Open AccessBook
Reverse engineering regular objects: simple segmentation and surface fitting procedures. (Research report of Geometric Modelling Laboratory, GML 1997/3.)
Tamás Várady,Pál Benkő,Géza Kós +2 more
- 01 Jan 1997
31
TL;DR: A non-iterative algorithm for direct segmentation is presented, where well-known techniques from computer vision are combined with new procedures for processing point and normal vector data, based on laser scanned point clouds with relatively high density and high accuracy.
read more
Abstract: Segmenting point clouds and fitting surfaces onto subsets of measured data are crucial elements of reverse engineering algorithms. Due to the variety in data acquisition procedures and the requirements concerning the representation of the model to be created there are several methods to approach this problem. Our current interest is to construct exact, 'watertight' boundary representation models of regular objects, based on laser scanned point clouds with relatively high density and high accuracy. After defining the term 'regular object', a non-iterative algorithm for direct segmentation is presented, where well-known techniques from computer vision are combined with new procedures for processing point and normal vector data. These include the separation of primary surfaces and transition elements, special filtering methods according to planarity and dimensionality and the detection of simple analytic surface types.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Chapter 26 – Reverse Engineering
Tamás Várady,Ralph R. Martin +1 more
- 01 Jan 2002
TL;DR: This chapter summarizes a representative set of algorithms that explain the way reverse engineering can be carried out by describing the way point data may be captured from an object and the way points from multiple views may be merged to form a single point cloud.
67
Methods to recover constant radius rolling ball blends in reverse engineering
TL;DR: The purpose of the current investigation is to present and compare algorithms for recovering constant radius rolling ball blends, the most widely used class of constant-radius rolling ball blended surfaces, due to their simplicity and intuitive behaviour.
58
3D shape recognition and reconstruction based on line element geometry
Michael Hofer,Boris Odehnal,Helmut Pottmann,Tibor Steiner,Johannes Wallner +4 more
- 17 Oct 2005
TL;DR: Line element geometry, which generalizes both line geometry and the Laguerre geometry of oriented planes, enables us to recognize a wide class of surfaces, by fitting linear subspaces in an appropriate seven-dimensional image space.
Reconstruction of piecewise planar objects from point clouds
Martin Peternell,Tibor Steiner +1 more
TL;DR: The main geometric features of a modeling system which are the detection of planar faces and the generation of a cad model are presented and applied to the problem of reconstruction of buildings from airborne laser scanner data.
An evolutionary approach to the extraction of object construction trees from 3D point clouds
TL;DR: An evolutionary algorithm that evolves set-theoretic expressions made of primitives fitted to the input point-set and modeling operations is presented, which uses a penalty term in the objective function optimized by the evolutionary algorithm.
References
Reverse engineering of geometric models—an introduction
TL;DR: Specific issues addressed include characterization of geometric models and related surface representations, segmentation and surface fitting for simple and free-form shapes, multiple view combination and creating consistent and accurate B-rep models.
1.3K
Segmentation through variable-order surface fitting
Paul J. Besl,Ramesh Jain +1 more
TL;DR: A piecewise-smooth surface model for image data that possesses surface coherence properties is used to develop an algorithm that simultaneously segments a large class of images into regions of arbitrary shape and approximates image data with bivariate functions so that it is possible to compute a complete, noiseless image reconstruction based on the extracted functions and regions.
An experimental comparison of range image segmentation algorithms
Adam Hoover,G. Jean-Baptiste,Xiaoyi Jiang,Patrick J. Flynn,Horst Bunke,Dmitry B. Goldgof,Kevin W. Bowyer,D. W. Eggert,Andrew Fitzgibbon,Robert B. Fisher +9 more
TL;DR: A methodology for evaluating range image segmentation algorithms and four research groups have contributed to evaluate their own algorithm for segmenting a range image into planar patches.
926
On three-dimensional surface reconstruction methods
Ruud M. Bolle,Baba C. Vemuri +1 more
TL;DR: A survey is presented of some of the surface reconstruction methods that can be found in the literature; the focus is on a small, recent, and important subset of the published reconstruction techniques.
315
Algorithms for reverse engineering boundary representation models
Pál Benkő,Ralph R. Martin,Tamás Várady +2 more
- 14 Sep 2001
TL;DR: A procedure for reconstructing solid models of conventional engineering objects from a multiple-view, 3D point cloud is described, with emphasis on producing accurate and topologically consistent boundary representation models, ready to be used in computer aided design and manufacture.