Zoom-invariant tracking using points and lines in affine views. An application of the affine multifocal tensors

  title={Zoom-invariant tracking using points and lines in affine views. An application of the affine multifocal tensors},
  author={Eric Hayman and Torfi Th{\'o}rhallsson and David William Murray},
  journal={Proceedings of the Seventh IEEE International Conference on Computer Vision},
  pages={269-277 vol.1}
This paper describes methods for tracking using point and line features in affine views to provide fundamental invariance to changes of focal length. It first demonstrates how an earlier method of transfer-based tracking using spatio-temporal matching of point features in a stereo active head is indeed zoom-invariant. In order to also make use of lines the paper then illustrates how the affine tri- and quadrifocal tensors may be applied to tracking with zoom in monocular and stereo systems… 

Figures from this paper

Tracking While Zooming Using Affine Transfer and Multifocal Tensors
In comparison with their projective counterparts, the affine tensors offer significant advantages in terms of computation time and convenience of parameterization, and the relations between the different tensors are shown to be much simpler.
Reactive Zoom Control while Tracking Using an Affine Camera
This paper describes a method for visual control of the zoom setting of an active camera during tracking that requires no self-calibration, the zooming camera may move quite generally, and no restriction need be applied to the nature of the scene being viewed.
Direct affine reconstruction
  • A. Heyden, F. Kahl
  • Computer Science
    Proceedings 15th International Conference on Pattern Recognition. ICPR-2000
  • 2000
This paper presents a novel method for structure and motion estimation from affine cameras, called direct affine reconstruction (DAR), which is well suited for tracking purposes as well as robust estimation schemes, like RANSAC, since only four basis points are needed.
Object tracking with a pan, tilt and zoom camera
This thesis reviews the existing work done on tracking with pan/tilt/zoom cameras and proposes a novel method of multiscale block tracking with perspective cameras using principles and methods from both computer vision and computer graphics.
Recent Progress in Epipolar Geometry
The research on the epipolar geometry was initiated for solving correspondence problems, and has been grown to the research on the general theory of multiple view geometry. The multiple view geometry
Continuous localization and mapping of a pan–tilt–zoom camera for wide area tracking
A solution that provides continuous online calibration of PTZ cameras which is robust to rapid camera motion, changes of the environment due to varying illumination or moving objects, and allows real-time tracking of multiple targets with high and stable degree of accuracy even at far distances and any zoom level is presented.
Corner detection and matching for visual tracking during power line inspection
In this paper, visual perception of frontal view in intelligent cars is considered. A Pan-Tilt-Zoom (PTZ) camera is used to track preceding vehicles. The aim of this work is to keep the rear view
Contour-based 3D motion recovery while zooming
Active Head Tracking Based on Chromatic Shape Fitting
In the proposed method, quasi real-time pursuit is achieved using a Pentium II computer in an uncontrolled environment with arbitrary relative motion between the target and camera.


Use Your Hand as a 3-D Mouse, or, Relative Orientation from Extended Sequences of Sparse Point and Line Correspondences Using the Affine Trifocal Tensor
This test problem illustrates the usefulness of the affine trifocal tensor in a situation where sufficient information is not available to compute the perspective trilinear tensor, while the geometry requires point correspondences as well as line correspondences over at least three views.
Geometry of Multiple Affine Views
A new linear method for Euclidean motion and structure from 3 calibrated affine images is described and some minimal point/line configurations for structure recovery are established.
The tensors of three affine views
  • T. Thórhallsson, D. W. Murray
  • Mathematics, Computer Science
    Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)
  • 1999
This paper shows how the estimation of the tensors from point correspondences is achieved through factorization, and discusses the estimation from line correspondences.
Matching constraints and the joint image
  • B. Triggs
  • Mathematics
    Proceedings of IEEE International Conference on Computer Vision
  • 1995
The geometry of multi image perspective projection and the matching constraints that this induces on image measurements are studied and their complex algebraic interdependency is captured by quadratic structural simplicity constraints on the Grassmannian.
Analysis and Computation of an Affine Trifocal Tensor
It will be shown that 4 point or 8 line correspondences along the three images are enough for a reliable computation of the trifocal tensor in the affine case (uncalibrated, weak perspective camera model), in contrast to the projective case, where at least 7 point or 13 line correspondence are needed for a linear computation (and usually with poor results).
Zooming while Tracking Using Affine Transfer
The use of afne transfer is demonstrated to track while zooming, using clusters of corner features, a natural mechanism to allow features to appear and disappear while tracking, events which will occur as detail sharpens and dissolves during zooming.
The Geometry of Projective Reconstruction I: Matching Constraints and the Joint Image
This paper studies the geometry of perspective projection into multiple images and the matching constraints that this induces between the images. The combined projections produce a 3D subspace of the
A Factorization Based Algorithm for Multi-Image Projective Structure and Motion
A practical method for the recovery of projective shape and motion from multiple images of a scene by the factorization of a matrix containing the images of all points in all views, using only fundamental matrices and epipoles estimated from the image data.
Tracking foveated corner clusters using affine structure
  • I. Reid, D. W. Murray
  • Computer Science
    1993 (4th) International Conference on Computer Vision
  • 1993
The method makes use of a real-time implementation of a corner detector and tracker and reconstructs the image position of the desired fixation point from a cluster of corners detected on the object using the affine structure available from two or three views.
A Common Framework for Multiple View Tensors
A common framework for the definition and operations on the different multiple view tensors is introduced and it is evident that the multiple view geometry is described by four different kinds of projective invariants; the epipoles, the fundamental matrices, the trifocal tensors and the quadfocal tensor.