Normal Distributions Transform. Benjamin Huhle1, Martin Magnusson2,. Wolfgang StraÃer1, Achim J. Lilienthal2. 1 WSI/GRIS, University of Tübingen, Germany.
Registration of Colored 3D Point Clouds with a Kernel-based Extension to the Normal Distributions Transform Benjamin Huhle1, Martin Magnusson2, Wolfgang Straßer1, Achim J. Lilienthal2 WSI/GRIS, University of Tübingen, Germany 2 AASS, Dept. of Technology, Örebro University, Sweden 1
05/23/2008 ICRA '08, Pasadena
Benjamin Huhle - WSI/GRIS, Tübingen
Motivation • point cloud registration for Localization & Mapping • Problems – geometric features (structure) required – small field-of-view – noise • additional color data available! 2
Outline of the talk • Related Work – Normal Distributions Transform (NDT) – Vision-aided registration (SIFT-Features) – Combined approach (SIFT-Features+NDT) • Color-NDT – straightforward approach fails – Kernel-based Color-NDT • Experiments – mobile robot with time-of-flight camera 3
Normal Distributions Transform (NDT) • Biber & Straßer, 2003 – cell grid – approximate point distributions – multiple overlapping grids – optimization using analytical (2nd order) derivatives
from: Biber, 2003
4
3D Normal Distributions Transform • in 3D
• comparison with ICP: Magnusson et al., 2007 5
Vision-Aided Registration
Andreasson & Lilienthal, 2007
• robust registration with image features (SIFT) – feature detection in images – lookup of 3D coordinates • challenges: – noise – dynamic environments from: Andreasson et al., 2007
6
Combined Energy Approach
Huhle, Jenke & Straßer, 2008
• Sum of NDT score and feature distances
• must favor features (small
) 7
Ad-hoc approach to using color with NDT • colored point cloud: [x,y,z,r,g,b] • 6D color–space distribution toy example: • 2D position • 1 colordimension (hue) • model is 3D normal distribution
8
Single-Mode Color–Space Distribution • conditional distributions of 2 test-points
9
Single-Mode Color–Space Distribution • ... for a test-point with different color
10
Kernel-Based Color-NDT • Gaussian mixture-model in color-space (EM-Algorithm) • components are weighting kernels for point distributions • use 3 kernels • for each kernel: compute spatial Normal Distribution using – weighted mean – weighted covariance 11
Toy Example revisited • perfect match of model and data
12
Toy Example revisited • ... test point with different color
13
Registration with Color-NDT • optimize score (mixture model of normal distributions) • Newton's method • translation + rotation vector (6D parameters)
14
Experiments • Time-of-flight camera – PMDTec 19k – 160x120 pixels – 30° fov – significant noise level • additional color camera
15
Results • 21 incrementally registered frames • odometry as initial poses
16
Results using combined approach SIFT only
• 11 frames
combined SIFT+NDT
combined SIFT+Color-NDT
17
Results using combined approach SIFT only
• 11 frames
combined SIFT+NDT
combined SIFT+Color-NDT
18
Results using combined approach SIFT only
• 11 frames
combined SIFT+NDT
combined SIFT+Color-NDT
19
Results using combined approach SIFT only
• 11 frames
combined SIFT+NDT
combined SIFT+ColorNDT
20
Conclusion • Color-NDT: – more robust/stable – more weight on Color-NDT score in combined approach – can fix inaccuracies of SIFT registration • towards registration of low-end sensor data with integrated use of color and depth data
21
Thank you for your attention! •
•
•
•
Peter Biber and Wolfgang Straßer. The Normal Distributions Transform: A New Approach to Laser Scan Matching. In Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 2743–2748, 2003 Martin Magnusson, Achim Lilienthal and Tom Duckett, Scan Registration for Autonomous Mining Vehicles Using 3D-NDT. Journal of Field Robotics, 24:10, 2007, pp. 803-827 Henrik Andreasson and Achim J. Lilienthal, Vision Aided 3D Laser Based Registration. Proceedings of the 3rd European Conference on Mobile Robots (ECMR), 2007 Benjamin Huhle, Philipp Jenke and Wolfgang Straßer. On-the-Fly Scene Acquisition with a Handy Multi-Sensor System. Int. J. of Intelligent Systems Technologies and Applications, to appear, 2008
22