Object recognition and localization from 3D point clouds by maximum-likelihood estimation
Open Access
- 16 August 2017
- journal article
- research article
- Published by The Royal Society in Royal Society Open Science
- Vol. 4 (8) , 160693
Abstract
We present an algorithm based on maximum-likelihood analysis for the automated recognition of objects, and estimation of their pose, from 3D point clouds. Surfaces segmented from depth images are used as the features, unlike ‘interest point’-based algorithms which normally discard such data. Compared to the 6D Hough transform, it has negligible memory requirements, and is computationally efficient compared to iterative closest point algorithms. The same method is applicable to both the initial recognition/pose estimation problem as well as subsequent pose refinement through appropriate choice of the dispersion of the probability density functions. This single unified approach therefore avoids the usual requirement for different algorithms for these two tasks. In addition to the theoretical description, a simple 2 degrees of freedom (d.f.) example is given, followed by a full 6 d.f. analysis of 3D point cloud data from a cluttered scene acquired by a projected fringe-based scanner, which demonstrated an RMS alignment error as low as 0.3 mm.Keywords
Funding Information
- Engineering and Physical Sciences Research Council (EP/K018124/1)
This publication has 26 references indexed in Scilit:
- 50 Years of object recognition: Directions forwardComputer Vision and Image Understanding, 2013
- Maximum-likelihood image matchingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- A Continuous Probabilistic Framework for Image MatchingComputer Vision and Image Understanding, 2001
- Error-reduction methods for shape measurement by temporal phase unwrappingJournal of the Optical Society of America A, 1997
- Using generative models for handwritten digit recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Invariant surface characteristics for 3D object recognition in range imagesComputer Vision, Graphics, and Image Processing, 1986
- Three-dimensional object recognitionACM Computing Surveys, 1985
- Model-Based Recognition and Localization from Sparse Range or Tactile DataThe International Journal of Robotics Research, 1984
- Random sample consensusCommunications of the ACM, 1981
- Use of the Hough transformation to detect lines and curves in picturesCommunications of the ACM, 1972