Showing papers by "Charles R. Dyer published in 1986"

Model-based recognition in robot vision

Abstract: This paper presents a comparative study and survey of model-based object-recognition algorithms for robot vision. The goal of these algorithms is to recognize the identity, position, and orientation of randomly oriented industrial parts. In one form this is commonly referred to as the "bin-picking" problem, in which the parts to be recognized are presented in a jumbled bin. The paper is organized according to 2-D, 2½-D, and 3-D object representations, which are used as the basis for the recognition algorithms. Three central issues common to each category, namely, feature extraction, modeling, and matching, are examined in detail. An evaluation and comparison of existing industrial part-recognition systems and algorithms is given, providing insights for progress toward future robot vision systems.

An algorithm for constructing the aspect graph

Abstract: In this paper we present tight bounds on the maximum size of aspect graphs and give worstcase optimal algorithms for their construction, first in the convex case and then in the general case. In particular, we give upper and lower bounds on the maximum size (including vertex labels) of Θ(n3) and Θ(n5) and algorithms for constructing the aspect graph which run in time O(n3) and O(n5) for the convex and general cases respectively. The algorithm for the general case makes use of a new 3D object representation called the aspect representation or asp. We also show a different way to label the aspect graph in order to save a factor of n in the asymptotic size (at the expense of label retrieval time) in both the convex and general cases, and we suggest alternatives to the aspect graph which require less space and store more information.

Shape Smoothing Using Medial Axis Properties

Abstract: A shape smoothing algorithm is presented which uses properties of the medial axis to define segments of the shape border and their prominence relative to the local radius of the shape. Prominence values are used to classify axes as either major or minor, and minor axes are then deleted. An augmented medial axis transform is also defined using an approximate Euclidean distance transform, and medial axis interpolation and linking.

Two dimensional object recognition using multiresolution models

Abstract: A multiresolution, model-based matching technique is described for coarse-to-fine object recognition. Each two-dimensional object is modeled as a directed acyclic graph. Each node in the graph stores a boundary segment of the object model at a selected level of spatial resolution. The root node of the graph contains the coarsest resolution representation of the boundary of the object, leaf nodes contain sections of the boundary at the highest resolution, and intermediate nodes contain features at intermediate levels of resolution. Arcs are directed from boundary segments at one level of resolution to spatially related boundary segments at finer levels of resolution. A generalized Hough transform is used to match the model nodes with regions in the corresponding level of resolution in a given input image pyramid. First, the root node of the model graph is matched with the coarsest level of the input image pyramid and an ordered list of hypothesized positions and orientations for the object is generated. These hypotheses limit the area in which the search for subobjects (children nodes) must be conducted. If the subobjects of a hypothesis are not found, the next best hypothesis for the position and orientation of the object at the coarsest level is tried. Advantages of this approach include the use of multiresolution descriptions to model different parts of an object at different scales, the ability to detect partially occluded objects, the ability to dynamically control the coarse-to-fine matching process, and the increase in recognition speed over conventional single resolution recognition algorithms.

Segmentation of textured images by pyramid linking

Abstract: A pyramid linking algorithm for texture segmentation is presented. It is based on the computation of spatial properties of long, straight edge segments at fixed orientations. Features are computed for each edge segment in terms of the distances to the nearest neighboring edge segments of given orientations. This produces a set of sparse “edge separation maps” of features which are then used as the basis of a pyramid linking procedure for hierarchically grouping edges into homogeneously textured regions. Segmentation is performed in one bottom-up pass of linking nodes to their most similar parent. Results are shown using both the raw and smoothed edge separation features. All of the steps of the procedure can be efficiently implemented as parallel operations on a pyramid machine.

Recognition and recovery of the three-dimensional orientation of planar point patterns

Abstract: A model-based approach is developed for recovering 3-dimensional surface orientation from a single image of an arbitrary planar point pattern or polygon. We define an iterative procedure which efficiently computes the correct surface orientation as well as solving the correspondence problem between the set of model features and the set of image features. There are no restrictions on the types of model point patterns and no a priori knowledge about the correspondence is assumed. The number of possible matches considered is linear in the number of points in the worst case, although experimental results show that using our heuristic for ordering candidate correspondences results in only a small constant number of matches that must be tried. The iterative procedure is also robust in that model tolerances and image distortions can be handled by relaxing the termination criterion; the resulting error in orientation is usually of the same order of magnitude as the distortion. Thus the method is of practical value because it uses arbitrary point sets and works on real, noisy data.