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, 2&D, and 3-D object representations, which are used as the basis for the recognition algorithms. Three

Abstract: Before corresponding points in images taken with two cameras can be used to recover distances to objects in a scene, one has to determine the position and orientation of one camera relative to the other. This is the classic photogrammetric problem of relative orientation, central to the interpretation of binocular stereo information. Iterative methods for determining relative orientation were developed long ago; without them we would not have most of the topographic maps we do today. Relative orientation is also of importance in the recovery of motion and shape from an image sequence when successive frames are widely separated in time. Workers in motion vision are rediscovering some of the methods of photogrammetry. Described here is a simple iterative scheme for recovering relative orientation that, unlike existing methods, does not require a good initial guess for the baseline and the rotation. The data required is a pair of bundles of corresponding rays from the two projection centers to points in the scene. It is well known that at least five pairs of rays are needed. Less appears to be known about the existence of multiple solutions and their interpretation. These issues are discussed here. The unambiguous determination of all of the parameters of relative orientation is not possible when the observed points lie on a critical surface. These surfaces and their degenerate forms are analysed as well.

Symmetry detection is important in the area of computer vision. A 3-D symmetry detection algorithm is presented in this correspondence. The symmetry detection problem is converted to the correlation of the Gaussian image. Once the Gaussian image of the object has been obtained, the algorithm is independent of the input format. The algorithm can handle different kinds of images or objects. Simulated and real images have been tested in a variety of formats, and the results show that the symmetry can be determined using the Gaussian image.

We introduce a new surface representation for recognizing curved objects. Our approach begins by representing an object by a discrete mesh of points built from range data or from a geometric model of the object. The mesh is computed from the data by deforming a standard shaped mesh, for example, an ellipsoid, until it fits the surface of the object. We define local regularity constraints that the mesh must satisfy. We then define a canonical mapping between the mesh describing the object and a standard spherical mesh. A surface curvature index that is pose-invariant is stored at every node of the mesh. We use this object representation for recognition by comparing the spherical model of a reference object with the model extracted from a new observed scene. We show how the similarity between reference model and observed data can be evaluated and we show how the pose of the reference object in the observed scene can be easily computed using this representation. We present results on real range images which show that this approach to modelling and recognizing three-dimensional objects has three main advantages: First, it is applicable to complex curved surfaces that cannot be handled by conventional techniques. Second, it reduces the recognition problem to the computation of similarity between spherical distributions; in particular, the recognition algorithm does not require any combinatorial search. Finally, even though it is based on a spherical mapping, the approach can handle occlusions and partial views.

The photometric-stereo method is one technique for three-dimensional shape determination that has been implemented in a variety of experimental settings and that has produced consistently good results. The idea is to use intensity values recorded from multiple images obtained from the same viewpoint but under different conditions of illumination. The resulting radiometric constraint makes it possible to obtain local estimates of both surface orientation and surface curvature without requiring either global smoothness assumptions or prior image segmentation. Photometric stereo is moved one step closer to practical possibility by a description of an experimental setting in which surface gradient estimation is achieved on full-frame video data at nearvideo-frame rates (i.e., 15 Hz). The implementation uses commercially available hardware. Reflectance is modeled empirically with measurements obtained from a calibration sphere. Estimation of the gradient (p, q) requires only simple table lookup. Curvature estimation additionally uses the reflectance map R(p, q). The required lookup table and reflectance maps are derived during calibration. Because reflectance is modeled empirically, no prior physical model of the reflectance characteristics of the objects to be analyzed is assumed. At the same time, if a good physical model is available, it can be retrofitted to the method for implementation purposes. Photometric stereo is subject to error in the presence of cast shadows and interreflection. No purely local technique can succeed because these phenomena are inherently nonlocal. Nevertheless, it is demonstrated that one can exploit the redundancy in three-light-source photometric stereo to detect locally, in most cases, the presence of cast shadows and interreflection. Detection is facilitated by the explicit inclusion of a local confidence estimate in the lookup table used for gradient estimation. 1.

In this paper we present a new technique for partial surface and volume matching of images in three dimensions. In this

We propose a novel technique for the registration of 3D point clouds which makes very few assumptions: we avoid any manual rough alignment or the use of landmarks, displacement can be arbitrarily large, and the two point sets can have very little overlap. Crude alignment is achieved by estimation of the 3D-rotation from two Extended Gaussian Images even when the data sets inducing them have partial overlap. The technique is based on the correlation of the two EGIs in the Fourier domain and makes use of the spherical and rotational harmonic transforms. For pairs with low overlap which fail a critical verification step, the rotational alignment can be obtained by the alignment of constellation images generated from the EGIs. Rotationally aligned sets are matched by correlation using the Fourier transform of volumetric functions. A fine alignment is acquired in the final step by running Iterative Closest Points with just few iterations.

This paper describes a system which locates and grasps parts from a pile. The system uses photometric stereo and binocu-lar stereo as vision input tools. Photometric stereo is used to make surface orientation measurements. With this informa-tion the camera field is segmented into isolated regions of a continuous smooth surface. One of these regions is then selected as the target region. The attitude of the physical ob-ject associated with the target region is determined by histo-graming surface orientations over that region and comparing them with stored histograms obtainedfrom prototypical objects. Range information, not available from photometric stereo, is obtained by the PRISM binocular stereo system..4 collision-free grasp configuration is computed and executed using the attitude and range data.

In this paper we present a new technique for partial surface and volume matching of images in three dimensions. In this problem, we are given two objects in 3-space, each represented as a set of points, scattered uniformly along its boundary or inside its volume. The goal is to find a rigid motion of one object which makes a sufficiently large portion of its boundary lying sufficiently close to a corresponding portion of the boundary of the second object. This is an important problem in pattern recognition and in computer vision, with many industrial, medical, and chemical applications. Our algorithm is based on assigning a directed footprint to every point of the two sets, and locating all the pairs of points (one of each set) whose undirected components of the footprints are sufficiently similar. The algorithm then computes for each such pair of points all the rigid transformations that map the first point to the second, while making the respective direction components of ...

In this paper we introduce and investigate similarity measures for convex polyhedra based on Minkowski addition and inequalities for the mixed volume, volume and surface area related to the Brunn-Minkowski theory. All measures considered are invariant under translations; furthermore, they may also be invariant under subgroups of the affine transformation group. For the case of rotation and scale invariance, we prove that to obtain the measures based on (mixed) volume, it is sufficient to compute certain functionals only for a finite number of critical rotations. Extensive use is made of the slope diagram representation of convex polyhedra. AMS Subject Classification (1991): 52A38, 52B15, 68T10, 68U05 Keywords & Phrases: similarity measure, convex set, convex polyhedron, Minkowski addition, slope diagram representation, affine transformation, rotation, reflection, multiplication, similitude, volume, mixed volume, Brunn-Minkowski inequality, critical rotation, critical angle. 1 Introdu...