No abstract

Aprocedure for reconstructing solid models of conventional engineering objects from a multiple-view, 3D point cloud is described. (Conventional means bounded by simple analytical surfaces, swept surfaces and blends.) Emphasis is put on producing accurate and topologically consistent boundary representation models, ready to be used in computer aided design and manufacture. The basic phases of our approach to reverse engineering are summarised, and related computational difficulties are analysed. Four key algorithmic components are presented in more detail: efficiently segmenting point data into regions; creating translational and rotational surfaces with smooth, constrained profiles; creating the topology of B-rep models; and finally adding blends. The application of these algorithms in an integrated system is illustrated by means of various examples, including a well-known reverse engineering benchmark.

This paper considers simultaneous fitting of multiple curves and surfaces to 3D measured data captured as part of a reverse engineering process, where constraints exist between the parameters of the curves or surfaces. Enforcing such constraints may be necessary (i) to produce models to sufficiently accurate tolerances for import into a CAD system, and (ii) to produce models which successfully reproduce regularities and symmetries required by engineering applications. The constraints to be satisfied may be determined manually, or more likely, by an automatic process. In the latter case, typically many more constraints are generated than can all be simultaneously satisfied. We present a new numerical method able to resolve conflicts between constraints. Secondly, reverse engineering generates large amounts of data. Constrained fitting methods are iterative in nature, and so an efficient method needs to restrict the amount of computation performed on each iteration. Our method achieves this through carefully constructed representations for objects and constraints, and approximations to distance functions. This paper describes our approach to constrained fitting, and illustrates its usefulness with some 2D and 3D examples taken from reverse engineering.