IEE Colloquium on Motion Analysis and Tracking (Ref. No. 1999/103)

1999

Filter Results

Displaying Results 1 - 19 of 19
  • Segmenting image sequences by embedding motion and colour cues within a contextual relaxation scheme

    Publication Year: 1999, Page(s):18/1 - 18/6
    Cited by:  Papers (1)  |  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (704 KB)

    The segmentation of variously moving elements in the images of a film sequence is the basis of a range of digital special effects. Segmentation in film post-production is often carried out laboriously by hand, a method that has a number of drawbacks. Automated segmentation methods are of great benefit to the industry. Such methods must not only determine the boundary between foreground and backgro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Correcting velocity measurements by tracking of linear features

    Publication Year: 1999, Page(s):10/1 - 10/6
    Cited by:  Patents (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (612 KB)

    This paper describes an approach to accurate velocity estimation of objects in image sequences. It combines feature-based and non-feature-based velocity estimation methods, in order to overcome the limitations that both techniques exhibit when used separately. It is well known that popular non-feature-based methods, such as optical flow and correlation methods, suffer from the problem of inaccurac... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The time-gradient Hough transform-a novel algorithm from meteor science

    Publication Year: 1999, Page(s):16/1 - 16/6
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (468 KB)

    A novel extension of the Hough transform is described, allowing measurement of the speed of motion of a body across the image plane. An astronomical application of the technique is described: the automatic detection and recording of meteors. The algorithm is presented and successful test results given View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image sequence segmentation using mixture models with uniqueness and spatio-temporal consistency constraints

    Publication Year: 1999, Page(s):6/1 - 6/6
    Cited by:  Papers (1)  |  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (852 KB)

    Operations such as video coding and digital video restoration rely on knowledge of the motion that has occurred in the scene. Whereas research in the 1980's and early 1990's concentrated on reliable recovery of motion fields on a per-pixel or per-block basis, the current trend is towards object-based motion estimation, and the aim is simultaneous recovery of the significant motions in a scene and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust multi-frame motion estimation with motion compensated prediction applications

    Publication Year: 1999, Page(s):12/1 - 12/6
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (436 KB)

    A motion trajectory provides a localised description of motion over multiple frames. This paper describes an approach for estimating a spatially distributed set of such trajectories, with the aim to adequately describe all of the motions present within an image. The problem is conveniently cast in a Markov Random Field (MRF) framework, with a coupled line-process field to handle motion boundaries.... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Finding continuous-model moving shapes by evidence gathering

    Publication Year: 1999, Page(s):14/1 - 14/5
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (460 KB)

    Two recent approaches are combined in a new technique to find moving arbitrary shapes. We combine the new velocity Hough transform, which extracts moving conic sections, with a continuous formulation for arbitrary shape extraction. The new velocity Hough transform is demonstrated to provide motion analysis that is resilient to noise and to be able to detect its target shapes, which are both moving... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Marker based motion capture in biomedical applications

    Publication Year: 1999, Page(s):4/1 - 4/5
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (284 KB)

    The problem of hip joint centre location using optical markers is addressed. We present a novel computational technique which can recover joint centre location based solely on marker measurements together with a quantitative estimate of its uncertainty. Preliminary experimental validation of the technique on a rigid jointed object is presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Higher order spatial transformations for motion analysis and modelling

    Publication Year: 1999, Page(s):9/1 - 9/6
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (496 KB)

    In this paper we present two novel methods for obtaining the ST motion parameters of arbitrary shaped video objects. These methods use genetic algorithm (GA) optimisation to efficiently and robustly search the multidimensional space of possible solutions. An overview of ST and GA techniques, is provided and the proposed algorithms are described. Some results are given, comparing the performance of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Designing video-joysticks

    Publication Year: 1999, Page(s):13/1 - 13/6
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (872 KB)

    This paper reports work in progress on the design of a video-joystick system. At first glance, the design of such a system might seem like a rather trivial computer vision problem. However, computer vision problems tend to be harder in practice than one initially expects. The paper discusses some of the need for such a system and some possible strategies for implementing it. The computer games ind... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion analysis and tracking

