Point-plane SLAM for hand-held 3D sensors
Authors:
- 1 May 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10504729,p. 5182-5189
Abstract
We present a simultaneous localization and mapping (SLAM) algorithm for a hand-held 3D sensor that uses both points and planes as primitives. We show that it is possible to register 3D data in two different coordinate systems using any combination of three point/plane primitives (3 planes, 2 planes and 1 point, 1 plane and 2 points, and 3 points). Our algorithm uses the minimal set of primitives in a RANSAC framework to robustly compute correspondences and estimate the sensor pose. As the number of planes is significantly smaller than the number of points in typical 3D data, our RANSAC algorithm prefers primitive combinations involving more planes than points. In contrast to existing approaches that mainly use points for registration, our algorithm has the following advantages: (1) it enables faster correspondence search and registration due to the smaller number of plane primitives; (2) it produces plane-based 3D models that are more compact than point-based ones; and (3) being a global registration algorithm, our approach does not suffer from local minima or any initialization problems. Our experiments demonstrate real-time, interactive 3D reconstruction of indoor spaces using a hand-held Kinect sensor.Keywords
This publication has 29 references indexed in Scilit:
- A Theory of Minimal 3D Point to 3D Plane Registration and Its GeneralizationInternational Journal of Computer Vision, 2012
- iSAM2: Incremental smoothing and mapping using the Bayes treeThe International Journal of Robotics Research, 2011
- Efficient RANSAC for Point‐Cloud Shape DetectionComputer Graphics Forum, 2007
- Unbiased estimation and statistical analysis of 3-D rigid motion from two viewsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- Estimating 3-D location parameters using dual number quaternionsCVGIP: Image Understanding, 1991
- Pose determination from line-to-plane correspondences: existence condition and closed-form solutionsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Least-squares estimation of transformation parameters between two point patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Determining motion from 3D line segment matches: a comparative studyImage and Vision Computing, 1991
- Closed-form solution of absolute orientation using unit quaternionsJournal of the Optical Society of America A, 1987