Showing papers by "Charles R. Dyer published in 1990"

Visibility, occlusion, and the aspect graph

Abstract: This chapter studies the ways in which the topology of the image of a polyhedron changes with changing viewpoint. We catalog the ways that the topological appearance, or aspect, can change. This enables us to find maximal regions of viewpoints of the same aspect. We use these techniques to construct the viewpoint space partition (VSP), a partition of viewpoint space into maximal regions of constant aspect, and its dual, the aspect graph. Here, we present tight bounds on the maximum size of the VSP and the aspect graph and give algorithms for their construction, first in the convex case and then in the general case. In particular, we give bounds on the maximum size of θ(n 2) and θ(n 6) under an orthographic projection viewing model and of θ(n 3) and θ(n 9) under a perspective viewing model. The algorithms make use of a new representation of the appearance of polyhedra from all viewpoints, called the aspect representation or asp. We believe that this representation is one of the significant contributions of this paper.

Aspect graphs: An introduction and survey of recent results

Abstract: The study of the aspect graph of a three-dimensional object has recently become an active area of research in computer vision. The aspect graph provides a complete enumeration of all possible distinct views of an object, given a model for viewpoint space and a definition for “distinct.” This article presents a tutorial introduction to the aspect graph, surveys the current state of the art in algorithms for automatically constructing aspect graphs, and describes some possible applications of aspect graphs in computer vision and computer graphics.

Cyclic motion detection using spatiotemporal surfaces and curves

Abstract: Cyclic motion is formally defined as repeating curvature values along a path of motion. A procedure is presented for cyclic motion detection using spatiotemporal (ST) surfaces and ST curves. The projected movement of an object generates ST surfaces. ST curves are detected on the ST surfaces, providing an accurate, compact, qualitative description of the ST surfaces. Curvature scale-space of the ST curves is then used to detect intervals of repeating curvature values. The successful detection of cyclic motion in two data sets is presented. >

Real-time motion tracking of three-dimensional objects

Abstract: The problem in which the 3D motion of an object corresponding to a known polyhedral model is to be computed using only the motion of edge features in a continuous stream of 2D images is considered. Advantage is taken of the spatiotemporal density of the input signal and the limitations of long-range trajectory-prediction methods are avoided. Two parallel algorithms which use feature-based, short-range (spatiotemporally local) motion processes to achieve real-time tracking of modeled objects are presented. Both algorithms have been implemented and tested on a tightly coupled multiprocessor system consisting of an Aspex Pipe for low-level image-feature computations and a Sequent Symmetry for high-level model-based computations. An analysis is given of the actual performance limits of each method using the current hardware configuration. >

Computing spatiotemporal surface flow

Abstract: It is observed that arc length of a contour does not change if that contour is moved in the direction of motion on the surface. A function measuring arc length change is defined. The direction of motion of a contour undergoing motion parallel to the image plane is shown to be perpendicular to the gradient of this function. This gradient approximates the direction of motion when object motion in the scene is not parallel to the image plane or when perspective projection is used. This method has been implemented and is shown to compute the ST (spatiotemporal) surface flow in sequences of edge images and gray level images. >

Real-time, parallel motion tracking of three dimensional objects from spatiotemporal sequences

Abstract: A major issue in computer vision is the interpretation of three-dimensional (3D) motion of moving objects from a continuous stream of two-dimensional (2D) images. In this paper we consider the problem where the 3D motion of an object corresponding to a known 3D model is to be tracked using only the motion of 2D features in the stream of images. Two general solution paradigms for this problem are characterized: (1) motion-searching, which hypothesizes and tests 3D motion parameters, and (2) motion-calculating, which uses back-projection to directly estimate 3D motion from image-feature motion. Two new algorithms for computing 3D motion based on these two paradigms are presented. One of the major novel aspects of both algorithms is their use of the assumption that the input image stream is spatiotemporally dense. This constraint is psychologically plausible since it is also used by the short-range motion processes in the human visual system.

