Using Extended EM to Segment Planar Structures in 3D

Authors:
Rolf Lakaemper;Longin Jan Latecki
Affiliations:
Temple University, Philadelphia,PA,USA;Temple University, Philadelphia,PA,USA
Venue:
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Year:
2006

Citing 0
Cited 7

3D Perception and Environment Map Generation for Humanoid Robot Navigation

International Journal of Robotics Research
Categorizing Perceptions of Indoor Rooms Using 3D Features

SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
A computational model for the alignment of hierarchical scene representations in human-robot interaction

IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Simultaneous multi-line-segment merging for robot mapping using mean shift clustering

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
A novel hierarchical technique for range segmentation of large building exteriors

ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part II
Robust estimation of planar surfaces using spatio-temporal RANSAC for applications in autonomous vehicle navigation

Robotics and Autonomous Systems
Three-dimensional point cloud plane segmentation in both structured and unstructured environments

Robotics and Autonomous Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The proposed algorithm segments planar structures out of data gained from 3D laser range scanners, typically used in robotics. The approach first fits planar patches to the dataset, using a new, extended Expectation Maximization (EM) algorithm. This algorithm solves the classical EM problems of insufficient initialization by iteratively determining the number and positions of patches in a split and merge framework. Determining the fitting quality of the gained patches, the approach then allows for segmentation of planar surfaces out of the 3D environment. The result is a set of 2D objects, which can be used as input for classical computer vision applications, in particular for object recognition. Our approach makes it possible to apply classical tools of 2D image processing to solve problems of 3D robot mapping, e.g. landmark recognition.