Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition

17-19 June 1997

Filter Results

Displaying Results 1 - 25 of 174
  • Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition

    Publication Year: 1997
    Request permission for reuse | PDF file iconPDF (813 KB)
    Freely Available from IEEE
  • Velocity and disparity cues for robust real-time binocular tracking

    Publication Year: 1997, Page(s):1 - 6
    Cited by:  Papers (9)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (654 KB)

    We have designed and implemented a real-time binocular tracking system which uses two independent cues commonly found in the primary functions of biological visual systems to robustly track moving targets in complex environments, without a-priori knowledge of the target shape or texture: a fast optical flow segmentation algorithm quickly locates independently moving objects for target acquisition ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An image-based visual-motion-cue for autonomous navigation

    Publication Year: 1997, Page(s):7 - 14
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (779 KB)

    This paper presents a novel time-based visual motion cue called the Hybrid Visual Threat Cue (HVTC) that provides some measure for a change in relative range as well as absolute clearances, between a 3D surface and a moving observer. It is shown that the HVTC is a linear combination of Time-To-Contact (TTC), visual looming and the Visual Threat Cue (VTC). The visual field associated with the HVTC ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time estimation of human body posture from monocular thermal images

    Publication Year: 1997, Page(s):15 - 20
    Cited by:  Papers (39)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (576 KB)

    This paper introduces a new real-time method to estimate the posture of a human from thermal images acquired by an infrared camera regardless of the back-ground and lighting conditions. Distance transformation is performed for the human body area extracted from the thresholded thermal image for the. Calculation of the center of gravity. After the orientation of the upper half of the body is obtain... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Color-based tracking of heads and other mobile objects at video frame rates

    Publication Year: 1997, Page(s):21 - 27
    Cited by:  Papers (115)  |  Patents (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1037 KB)

    We develop a simple and very fast method for object tracking based exclusively on color information in digitized video images. Running on a Silicon Graphics R4600 Indy system with an IndyCam, our algorithm is capable of simultaneously tracking objects at full frame size (640/spl times/480 pixels) and video frame rate (30 fps). Robustness with respect to occlusion is achieved via can explicit hypot... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Matching 3-D arcs

    Publication Year: 1997, Page(s):28 - 33
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (705 KB)

    We present a new algorithm for efficient matching of 3-D polygonal arcs. The algorithm is based on the decomposition of the arcs into sets of corresponding line segments with equal lengths. We derive a closed-form solution for the transformation that gives the best match between two sets of corresponding line segments (best in the sense of an L/sub 2/ norm distance measure), which enables the deve... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pictorial recognition using affine-invariant spectral signatures

    Publication Year: 1997, Page(s):34 - 39
    Cited by:  Papers (10)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (738 KB)

    This paper describes an efficient approach to pose invariant object recognition employing pictorial recognition of image patches. A complete affine invariance is achieved by a representation which is based on a new sampling configuration in the frequency domain. Employing Singular Value Decomposition (SVD), the affine transform is decomposed into slant, tilt, swing, scale and 2D translation. From ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A bootstrapping algorithm for learning linear models of object classes

    Publication Year: 1997, Page(s):40 - 46
    Cited by:  Papers (66)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (904 KB)

    Flexible models of object classes, based on linear combinations of prototypical images, are capable of matching novel images of the same class and have been shown to be a powerful tool to solve several fundamental vision tasks such as recognition, synthesis and correspondence. The key problem in creating a specific flexible model is the computation of pixelwise correspondence between the prototype... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An assessment of information criteria for motion model selection

    Publication Year: 1997, Page(s):47 - 52
    Cited by:  Papers (50)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (887 KB)

    Rigid motion imposes constraints on the motion of image points between the two images. The matched points must conform to one of several possible constraints, such as that given by the fundamental matrix or image-image homography, and it is essential to know which model to fit to the data before recovery of structure, matching or segmentation can be performed successfully This paper compares sever... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape from the light field boundary

    Publication Year: 1997, Page(s):53 - 59
    Cited by:  Papers (9)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (806 KB)

    Ray-based representations of shape have received little attention in computer vision. In this paper we show that the problem of recovering shape from silhouettes becomes considerably simplified if it is formulated as a reconstruction problem in the space of oriented rays that intersect the object. The method can be used with both calibrated and uncalibrated cameras, does not rely on point correspo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Uncalibrated 1D projective camera and 3D affine reconstruction of lines

    Publication Year: 1997, Page(s):60 - 65
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (526 KB)

    We describe a linear algorithm to recover 3D affine shape/motion from line correspondences over three views with uncalibrated affine cameras. The key idea is the introduction of a one-dimensional projective camera. This converts the 3D affine reconstruction of "lines" into 2D projective reconstruction of "points". Using the full tensorial representation of three uncalibrated 1D views, we prove tha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gradient vector flow: a new external force for snakes

    Publication Year: 1997, Page(s):66 - 71
    Cited by:  Papers (145)  |  Patents (9)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (629 KB)

    Snakes, or active contours, are used extensively in computer vision and image processing applications, particularly to locate object boundaries. Problems associated with initialization and poor convergence to concave boundaries, however, have limited their utility. This paper develops a new external force for active contours, largely solving both problems. This external force, which we call gradie... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated model acquisition from range images with view planning

    Publication Year: 1997, Page(s):72 - 77
    Cited by:  Papers (17)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (960 KB)

    We present an incremental system that builds accurate CAD models of objects from multiple range images. Using a hybrid of surface mesh and volumetric representations, the system creates a "water-tight" 3D model at each step of the modeling process, allowing reasonable models to be built from a small number of views. We also present a method that can be used to plan the next view and reduce the num... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Deterioration detection for digital film restoration