Modeling the rim appearance

Abstract: A viewer-centered approach is presented to modeling the geometry of the visible occluding contour of solid 3-D shape. The rim appearance representation models the exact appearance of the occluding contour formed by the edges of a polyhedron. An algorithm is presented for constructing the rim appearance representation. Bounds on space and time are given, and implementation results show that the rim appearance representation is significantly smaller than both the aspect graph and the asp representation. >

Aspect graphs: an introduction and survey of recent results

Abstract: . The study of the aspect graph of a three-dimensional object has recently become an active area of research in computer vision. The aspect graph provides a complete enumeration of all the possible distinct views of an object, under a particular model for the viewpoint space and a particular definition for "distinct." This paper gives a tutorial introduction to the aspect graph, surveys the current state of the art in algorithms for automati- cally constructing the aspect graph, and describes some possible applications of aspect graphs in computer vision and computer graphics.

Parallel simulation of a connectionist stereo algorithm on a shared-memory multiprocessor

Abstract: This paper describes the parallel simulation of a connectionist network stereo matching algorithm. In the algorithm a relaxation computation uses a variety of consistency measures between candidate matches to determine the correct match for each edge. These measures include disparity consistency, contour consistency, and multiresolution consistency. In the network each node represents a candidate match and the connections between nodes implement the consistency relations. The simulation involves constructing the list of candidate matches, constructing the list of connections between matches, and performing the iterations of the relaxation computation. Within each of these stages of the simulation, computation may be partitioned among a number of processors with very little need for synchronization or mutual exclusion except at the end of the stage. As a result, the implementation of the simulation on a shared-memory multiprocessor produced nearly linear speed-ups for up to nine processors (the maximum available at the time of implementation).

Real-time, parallel motion tracking of three dimensional objects from spatiotemporal

Abstract: A major issue in computer vision is the interpretation of three-dimensional (3D) motion of moving objects from a continuous stream of two-dimensional (2D) images. In this paper we consider the problem where the 3D motion of an object corresponding to a known 3D model is to be tracked using only the motion of 2D features in the stream of images. Two general solution paradigms for this problem are characterized: (1) motion-searching, which hypothesizes and tests 3D motion parameters, and (2) motion-calculating, which uses back­ projection to directly estimate 3D motion from image-feature motion. Two new algorithms for computing 3D motion based on these two paradigms are presented. One of the major novel aspects of both algorithms is their use of the assumption that the input image stream is spatiotemporally dense. This constraint is psychologically plausible since it is also used by the short-range motion processes in the human visual system. The processing of a temporally-unbounded, spatiotemporal image com­ bined with the resource constraint of finite image buffer memory, requires real-time throughput rates for our algorithms. Consequently, another major focus of this paper is the development of real-time, parallel implementations to achieve the required throughput. Implementations of both algorithms are described using an Aspex Pipe for low-level, image-feature computations and a Sequent Symmetry for high-level, model-based computations. The Pipe, a pipelined image processor, is tightly-coupled with the Sequent, and semaphores are used for synchronization between the two. Design issues and parallel im­ plementation issues of both algorithms are discussed in detail.

Parallel simulation of a connectionist stereo algorithm

Abstract: This paper describes the parallel simulation of a connectionist network stereo matching algorithm. In the algorithm a relaxation computation uses a variety of consistency measures between candidate matches to determine the correct match for each edge. These measures include disparity consistency, contour consistency, and multiresolution consistency. In the network each node represents a candidate match and the connections between nodes implement the consistency relations. The simulation involves constructing the list of candidate matches, constructing the list of connections between matches, and performing the iterations of the relaxation computation. Within each of these stages of the simulation, computation may be partitioned among a number of processors with very little need for synchronization or mutual exclusion except at the end of the stage. As a result, the implementation of the simulation on a shared-memory multiprocessor produced nearly linear speed-ups for up to nine processors (the maximum available at the time of implementation).