The authors describe a general-purpose, representation-independent method for the accurate and computationally efficient registration of 3-D shapes including free-form curves and surfaces. The method handles the full six degrees of freedom and is based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point. The ICP algorithm always converges monotonically to the nearest local minimum of a mean-square distance metric, and the rate of convergence is rapid during the first few iterations. Therefore, given an adequate set of initial rotations and translations for a particular class of objects with a certain level of 'shape complexity', one can globally minimize the mean-square distance metric over all six degrees of freedom by testing each initial registration. One important application of this method is to register sensed data from unfixtured rigid objects with an ideal geometric model, prior to shape inspection. Experimental results show the capabilities of the registration algorithm on point sets, curves, and surfaces. >

A method for registration of 3-D shapes

We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face" and "nonface" model clusters. At each image location, a difference feature vector is computed between the local image pattern and the distribution-based model. A trained classifier determines, based on the difference feature vector measurements, whether or not a human face exists at the current image location. We show empirically that the distance metric we adopt for computing difference feature vectors, and the "nonface" clusters we include in our distribution-based model, are both critical for the success of our system.

/pdf/example-based-learning-for-view-based-human-face-detection-k0lbwr2rer.pdf

Example-based learning for view-based human face detection

https://www.cs.ubc.ca/~lowe/papers/aij87.pdf

Three-dimensional object recognition from single two-dimensional images

Model-based recognition and motion tracking depend upon the ability to solve for projection and model parameters that will best fit a 3-D model to matching 2-D image features. The author extends current methods of parameter solving to handle objects with arbitrary curved surfaces and with any number of internal parameters representing articulation, variable dimensions, or surface deformations. Numerical stabilization methods are developed that take account of inherent inaccuracies in the image measurements and allow useful solutions to be determined even when there are fewer matches than unknown parameters. The Levenberg-Marquardt method is used to always ensure convergence of the solution. These techniques allow model-based vision to be used for a much wider class of problems than was possible with previous methods. Their application is demonstrated for tracking the motion of curved, parameterized objects. >

/pdf/fitting-parameterized-three-dimensional-models-to-images-qh3tnmd54d.pdf

Fitting parameterized three-dimensional models to images

A general method for model-based object recognition in occluded scenes is presented. It is based on geometric hashing. The method stands out for its efficiency. We describe the general framework of the method and illustrate its applications for various recogni- tion problems both in 3-D and 2-D. Special attention is given to the recognition of 3-D objects in occluded scenes from 2-D gray scale images. New experimental results are included for this important case.

Geometric Hashing: A General And Efficient Model-based Recognition Scheme

This paper discusses how local measurements of three-dimensional positions and surface normals (recorded by a set of tactile sensors, or by three-dimensional range sensors), may be used to identify and locate objects from among a set of known objects. The objects are modeled as polyhedra having up to six degrees of freedom relative to the sensors. We show that inconsistent hypotheses about pairings between sensed points and object surfaces can be discarded efficiently by using local constraints on distances between faces, angles between face normals, and angles (relative to the surface normals) of vectors between sensed points. We show by simulation and by mathematical bounds that the number of hypotheses consistent with these constraints is small We also show how to recover the position and orientation of the object from the sensory data. The algorithm's performance on data obtained from a triangulation range sensor is illustrated.

/pdf/model-based-recognition-and-localization-from-sparse-range-1ioi2y3ibh.pdf

Model-based recognition and localization from sparse range or tactile data

This paper discusses how local measurements of three-dimensional positions and surface normals may be used to identify and locate objects, from among a set of known objects. The objects are modeled as polyhedra having up to six degrees of freedom relative to the sensors. We show that inconsistent hypotheses about pairings between sensed points and object surfaces can be discarded efficiently by using local constraints on: distances between faces, angles between face normals, and angles (relative to the surface normals) of vectors between sensed points. We show by simulation that the number of hypotheses consistent with these constraints is small. We also show how to recover the position and orientation of the object from the sense data. The algorithm's performance on data obtained from a triangulation range sensor is illustrated.

Model-Based Recognition and Localization from Sparse Range Data

Computational models of the human stereo system can provide insight into general information processing constraints that apply to any stereo system, either artificial or biological. In 1977, Marr and Poggio proposed one such computational model, that was characterized as matching certain feature points in difference-of-Gaussian filtered images, and using the information obtained by matching coarser resolution representations to restrict the search space for matching finer resolution representations. An implementation of the algorithm and its testing on a range of images was reported in 1980. Recent computational experiments applying the algorithm to a variety of natural images, especially aerial photographs, have led to a number of modifications. In this article, we present a version of the Marr-Poggio-Grimson algorithm that embodies these modifications, and is characterized as matching extended contours of feature points obtained from a range of different spatial frequency tuned channels. We illustrate its performance on a series of natural images.

W. Eric

Papers

Model-based recognition and localization from sparse range or tactile data

Model-Based Recognition and Localization from Sparse Range Data

Computing Stereopsis Using Feature Point Contour Matching