By Topic

Computer Vision and Pattern Recognition, 1988. Proceedings CVPR '88., Computer Society Conference on

5-9 June 1988

Filter Results

Displaying Results 1 - 25 of 142
  • Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.88CH2605-4)

    Publication Year: 1988
    Request permission for commercial reuse | PDF file iconPDF (25 KB)
    Freely Available from IEEE
  • The inverse perspective problem from a single view for polyhedra location

    Publication Year: 1988, Page(s):61 - 66
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (463 KB)

    A method to find the analytical solutions of the inverse perspective problem for the determination of the 3-D object attitude in space from a single perspective image is presented. Its principle is based on the interpretation of a triplet of any image lines as the perspective projection of triplet of linear ridges of the object model. The geometrical transformations to apply to the model to bring ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Structural pyramids for representing and locating moving obstacles in visual guidance of navigation

    Publication Year: 1988, Page(s):832 - 837
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    The author presents an image pyramidal approach for representing and locating moving obstacles in the visual guidance of navigation for mobile robots or autonomous land vehicles. The algorithm is based on the utilization of a structural representation of the image in pyramids. A thresholding and mapping scheme for generating the structural pyramids is described. Obstacles are represented and locat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An expert vision system for autonomous land vehicle road following

    Publication Year: 1988, Page(s):826 - 831
    Cited by:  Papers (2)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (532 KB)

    A production-system model of problem solving is applied to the design of a vision system by which an autonomous land vehicle (ALV) navigates roads. The ALV vision task consists of hypothesizing objects in a scene model and verifying these hypotheses using the vehicles sensors. Object hypothesis generation is based on the local navigation task, and a priori road map, and the contents of the scene m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An integrated approach to feature based dynamic vision

    Publication Year: 1988, Page(s):820 - 825
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (488 KB)

    A novel method for dynamic scene analysis by computer vision is described that combines 3-D shape models, dynamical models as known from modern control theory and the laws of perspective projection. To arrive at numerically efficient real-time algorithms, the recursive state estimation by Kalman filtering is adapted to a feature-based image sequence analysis scheme. The spatial and temporal constr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spline-based surface fitting on range images for CAD applications

    Publication Year: 1988, Page(s):249 - 253
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (312 KB)

    The authors present an approach for integration of manually designed parts in CAD databases. They propose a system to derive spline-based descriptions of various component surfaces of objects given only the range image of the object under consideration. The system consists of two modules. The first module, which is centred on a robust segmentation algorithm, generates a segmentation plot of the gi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Graph-based vectorization method for line patterns

    Publication Year: 1988, Page(s):616 - 621
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (472 KB)

    A vectorization method for line patterns is proposed which converts digital binary images into line segment vectors. The vector data is more compact and more natural than that obtained by conventional methods using thinning operations. The proposed method consisted of four steps. First, thinning of an input binary image is performed. Then a medical line image obtained by the thinning operation is ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Road finding for road-network extraction

    Publication Year: 1988, Page(s):814 - 819
    Cited by:  Papers (4)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (712 KB)

    Automatic extraction of roads from aerial photos has been demonstrated in a number of systems, but the systems which display the better capabilities usually rely on manual selection of road starting points. This interaction with a human operator is eliminated by integrating a road-finding module into a road network extraction system. The road finder combines a greedy, edge-based, road-center linke... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Region grouping from a range image

    Publication Year: 1988, Page(s):241 - 248
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (580 KB)

    A novel method is presented for grouping range image regions such that each group of regions represents a meaningful part of an object. The set of regions, defined as a convex region set (CRS), is obtained by analyzing the boundary types between a pair of regions. The boundary types are classified as convex, concave and jump boundaries. If two regions share a convex boundary it is assumed that the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detecting motion in out-of-register pictures

    Publication Year: 1988, Page(s):696 - 701
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (656 KB)

    A novel technique is described that can be applied to a sequence of pictures to detect moving objects and segment them from the stationary background. It does not require the pictures to be in-register, and is suitable for cases where the camera moves while the pictures are taken. Its greatest advantage is the simplicity and efficiency in which it can be implemented. By the use of fast Fourier tra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Polynomial shift-invariant operators for texture segmentation

    Publication Year: 1988, Page(s):100 - 104
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (356 KB)

    Marking boundaries in an image between regions that are differently textured depends on computing descriptions of the regions that show them to be differently textured. Many texture description functions have been introduced in the literature; however, the texture description problem has never been treated in full generality. The author proposed shift-invariant vector-valued piecewise continuous f... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the number of digital straight lines on an N×N grid

    Publication Year: 1988, Page(s):610 - 615
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (264 KB)

    The number of different digital straight lines on an N×N square pixel array is studied. The problem is equivalent to finding the number of linear dichotomies of a planar set of N2 points of an N×N grid. For any planar set of points, adjacent pairs are defined to be pairs of points from the set such that no other point from the set... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A collision-free navigation scheme in the presence of moving obstacles

    Publication Year: 1988, Page(s):808 - 813
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (224 KB)

    A collision-free navigation scheme for an autonomous vehicle is presented. An attempt is made toward establishing a more realistic navigational environment by considering moving obstacles with unknown trajectories. A collision-free path between the current location and a desired location of the vehicle is obtained, based on future positions of the obstacles. The future positions are predicted usin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An analysis of feature detectability from curvature estimation