    Publication Year: 1999, Page(s):0_5 - 0_6
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (76 KB)

    First Page of the Article
    View full abstract»

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

    Publication Year: 1999, Page(s):3/1 - 3/6
    Cited by:  Papers (35)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (644 KB)

    Gait is an emergent biometric aimed essentially to recognise people by the way they walk. Its advantages are that it is non-invasive and that it is less likely to be obscured since it appears to be difficult to camouflage, especially in cases of serious crime. Gait has allied subjects which lend support to the view that gait has clear potential as a biometric. Essentially, we use computer vision t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Target identification in a complex maritime scene

    Publication Year: 1999, Page(s):15/1 - 15/4
    Cited by:  Papers (4)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (684 KB)

    This paper describes new methods applied to the problem of target identification in complex maritime scenes. The algorithm described here automatically identifies rigid objects moving in a maritime scene. The methods for target identification proposed here are based on the change in statistical descriptors of image segments and on axis projections of the difference image. Results from this stage o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion estimation and tracking using multiresolution affine models

    Publication Year: 1999, Page(s):7/1 - 7/6
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (1036 KB)

    As in many areas of image analysis, a key issue when tackling motion is determining the appropriate size of local analysis window to be used. The work described in the paper attempts to address this problem. It is based on two key elements: the use of an affine model to describe local motion variation within a sequence; and the incorporation of this local model into a multiresolution framework to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Bayesian theory of multi-scale cross-correlation in images

    Publication Year: 1999, Page(s):1/1 - 1/4
    Cited by:  Papers (1)  |  Patents (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (652 KB)

    Cross-correlation is a commonly used principle for intensity-based object localization but gives only a single estimate of location. On the other hand, random sampling algorithms can generate an entire probability distribution for object location. That allows the representation of ambiguity, and sequential inference including propagation from coarse to fine scale, and over time. Bayesian cross-cor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CDWT optical flow applied to moving target detection

    Publication Year: 1999, Page(s):17/1 - 17/6
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (472 KB)

    Moving target detection and tracking is a problem of major importance in modern military applications. Examples of such applications include detection of moving targets from a surveillance post, a missile flyby search for ground-based moving targets, and the detection of airborne targets from an airborne platform. The work presented here focuses on the detection of the target rather than the track... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tracking objects in underwater multibeam sonar images

    Publication Year: 1999, Page(s):11/1 - 11/7
    Cited by:  Papers (7)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (432 KB)

    This paper describes an obstacle detection and tracking algorithm applied to multibeam forward-looking sonar images. It is used by an obstacle avoidance system to be fitted in a remotely operated underwater vehicle (ROV). The real-time data flow from the sonar output is represented as an image and pre-processed (smoothing filters, region-based segmentation and feature extraction) by the system to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human walking: tracking and analysis

    Publication Year: 1999, Page(s):5/1 - 514
    Cited by:  Papers (7)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (1264 KB)

    The study of human walking has been of interest to researchers in different disciplines, e.g. modelling of human body, perceiving actions and analysing gait. Our research addresses the question of the existence of diagnostic signatures far human walking from kinematic gait data. This is motivated by the capabilities of humans to perceive gait from reduced spatio-temporal features and characteristi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining segmentation by nonlinear diffusion and shape adaptive block-matching for content based coding

    Publication Year: 1999, Page(s):19/1 - 19/6
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (1240 KB)

    A technique for image simplification and segmentation in scale-space is presented. Segmentation masks are then used to estimate accurately the parameters describing motion of single objects in the scene. The segmentation approach relies on a non-linear diffusion model in which multiscale image simplification and subsequent segmentation of the resulting smoothed images is performed. Motion paramete... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature tracking in real world scenes (or how to track a cow)

    Publication Year: 1999, Page(s):2/1 - 2/7
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (544 KB)

    In this paper we present a novel scheme for modelling and tracking complex real life objects. The scheme uses multiple models based on a variation of the point distribution model known as the vector distribution model. Inter and intra-class variation is separated using a variation on linear discriminant analysis known as `Delta Analysis'. The tracking scheme is stochastic and is based on modelling... View full abstract»

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