Showing papers by "Andrew Zisserman published in 1993"

A framework for spatiotemporal control in the tracking of visual contours

Abstract: There has been a great deal of research interest in contour tracking over the last five years. This article combines themes from tracking theory—elastic models and stochastic filtering—with the notion of affine invariance to synthesize a substantially new and demonstrably effective framework for contour tracking. A mechanism is developed for incorporating a shape template into a contour tracker via an affine invariant coupling. In that way the tracker becomes selective for shape and therefore able to ignore background clutter. Affine invariance ensures that the effect of varying viewpoint is accommodated. Use of a standard statistical filtering framework allows uncertainties to be treated systematically, which accommodates object flexibility and un-modeled distortions such as the deformation of a silhouette under motion. The statistical framework also facilitates a further development. In place of heuristically determined spatial scale for feature search, both spatial scale and temporal memory are controlled automatically and in a way that is responsive to the tracking process. Typically, the tracker operates initially in a coarse scale/short memory mode while it searches for a feature. Then spatial scale diminishes to allow more precise localization while memory (temporal scale) lengths to take advantage of motion coherence. All system parameters are determined by natural assumptions and desired tracking performance, leaving none to be fixed heuristically. Versions of the tracker have been implemented at video rate, both on SUN 4 and in parallel, using a network of 11 transputers. The theoretically established properties of automatic control of spatiotemporal scale and of affine invariance are demonstrated using the implemented tracker.

Extracting projective structure from single perspective views of 3D point sets

Abstract: A number of recent papers have argued that invariants do not exist for three-dimensional point sets in general position, which has often been misinterpreted to mean that invariants cannot be computed for any three-dimensional structure. It is proved by example that although the general statement is true, invariants do exist for structured three-dimensional point sets. Projective invariants are derived for two object classes: the first is for points that lie on the vertices of polyhedra, and the second for objects that are projectively equivalent to ones possessing a bilateral symmetry. The motivations for computing such invariants are twofold: they can be used for recognition, and they can be used to compute projective structure. Examples of invariants computed from real images are given. >

Affine-invariant contour tracking with automatic control of spatiotemporal scale

Abstract: A framework for visual tracking of contours is presented, based on a synthesis of elastic models, stochastic filtering, and geometric invariance. Flexibly coupled curve templates implement soft prior assumptions about shape. Affine invariance, built into the flexible coupling, ensures that the affine deformations that arise naturally from image projection are favored. The stochastic basis of the framework is shown to result naturally in an automatic mechanism for the control of spatiotemporal scale. >

Efficient recognition of rotationally symmetric surfaces and straight homogeneous generalized cylinders

Abstract: It is known that rotationally symmetric surfaces can be recognized from their outlines alone, using cross-ratios of bitangent intersections. A successful implementation of this technique is demonstrated using a novel bitangent finder which works on images of real scenes. The stability of the cross-ratios is reported and compared to affine invariants. The recognition technique is shown to extend to the case of straight homogeneous generalized cylinders. >

Repeated Structures: Image Correspondence Constraints and 3D Structure Recovery

Abstract: Recently, a number of classes of 3D structures have been identified which permit structure recovery and 3D invariants to be measured from a single image of the structure. A large class with this property is the case of repeated structures where a structure (such as a pointset, curve or surface), and a transformed copy of the structure are both observed in a single perspective image. In general the 3D reconstruction is only possible up to a 3D projectivity of space, but smaller ambiguities are possible, depending on the nature of the 3D transformation between the repeated structures. An additional theme of the paper is the development of feature correspondence relations based on the epipolar geometry induced in the image by the repeated structure. In some cases, correspondence is based on projective homologies rather than a true epipolar geometry.

A Case Against Epipolar Geometry

Abstract: We discuss briefly a number of areas where epipolar geometry is currently central in carrying out visual tasks. In contrast we demonstrate configurations for which 3D projective invariants can be computed from perspective stereo pairs, but epipolar geometry (and full projective structure) cannot. We catalogue a number of these configurations which generally involve isotropies under the 3D projective group, and investigate the connection with camera calibration. Examples are given of the invariants recovered from real images. We also indicate other areas where a strong reliance on epipolar geometry should be avoided, in particular for image transfer.

Visual exploration of free-space

Abstract: A gas and vapor separator includes an axial fan with blade members which carry an absorbing material. A power means, such as an electric motor, rotates the fan, which causes the adulterated fluid to pass through the apparatus. As the fan blades contact the fluid, the desiccant material absorbs the undesirable elements in the fluid and simultaneously expels the cleansed fluid. The centrifugal force which acts on the absorbed matter causes said matter to radially translate in an outwardly fashion into a circular collector which entraps and retains the absorbed matter. The desiccant material is thereby continuously purged and capable of continuously cleansing the adulterated fluid.

Finding Point Correspondences in Motion Sequences Preserving Affine Structure.

Abstract: In this paper the problem of computing the point correspondences in a sequence of time-varying images of a 3D object undergoing nonrigid (affine) motion is addressed. It is assumed that the images are obtained through affine projections. The correspondences are established only from the analysis of the unknown 3D affine structure of the object, without making use of any attributes of the feature points. It is shown that it is possible to establish the point correspondences uniquely (up to symmetry) in the sense that they yield a unique affine structure of the object and that the computation is possible in polynomial time. Two different algorithms for computing the point correspondences are presented. Results on various real image sequences, including a sequence containing independently moving objects, demonstrate the applicability of the structure based approach to motion correspondence.

Extracting Structure from an Affine View of a 3D Point Set with One or Two Bilateral Symmetries.

Abstract: We demonstrate that the structure of a 3D point set with a single bilateral symmetry can be reconstructed from an uncalibrated affine image, modulo a Euclidean transformation, up to a four parameter family of symmetric objects that could have given rise to the image. If the object has two orthogonal bilateral symmetries, its shape can be reconstructed, modulo a Euclidean transformation, to a three parameter family of symmetric shapes that could have given rise to the image. Furthermore, if the camera aspects ratio is known, the three parameter family reduces to a single scale and the orientation of the object can be determined. These results are demonstrated using real images with uncalibrated cameras.

Eliciting qualitative structure from image curve deformations

Abstract: A family of qualitative methods is described that determines structure of curves in a scene from their image projections in two or more views. For example, plane curves are distinguished from space curves, and space curves from contour generators. The novelty of the approach is that first, it is unaffected by camera intrinsic parameters, so calibration is not required; second, it is also unaffected by camera motion, so viewer motion need not be known; and third, curves need not be matched point by point. Qualitative scene descriptions can be determined using relative measurements, and affine or projective properties alone. The practical power of this family of methods is demonstrated using a real-time vision system based on B-spline snake-tracking. >

Seismic Time Section Analysis Using Machine Vision.

Abstract: In this paper we introduce a three stage approach for extracting events from a seismic time section. The approach incorporates recent, techniques from computer vision such as deformable templates and multiple hypothesis tracking, and also takes advantage of constraints arising from the physics of seismic reflectors. First, a 2D local matched fdtering scheme is used to reduce the time section to a collection of event tokens suitable for tracking with a Kalman filter. Second, a multiple tracking system is used to analyse regions with crossing events. By using a dynamic model of event shape parameters, Kalman filters are able to track events that deviate from an ideal form. Finally, based on events found through Kalman filtering, flexible templates are used to exploit similarity between events. Due to the global nature of the flexible template search process, even events with sections of poor visibility can be identified. Based on this research, a semi-automatic system for extracting seismic events has been developed.