    Publication Year: 1988, Page(s):235 - 240
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (428 KB)

    A common approach to finding features in digitized lines is to estimate the curvature along the lines and determine the features from the curvature plot. The authors compare two approaches to curvature estimation by analyzing performance with respect to signal-to-noise ratio and signal localization of corner features. One approach, curvature estimation by difference of slopes, is analyzed to deter... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A tree search algorithm for target detection in image sequences

    Publication Year: 1988, Page(s):690 - 695
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (692 KB)

    Given a time sequence of digital images of a high-noise environment, the authors address the problem of detecting pixel-sized, barely discernible moving objects whose position and trajectories are unknown. The sequences may be temporally sparse and contain significant frame-to-frame drifting background clutter as caused by relative motion between the sensor array and natural terrain, ocean, or clo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Qualitative depth from vertical and horizontal binocular disparities, in agreement with psychophysical evidence

    Publication Year: 1988, Page(s):159 - 164
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (456 KB)

    The author concentrates on the problem of obtaining depth information from binocular disparities. It is motivated by the fact that implementing registration algorithms and using the results for depth computations is hard in practice with real images due to noise and quantization errors. It is shown that qualitative depth information can be obtained from stereo disparities with almost no computatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture segmentation using Voronoi polygons

    Publication Year: 1988, Page(s):94 - 99
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (576 KB)

    The authors have developed a texture-segmentation algorithm based on the Voronoi tessellation. The algorithm first builds the Voronoi tessellation of the tokens that make up the image. It then computes a set of features from the Voronoi polygons. Finally, it performs a probabilistic relaxation labeling on the tokens, to identify the interior and the border regions of the textures. The algorithm ha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluation of quantization error in computer vision

    Publication Year: 1988, Page(s):52 - 60
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (616 KB)

    The authors develop the mathematical tools for the computation of the average error due to quantization. They can be used in estimating the actual error occurring in the implementation of a method. Also derived is the analytic expression for the probability density of error distribution of a function of an arbitrarily large number of independently quantized variables. The probability of the error ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated fast recognition and location of arbitrarily shaped objects by image morphology

    Publication Year: 1988, Page(s):774 - 779
    Cited by:  Papers (9)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB)

    Morphological operations are used for segmentation, feature generation and location extraction. A recursive adaptive thresholding algorithm transforms a gray-level image into a set of multiple level regions of objects. A distance transformation algorithm then is used to transform a binary image into the minimum distance from each object point to the object's boundary. This algorithm uses a morphol... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Point symmetry of convex digital regions

    Publication Year: 1988, Page(s):604 - 609
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (360 KB)

    The authors define point symmetry for convex digital regions. They restrict their attention to convex digital regions that are N-connected. An efficient algorithm is presented to determine the points of symmetry of such regions by eliminating portions of a feasible region. If a convex digital region is not N-connected, the main result still applies and algorithm can still be used... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Color constancy computation in near-Mondrian scenes using a finite dimensional linear model

    Publication Year: 1988, Page(s):544 - 549
    Cited by:  Papers (11)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (364 KB)

    The authors combine an alternate version of B.K.P. Horn's computation (1974) for recovering lightness from Land's retinex scheme, as modified by A. Blake (1985), with a finite-dimensional linear model for color images. The authors recover surface spectral reflectance from images of near-Mondrian scenes by using edge detection and derivatives to screen out slowly changing illumination from color sc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Finding objects on aerial photographs: a rule-based low level system

    Publication Year: 1988, Page(s):118 - 122
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    A rule-based system for image segmentation and understanding is proposed. Called ROF (rule-based object finder), it is the low-level state of an image understanding system for aerial photographs. The general design of ROF uses a novel paradigm for segmentation. Candidate pixels for regions (or borders of regions) are chosen by the raw data module (RDM) on the basis of the geometric shape of their ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of two new stereo algorithms

    Publication Year: 1988, Page(s):177 - 182
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (552 KB)

    The authors present two algorithms for stereo matching that make use of simultaneous matching and surface reconstruction. By integrating matching and reconstruction, which are traditionally separated temporally, the algorithms can make use of the current surface approximation to help disambiguate the remaining matches. The result is a consistent smoothness assumption in both matching and surface r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Accessibility: a new approach to path planning among moving obstacles

    Publication Year: 1988, Page(s):803 - 807
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (400 KB)

    A study is performed of the problem of planning a collision-free path for a robot in a time-varying environment. It is assumed that an obstacle moves along a known path. The formulation also allows the destination point (the point to be reached) to move along a predetermined path. A concept of `accessibility' from a point to a moving object is introduced and is used to determine a collision-free p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A scale-independent dominant point detection algorithm

    Publication Year: 1988, Page(s):229 - 234
    Cited by:  Papers (4)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (496 KB)

    A parallel algorithm for detecting dominant points on a digital closed curve is presented. The procedure requires no input parameter and remains reliable even when features of multiple sizes are present on the digital curve. The procedure first determines the region of support for each point based on its local properties, then computes measures of relative significance (e.g. curvature) of each poi... View full abstract»

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