation problem" when using a quadratic cost function and restricting to (locally) translation-invariant imaging models. We apply the solution to the problem of reconstructing the three-dimensional shape and radiance of a scene from a number of defocused images. Since the imaging process maps the continuum of three-dimensional space ont... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A general method for Errors-in-Variables problems in computer vision

    Publication Year: 2000, Page(s):18 - 25 vol.2
    Cited by:  Papers (42)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (330 KB)

    The Errors-in-Variables (EIV) model from statistics is often employed in computer vision though only rarely under this name. In an EIV model all the measurements are corrupted by noise while the a priori information is captured with a nonlinear constraint among the true (unknown) values of these measurements. To estimate the model parameters and the uncorrupted data, the constraint can be lineariz... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Transformed hidden Markov models: estimating mixture models of images and inferring spatial transformations in video sequences

    Publication Year: 2000, Page(s):26 - 33 vol.2
    Cited by:  Papers (25)  |  Patents (10)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (323 KB)

    In this paper we describe a novel generative model for video analysis called the transformed hidden Markov model (THMM). The video sequence is modeled as a set of frames generated by transforming a small number of class images that summarize the sequence. For each frame, the transformation and the class are discrete latent variables that depend on the previous class and transformation in the seque... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multimodal speaker detection using error feedback dynamic Bayesian networks

    Publication Year: 2000, Page(s):34 - 41 vol.2
    Cited by:  Papers (25)  |  Patents (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (302 KB)

    Design and development of novel human-computer interfaces poses a challenging problem: actions and intentions of users have to be inferred from sequences of noisy and ambiguous multi-sensory data such as video and sound. Temporal fusion of multiple sensors has been efficiently formulated using dynamic Bayesian networks (DBNs) which allows the power of statistical inference and learning to be combi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new algorithm for non-rigid point matching

    Publication Year: 2000, Page(s):44 - 51 vol.2
    Cited by:  Papers (66)  |  Patents (12)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1221 KB)

    We present a new robust point matching algorithm (RPM) that can jointly estimate the correspondence and non-rigid transformations between two point-sets that may be of different sizes. The algorithm utilizes the soft assign for the correspondence and the thin-plate spline for the non-rigid mapping. Embedded within a deterministic annealing framework, the algorithm can automatically reject a fracti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maximum-likelihood template matching

    Publication Year: 2000, Page(s):52 - 57 vol.2
    Cited by:  Papers (26)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (386 KB)

    In image matching applications such as tracking and stereo matching, it is common to use the sum-of-squared-differences (SSD) measure to determine the best match for an image template. However, this measure is sensitive to outliers and is not robust to template variations. We describe a robust measure and efficient search strategy for template matching with a binary or greyscale template using a m... View full abstract»

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

    Publication Year: 2000, Page(s):58 - 65 vol.2
    Cited by:  Papers (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (314 KB)

    Many visual matching algorithms can be described in terms of the features and the inter-feature distance or metric. The most commonly used metric is the sum of squared differences (SSD), which is valid from a maximum likelihood perspective when the real noise distribution is Gaussian. Based on real noise distributions measured from international test sets, we have found experimentally that the Gau... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient matching of pictorial structures

    Publication Year: 2000, Page(s):66 - 73 vol.2
    Cited by:  Papers (147)  |  Patents (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (221 KB)

    A pictorial structure is a collection of parts arranged in a deformable configuration. Each part is represented using a simple appearance model and the deformable configuration is represented by spring-like connections between pairs of parts. While pictorial structures were introduced a number of years ago, they have not been broadly applied to matching and recognition problems. This has been due ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Handwritten digit recognition with a novel vision model that extracts linearly separable features

    Publication Year: 2000, Page(s):76 - 81 vol.2
    Cited by:  Papers (1)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (99 KB)

    We use well-established results in biological vision to construct a novel vision model for handwritten digit recognition. We show empirically that the features extracted by our model are linearly separable over a large training set (MNIST). Using only a linear classifier on these features, our model is relatively simple yet outperforms other models on the same data set. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Active character recognition using "A*-like" algorithm

    Publication Year: 2000, Page(s):82 - 87 vol.2
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (142 KB)

    This paper describes an Active Character Recognition methodology, henceforth referred to as ACR. We present in this paper a method that uses an active heuristic function similar to the one used by A* search algorithm that adaptively determines the length of the feature vector as well as the features themselves used to classify an input pattern. ACR adapts to factors such as the quality of the inpu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • View-independent recognition of hand postures

    Publication Year: 2000, Page(s):88 - 94 vol.2
    Cited by:  Papers (40)  |  Patents (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (506 KB)

    Since the human hand is highly articulated and deformable, hand posture recognition is a challenging example in the research on view-independent object recognition. Due to the difficulties of the model-based approach, the appearance-based learning approach is promising to handle large variation in visual inputs. However, the generalization of many proposed supervised learning methods to this probl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computing 3D object parts from similarities among object views

    Publication Year: 2000, Page(s):95 - 100 vol.2
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (225 KB)

