By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 6 • Date Nov. 1980

Filter Results

Displaying Results 1 - 19 of 19
  • [Front cover]

    Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (549 KB)  
    Freely Available from IEEE
  • [Front inside cover]

    Page(s): c2
    Save to Project icon | Request Permissions | PDF file iconPDF (397 KB)  
    Freely Available from IEEE
  • Preface

    Page(s): 493 - 494
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (991 KB)  

    THIS Special Issue is an outgrowth of the IEEE Computer X Society Workshop on Computer Analysis of Time-Varying Imagery held in Philadelphia, PA, April 5–6, 1979. The Workshop was sponsored by the Technical Committee on Machine Intelligence and Pattern Analysis. Obviously, the Workshop played a significant role in bringing about this Special Issue and a major fraction of the papers included in this issue were presented or discussed at the Workshop. However, there was no attempt on the part of the Editors to limit the issue to the papers presented at the Workshop. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion detection and analysis of matching graphs of intermediate-level primitives

    Page(s): 495 - 510
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (22238 KB)  

    Introduces a new primitive, the half-chunk, for encoding boundary, region, and surface information in graph form. General graph matching is discussed and a specific graph matching system based on half-chunk graphs is presented. Following matching, bindings are interpreted as object component motion or depth. The half-chunk graph allows scale and coordinate system independent object models to be represented. Half-chunk graphs may encode 2-D or 3-D structure equally well. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Depth from camera motion in a real world scene

    Page(s): 511 - 516
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4466 KB)  

    Presents a method for deriving depth information from a moving image where the camera is moving through a real world scene. The method refines a simple surface model based on error measures that are derived by interimage comparisons of point values. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tracking and segmentation of moving objects in dynamic line images

    Page(s): 516 - 522
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1924 KB)  

    As a part of a cine-film understanding system, the paper presents a dynamic scene analyzer which separates moving objects from the background and analyzes their motion patterns in dynamic line images such as cartoon films. Finding correspondence of regions and their segments in a sequence of input frames by a new flexible template matching method, the analyzer tracks moving regions and their segments in the dynamic images. Next a similarity test of segment movements detects the background movement, and classifies the regions into stationary and nonstationary ones. Each in the latter group is further labeled as partly occluded, false, or moving, by examining both motion patterns of its segments and temporal change of its structure. Finally, the analyzer merges segments of each moving object into groups, having similar motion patterns, in order to obtain a meaningful partition corresponding to its components such as hands or legs. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model-based image analysis of human motion using constraint propagation

    Page(s): 522 - 536
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (11248 KB)  

    A system capable of analyzing image sequences of human motion is described. The system is structured as a feedback loop between high and low levels: predictions are made at the semantic level and verifications are sought at the image level. The domain of human motion lends itself to a model-driven analysis, and the system includes a detailed model of the human body. All information extracted from the image is interpreted through a constraint network based on the structure of the human model. A constraint propagation operator is defined and its theoretical properties outlined. An implementation of this operator is described, and results of the analysis system for short image sequences are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A plan-guided analysis of cineangiograms for measurement of dynamic behavior of heart wall

    Page(s): 537 - 543
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3933 KB)  

    As an example of noisy dynamic image processing, the paper presents a plan-guided analysis system of cineangiograms, X-ray motion pictures of a beating heart in which X-ray opaque dye is injected through a catheter. A task of the system is the detection of both the internal and external surfaces of the left ventricular chamber and the measurement of the spatial and temporal change in thickness of the heart wall, which gives us important measures of various heart diseases. The features of the system are as follows: 1) sophisticated edge detectors to detect boundary points having low contrast in noisy pictures, 2) an efficient search method for finding smooth boundaries of heart wall accurately using an improved optimization method, and 3) use of the plan to guide the above two processes so that the cineangiogram can be analyzed efficiently and reliably. Experiments have been carried out, and the results obtained so far show very good agreement with boundaries detected by radiologists. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining motion and contrast for segmentation

    Page(s): 543 - 549
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (6728 KB)  

    A method is presented for partitioning a scene into regions corresponding to surfaces with distinct velocities. Both motion and contrast information are incorporated into the segmentation process. Velocity estimates for each point in a scene are obtained using a local nonmatching technique not dependent on any prior boundary determination. The actual segmentation is accomplished using a region merging procedure which combines regions based on similarities in both brightness and motion. The method is effective in determining object boundaries not easily found using analysis applied only to a single image frame. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exploiting image formation knowledge for motion analysis

