. Visual servoing, using image-based control or positionbased control, generally gives satisfactory results. However, in some cases, convergence and stability problems may occur. The aim of this paper is to emphasize these problems by considering an eye-in-hand system and a positioning task with respect to a static target which constrains the six camera degrees of freedom. To appear in: The Confluence of Vision and Control, Lecture Notes in Control and Informations Systems, Springer-Verlag, 1998. 1 Introduction The two classical approaches of visual servoing (that is image-based control and position-based control) are different in the nature of the inputs used in their respective control schemes [28,10,14]. Even if the resulting robot behaviors thus also differ, both approaches generally give satisfactory results: the convergence to the desired position is reached, and, thanks to the closed-loop used in the control scheme, the system is stable, and robust with respect to camera calib...

This paper describes a method for detecting and recognizing road signs in gray-level and color images acquired by a single camera mounted on a moving vehicle. The method works in three stages. First, the search for the road sign is reduced to a suitable region of the image by using some a priori knowledge on the scene or color clues (when available) . Secondly, a geometrical analysis of the edges extracted from the image is carried out, which generates candidates to be circular and triangular signs. Thirdly, a recognition stage tests by cross-correlation techniques each candidate which, if validated, is classified according to the data-base of signs. An extensive experimentation has shown that the method is robust against low-level noise corrupting edge detection and contour following, and works for images of cluttered urban streets as well as country roads and highways. A further improvement on the detection and recognition scheme has been obtained by means of temporal integration b...

A central problem in object recognition is to determine the transformation that relates the model to the image, given some partial correspondence between the two. This is useful in determining whether an object is present in an image, and if so, determining where the object is. We present a novel method of solving this problem that uses region information. In our approach the model is divided into volumes, and the image is divided into regions. Given a match between subsets of volumes and regions (without any explicit correspondence between different pieces of the regions) the alignment transformation is computed. The method applies to planar objects under similarity, affine, and projective transformations and to projections of 3-D objects undergoing affine and projective transformations. 1 Introduction A fundamental problem in recognition is pose estimation. Given a correspondence between some portions of an object model and some portions of an image, determine the transformation th...

This thesis presents a methodology for scene reconstruction that is based on the principles of projective geometry, while dealing with uncertainty at a fundamental level. Uncertainty in geometric features is represented and manipulated using probability density functions on projective space, allowing geometric constructions to be carried out via statistical inference. The main contribution of this thesis is the development of stochastic projective geometry, a formalism for performing uncertain geometric reasoning during the scene reconstruction process. The homogeneous coordinates of points and lines in the projective plane are represented by antipodal pairs of points on the unit sphere, and geometric uncertainty in their location is represented...

Abstract-This paper investigates a fundamental problem of determining the position and orientation of a three-dimensional (3-D) object using single perspective image view. The technique is focused on the interpretation of trihedral angle constraint information. A new closed from solution based on Kanatani’s formulation is proposed. The main distinguishing feature of our method over the original Kanatani’s formulation is that our approach gives an effective closed form solution for general trihedral angle constraint. The method also provides a general analytic technique for dealing with a class of problem of shape from inverse perspective projection by using “Angle to Angle Correspondence Information. ” A detailed implementation of our technique is presented. Different trihedral angle configurations were generated using synthetic data for testing our approach of finding object orientation by angle to angle constraint. We performed simulation experiments by adding some noise to the synthetic data for evaluating the effectiveness of our method in real situation. It has been found that our method worked effectively in a noisy environment which confirms that the method is robust in practical application. Index Terms-Shape from angle, shape from perspective pro-jection, pose estimation, extrinsic camera calibration, 3-D object recognition. I.

Model-based object recognition commonly involves using a minimal set of matched model and image points to compute the pose of the model in image coordinates. Furthermore, recognition systems often rely on the "weak-perspective" imaging model in place of the perspective imaging model. This paper discusses computing the pose of a model from three corresponding points under weak-perspective projection. A new solution to the problem is proposed which, like previous solutions, involves solving a biquadratic equation. Here the biquadratic is motivated geometrically and its solutions, comprised of an actual and a false solution, are interpreted graphically. The final equations take a new form, which lead to a simple expression for the image position of any unmatched model point.

AbstractÐWe have recently proposed an approach to recognition that uses regions to determine the pose of objects while allowing for partial occlusion of the regions. Regions introduce an attractive alternative to existing global and local approaches, since, unlike global features, they can handle occlusion and segmentation errors, and unlike local features they are not as sensitive to sensor errors, and they are easier to match. The region-based approach also uses image information directly, without the construction of intermediate representations, such as algebraic descriptions, which may be difficult to reliably compute. In this paper, we further analyze properties of the method for planar objects undergoing projective transformations. In particular, we prove that three visible regions are sufficient to determine the transformation uniquely and that for a large class of objects, two regions are insufficient for this purpose. However, we show that when several regions are available, the pose of the object can generally be recovered even when some or all regions are significantly occluded. Our analysis is based on investigating the flow patterns of points under projective transformations in the presence of fixed points. Index TermsÐObject recognition, pose estimation with regions. 1

We address the problem of recognizing free-form 3D objects from a single 2D intensity image. A model-based solution within the alignment paradigm is presented which involves three major schemes -- modeling, matching, and indexing. The modeling scheme constructs a set of model aspects which can predict the object contour as seen from any viewpoint. The matching scheme aligns the edgemap of a candidate model to the observed edgemap using an initial approximate pose. The major contribution of this paper involves the indexing scheme and its integration with modeling and matching to perform recognition. Indexing generates hypotheses specifying both candidate model aspects and approximate pose and scale. Hypotheses are ordered by likelyhood based on prior knowledge of pre-stored models and the visual evidence from the observed objects. A prototype implementation has been tested in recognition and localization experiments with a database containing 658 model aspects from 20 3D objects and 80 ...

This paper presents a novel approach to parts-based object recognition in the presence of occlusion. We focus on the problem of determining the pose of a 3-D object from a single 2-D image when convex parts of the object have been matched to corresponding regions in the image. We consider three types of occlusions: self-occlusion, occlusions whose locus is identified in the image, and completely arbitrary occlusions. We show that in the first two cases this is a convex optimization problem, derive efficient algorithms, and characterize their performance. For the last case, we prove that the problem of finding valid poses is computationally hard, but provide an efficient, approximate algorithm. This work generalizes our previous work on region-based object recognition, which focused on the case of planar models. This research was supported by the Unites States-Israel Binational Science Foundation, Grant No. 94-100. The vision group at the Weizmann Inst. is supported in part by...

This paper deals with the interpretation of line drawings of Origami scenes (Kanade, 1980), that is scenes obtained by assembling planar panels of negligible thickness, and it addresses the computational complexity of the problem of consistently assigning suitable labels to the segments describing 3D properties as convexity, concavity and occlusion (labeling problem). The main results of the paper are the following: (a) the labeling problem for line drawings of Origami scenes is NP-complete, as for the case of trihedral scenes; (b) the problem remains NP-complete even if the location of the vanishing points in the image plane is given, whereas for trihedral scenes the problem was polynomially solvable; (c) in case the vanishing points are known the labeling problem can be subdivided into two subproblems, the paneling problem and the labeling-a-paneled-line-drawing problem which are both polynomially solvable. The approach provides geometrical constraints which help select `natural' in...