    The following shape segmentation problem is addressed: find the part decomposition of a 3D object that accounts for an observed pattern of similarities among several of the object's views. This represents the inverse, ill-posed version of the direct problem of computing perceptual similarities among object views when the object parts are known. The problem is solved by inverting a proposed model f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards automatic discovery of object categories

    Publication Year: 2000, Page(s):101 - 108 vol.2
    Cited by:  Papers (96)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (2099 KB)

    We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Our models represent objects as probabilistic constellations of rigid parts (features). The variability within a class is represented by a join probability density function on the shape of the constellation and the appearan... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simultaneous tracking and verification via sequential posterior estimation

    Publication Year: 2000, Page(s):110 - 117 vol.2
    Cited by:  Papers (10)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (585 KB)

    An approach to simultaneous tracking and verification in video data is presented. The approach is based on posterior estimation using sequential Monte Carlo methods. Visual tracking, which is in essence a temporal correspondence problem, is solved through probability density propagation, with the density being defined over a proper state space characterizing the object configuration. Verification ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tracking segmented objects using tensor voting

    Publication Year: 2000, Page(s):118 - 125 vol.2
    Cited by:  Papers (16)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (422 KB)

    The paper presents a new approach to track objects in motion when observed by a fixed camera, with severe occlusions, merging/splitting objects and defects in the detection. We first detect regions corresponding to moving objects in each frame, then try to establish their trajectory. We propose to implement the temporal continuity constraint efficiently, and apply it to tracking problems in realis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Articulated body motion capture by annealed particle filtering

    Publication Year: 2000, Page(s):126 - 133 vol.2
    Cited by:  Papers (430)  |  Patents (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1468 KB)

    The main challenge in articulated body motion tracking is the large number of degrees of freedom (around 30) to be recovered. Search algorithms, either deterministic or stochastic, that search such a space without constraint, fall foul of exponential computational complexity. One approach is to introduce constraints: either labelling using markers or colour coding, prior assumptions about motion t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic layer representation with applications to tracking

    Publication Year: 2000, Page(s):134 - 141 vol.2
    Cited by:  Papers (21)  |  Patents (11)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (257 KB)

    A dynamic layer representation is proposed for tracking moving objects. Previous work on layered representations has largely concentrated on two-/multi-frame batch formulations, and tracking research has not addressed the issue of joint estimation of object motion ownership and appearance. The paper extends the estimation of layers in a dynamic scene to incremental estimation formulation and demon... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time tracking of non-rigid objects using mean shift

    Publication Year: 2000, Page(s):142 - 149 vol.2
    Cited by:  Papers (1352)  |  Patents (63)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (542 KB)

    A new method for real time tracking of non-rigid objects seen from a moving camera is proposed. The central computational module is based on the mean shift iterations and finds the most probable target position in the current frame. The dissimilarity between the target model (its color distribution) and the target candidates is expressed by a metric derived from the Bhattacharyya coefficient. The ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation and prediction of evolving color distributions for skin segmentation under varying illumination

    Publication Year: 2000, Page(s):152 - 159 vol.2
    Cited by:  Papers (53)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (2005 KB)

    A model approach for real time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and based on predic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scene modeling for wide area surveillance and image synthesis

    Publication Year: 2000, Page(s):160 - 167 vol.2
    Cited by:  Papers (55)  |  Patents (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (502 KB)

    We present a method for modeling a scene that is observed by a moving camera, where only a portion of the scene is visible at any time. This method uses mixture models to represent pixels in a panoramic view, and to construct a "background image" that contains only static (non-moving) parts of the scene. The method can be used to reliably detect moving objects in a video sequence, detect patterns ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting and tracking human face and eye using an space-varying sensor and an active vision head

    Publication Year: 2000, Page(s):168 - 173 vol.2
    Cited by:  Papers (8)  |  Patents (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (993 KB)

    We have developed a system for detecting and tracking human face and eye in an unstructured environment. We adopt a biologically plausible retinally connected neural network architecture and integrate it with an active vision system. While the active vision system tracks the object moving in real time, the neural network detects the face and eye location from the video stream at a slower rate. The... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Video summarization using singular value decomposition

    Publication Year: 2000, Page(s):174 - 180 vol.2
    Cited by:  Papers (25)  |  Patents (20)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (345 KB)

    The authors propose a novel technique for video summarization based on singular value decomposition (SVD). For the input video sequence, we create a feature-frame matrix A, and perform the SVD on it. From this SVD, we are able, to not only derive the refined feature space to better cluster visually similar frames, but also define a metric to measure the amount of visual content contained in each f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An effective approach to detect lesions in color retinal images

    Publication Year: 2000, Page(s):181 - 186 vol.2
    Cited by:  Papers (24)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (181 KB)

    Diabetic-related eye diseases are the most common cause of blindness in the world. So far the most effective treatment for these eye diseases is early detection through regular screening. To lower the cost of such screenings, we employ state-of-the-art image processing techniques to automatically detect the presence of abnormalities in the retinal images obtained during the screenings. The authors... View full abstract»

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