    Publication Year: 1997, Page(s):78 - 84
    Cited by:  Papers (17)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (949 KB)

    This paper presents a robust technique to detect local deteriorations of old cinematographic films. This method relies on spatio-temporal information and combines two different detectors: a morphological detector which uses spatial properties of deteriorations, and a dynamic detector based on motion estimation techniques. Our deterioration detector has been validated on several film sequences and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fully 3D active surface models with self-inflation and self-deflation forces

    Publication Year: 1997, Page(s):85 - 90
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (857 KB)

    In this paper, we propose fully 3D active surface models for image segmentation. Our models are capable of fitting a diverse range of region shapes. They have low sensitivity to initial shape and position. We design self-inflation/deflation forces, which cooperate naturally with gradient forces. They permit the active surface to travel a long distance without the aid of any external forces. They a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Resolving occlusion in augmented reality: a contour based approach without 3D reconstruction

    Publication Year: 1997, Page(s):91 - 96
    Cited by:  Papers (27)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (695 KB)

    We present a new approach for resolving occlusions in augmented reality. The main interest is that it does not require 3D reconstruction of the considered scene. Our idea is to use a contour based approach and to label each contour point as being "behind" or "in front of", depending on whether it is in front of or behind the virtual object. This labeling step only requires that the contours can be... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast binary image processing using binary decision diagrams

    Publication Year: 1997, Page(s):97 - 102
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (592 KB)

    Many classical image processing tasks can be realized as evaluations of a Boolean function over subsets of an image. For instance, the simplicity test used in 3D thinning requires examining the 26 neighbors of each voxel and computing a single Boolean function of these inputs. In this article, we show how binary decision diagrams can be used to produce automatically very efficient and compact code... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Characterization of errors in compositing panoramic images

    Publication Year: 1997, Page(s):103 - 109
    Cited by:  Papers (3)  |  Patents (7)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (699 KB)

    In this paper we describe the effect of errors in the intrinsic camera parameters on reconstructed panoramic images. A panoramic image is created by first capturing a sequence of images while rotating the camera about a vertical axis a full 360/spl deg/. The subsequent steps are projecting the original rectilinear images onto cylindrical surfaces and compositing them to form the panoramic image. O... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Determining a polyhedral shape using interreflections

    Publication Year: 1997, Page(s):110 - 115
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (539 KB)

    We discuss the uniqueness of 2-D shape recovery of a polyhedron from a single shading image. First, we analytically show that multiple convex (and concave) shape solutions usually exist for a simple polyhedron if interreflections are not considered. Then we propose a new approach to uniquely determine the concave shape solution using interreflections as a constraint. A numerical example, in which ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Removing the bias from line detection

    Publication Year: 1997, Page(s):116 - 122
    Cited by:  Papers (2)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1232 KB)

    The extraction of curvilinear structures is an important low-level operation in computer vision. Most existing operators use a simple model for the line that is to be extracted, i.e., they do not take into account the surroundings of a line. Therefore, they will estimate a wrong line position whenever a line with different lateral contrast is extracted. In contrast, the algorithm proposed in this ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • LAFTER: lips and face real time tracker

    Publication Year: 1997, Page(s):123 - 129
    Cited by:  Papers (85)  |  Patents (10)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (768 KB)

    This paper describes an active-camera real-time system for tracking, shape description, and classification of the human face and mouth using only an SGI Indy computer. The system is based on use of 2-D blob features, which are spatially-compact clusters of pixels that are similar in terms of low-level image properties. Patterns of behavior (e.g., facial expressions and head movements) can be class... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Training support vector machines: an application to face detection

    Publication Year: 1997, Page(s):130 - 136
    Cited by:  Papers (1072)  |  Patents (52)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (999 KB)

    We investigate the application of Support Vector Machines (SVMs) in computer vision. SVM is a learning technique developed by V. Vapnik and his team (AT&T Bell Labs., 1985) that can be seen as a new method for training polynomial, neural network, or Radial Basis Functions classifiers. The decision surfaces are found by solving a linearly constrained quadratic programming problem. This optimiza... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The FERET evaluation methodology for face-recognition algorithms

    Publication Year: 1997, Page(s):137 - 143
    Cited by:  Papers (169)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (748 KB)

    Two of the most critical requirements in support of producing reliable face-recognition systems are a large database of facial images and a testing procedure to evaluate systems. The Face Recognition Technology (FERET) program has addressed both issues through the FERET database of facial images and the establishment of the FERET tests. To date, 14,126 images from 1199 individuals are included in ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parametrized structure from motion for 3D adaptive feedback tracking of faces

    Publication Year: 1997, Page(s):144 - 150
    Cited by:  Papers (103)  |  Patents (27)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (858 KB)

    A real-time system is described for automatically detecting, modeling and tracking faces in 3D. A closed loop approach is proposed which utilizes structure from motion to generate a 3D model of a face and then feed back the estimated structure to constrain feature tracking in the next frame. The system initializes by using skin classification, symmetry operations, 3D warping and eigenfaces to find... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reflectance and texture of real-world surfaces

    Publication Year: 1997, Page(s):151 - 157
    Cited by:  Papers (76)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1153 KB)

    In this work, we investigate the visual appearance of real-world surfaces and the dependence of appearance on imaging conditions. We present a BRDF (bidirectional reflectance distribution function) database with reflectance measurements for over 60 different samples, each observed with over 200 different combinations of viewing and source directions. We fit the BRDF measurements to two recent mode... View full abstract»

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