A 3D Sequential LiDAR Data Registration Method for Unmanned Ground Vehicle

Abstract:

This paper proposes a 3D point cloud registration method based on light detection and ranging (LiDAR) system. The proposed method consists of three steps: Gaussian-Process based ground segmentation, a novel k-neighbors based dynamic point feature and Iterative Closest Point (ICP) fine registration. The first two steps are the preparation of ICP fine registration. The odometry information from a GPS/IMU system is used to compensate the vehicle's ego-motion. The Gaussian-Process based ground segmentation is adopted to remove ground points. A novel Initial Localization based Dynamic Feature (ILDF) is proposed to detect and remove dynamic points. It is applicable in sequential frames and a proper initial localization without a large dislocation. In experiment results, a large number of dynamic points will be detected and removed by ILDF. The removal of dynamic points improves both accuracy and efficiency of registration algorithm.

• Periodical: Applied Mechanics and Materials (Volume 664)
• Pages: 365-370
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.664.365
• Online since: October 2014
• Authors: Chao Chen*, Yan Li, Wei Wang
• Keywords: Dynamic Points, Ground Segmentation, ICP, Point Clouds, Registration

References

[1] P. Besl and N. McKay: A method for registration of 3-D shapes, IEEE Trans. Pattern Anal. Machine Intell. Vol. 14(2), 1992, p.239–256.

DOI: 10.1109/34.121791

[2] Y. Chen and G. Medioni: Object modelling by registration of multiple range images, , Image and vision computing. Vol. 10(3), 1992, pp.145-155.

DOI: 10.1016/0262-8856(92)90066-c

[3] M. Magnusson, A. Lilienthal and T. Duckett: Scan registration for autonomous mining vehicles using 3D-NDT, Journal of Field Robotics. Vol. 24(10), 2007, pp.803-827.

DOI: 10.1002/rob.20204

[4] S. Rusinkiewicz and M. Levoy: Efficient variants of the ICP algorithm, In Third International Conference on 3D Digital Imaging and Modeling, 2001, pp.145-152.

DOI: 10.1109/im.2001.924423

[5] R. Rusu, N. Blodow and M. Beetz: Fast point feature histograms (FPFH) for 3D registration, , IEEE International Conference on Robotics and Automation (ICRA), 2009, pp.3212-3217.

DOI: 10.1109/robot.2009.5152473

[6] A. Johnson, Spin-Images: A representation for 3-D surface matching, Ph.D. dissertation, Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, (1997).

[7] B. Steder, R. B. Rusu, K. Konolige and W. Burgard: NARF: 3D range image features for object recognition, , in Workshop on Defining and Solving Realistic Perception Problems in Personal Robotics at the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), (2010).

DOI: 10.1109/icra.2011.5980187

[8] A. Frome, D. Huber, R. Kolluri, T. Blow, and J. Malik: Recognizing objects in range data using regional point descriptors, , Proceedings of the European Conference on Computer Vision (ECCV), 2004, pp.356-369.

DOI: 10.1007/978-3-540-24672-5_18

[9] Zhang, L.: Line Primitives and Their Applications in Geometric Computer Vision, Universitätsbibliothek Kiel, (2013).

[10] Xiao, J.: Planar Segments Based Three-dimensional Robotic Mapping in Outdoor Environments, (2013).

[11] C. Tongtong, D. Bin, L. Daxue, Z. Bo and L. Qixu: 3d lidar-based ground segmentation, in 2011 First Asian Conference on Pattern Recognition (ACPR), Beijing, China, 2011, p.446–450.

DOI: 10.1109/acpr.2011.6166587

[12] B. Douillard, J. Underwood, N. Kuntz, V. Vlaskine, A. Quadros, P. Morton, and A. Frenkel, On the segmentation of 3d lidar point clouds, IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China, May 2011, p.2798–2805.

DOI: 10.1109/icra.2011.5979818

[13] T. Foley and J. Sugerman: KD-tree acceleration structures for a GPU raytracer, In Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware, 2005, pp.15-22.

DOI: 10.1145/1071866.1071869

[14] Kalman, R.E.: A new approach to linear filtering and prediction problems, , Journal of basic Engineering, Vol. 82(1), 1960, pp.35-45.

DOI: 10.1115/1.3662552