    Page(s): 550 - 554
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1335 KB)  

    Deals with scene sequences showing objects in motion. Gray values of an object surface element, traced through the sequence, will exhibit systematic variations due to changing lighting and viewing conditions. Much of today's understanding of the underlying image formation process is due to Horn, who showed in particular that given sufficient knowledge about imaging conditions, gray values may be used to infer object shape. Assuming certain idealized but unknown object surface properties and light source characteristics it is shown that in general rotation angle increments and projected object surface angles but no absolute angle values may be computed from the observed data. Given additional knowledge about unknown illumination parameters, however, object shape may be determined. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Determining the movement of objects from a sequence of images

    Page(s): 554 - 562
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2005 KB)  

    Discusses the problem of determining the three-dimensional model and movement of an object from a sequence of two-dimensional images. A solution to this problem depends on solving a system of nonlinear equations using a modified least-squared error method. Two views of six points or three views of four points are needed to provide an overdetermined set of equations when the images are noisy. It is shown, however, that this numerical method is not very accurate unless the images of considerably more points are used. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A framework for visual motion understanding

    Page(s): 563 - 573
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2862 KB)  

    A framework for the abstraction of motion concepts from sequences of images by computer is presented. The framework includes: 1) representation of knowledge for motion concepts that is based on semantic networks; and 2) associated algorithms for recognizing these motion concepts. These algorithms implement a form of feedback by allowing competition and cooperation among local hypotheses. They also allow a change of attention mechanism that is based on similarity links between knowledge units, and a hypothesis ranking scheme based on updating of certainty factors that reflect the hypothesis set inertia. The framework is being realized with a system called ALVEN. The purpose behind this system is to provide an evolving research prototype for experimenting with the analysis of certain classes of biomedical imagery, and for refining and quantifying the body of relevant medical knowledge. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards a system for the interpretation of moving light displays

    Page(s): 574 - 581
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1940 KB)  

    Lights is a system for the interpretation of simple moving light displays (MLD) of jointed objects against a stationary background. The displays studied differ from those examined by previous researchers in that 1) objects are represented by a relatively small number of points, 2) objects are not rigid, and 3) the viewing geometry is such that highly varying degrees of perspective distortion occur. An algorithm is presented which segments the points of an MLD of a wire-frame man into body parts. The relationship of this algorithm to previous theories of MLD perception and actual human performance is discussed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Correspondence: On monocular perception of 3-D moving objects

    Page(s): 582 - 583
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (607 KB)  

    The reconstruction of a 3-D moving object from its images is discussed. Inequalities describing the relation between the required number of points observed on the object and the number of frames are given, and the scale and orientational invariance of the procedure are discussed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of three-dimensional movement using Fourier descriptors

    Page(s): 583 - 588
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1279 KB)  

    Recent improvements in Fourier descriptor (FD) shape analysis enable rapid identification of three-dimensional objects using FD feature vectors derived from their boundaries. In three-dimensional shape analysis, it is essential to preserve all information to achieve good performance. In the real-time situation it is, of course, equally important to use a computationally efficient method. The method of three-dimensional shape analysis using normalized Fourier descriptors is information preserving, yet is as fast as previous suboptimum methods. In addition, the feature vector has a linear property, allowing to interpolate between library projections and effectively define a continuum of library projections rather than a finite set. This method is applied to the analysis of sequential data varying in resolution and orientation relative to the camera. Computational considerations are discussed, and it is seen that real-time implementation of the method is feasible. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 1980 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. PAMI-2

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | PDF file iconPDF (1556 KB)  
    Freely Available from IEEE
  • Advertisements

    Page(s): 1 - 2
    Save to Project icon | Request Permissions | PDF file iconPDF (1141 KB)  
    Freely Available from IEEE
  • Inside back cover

    Page(s): c3
    Save to Project icon | Request Permissions | PDF file iconPDF (333 KB)  
    Freely Available from IEEE
  • Back cover

    Page(s): c4
    Save to Project icon | Request Permissions | PDF file iconPDF (6574 KB)  
    Freely Available from IEEE

Aims & Scope

The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is published monthly. Its editorial board strives to present most important research results in areas within TPAMI's scope.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
David A. Forsyth
University of Illinois