Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
175 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Fast and Robust Normal Estimation for Sparse LiDAR Scans (2404.14281v1)

Published 22 Apr 2024 in cs.RO and cs.CV

Abstract: Light Detection and Ranging (LiDAR) technology has proven to be an important part of many robotics systems. Surface normals estimated from LiDAR data are commonly used for a variety of tasks in such systems. As most of the today's mechanical LiDAR sensors produce sparse data, estimating normals from a single scan in a robust manner poses difficulties. In this paper, we address the problem of estimating normals for sparse LiDAR data avoiding the typical issues of smoothing out the normals in high curvature areas. Mechanical LiDARs rotate a set of rigidly mounted lasers. One firing of such a set of lasers produces an array of points where each point's neighbor is known due to the known firing pattern of the scanner. We use this knowledge to connect these points to their neighbors and label them using the angles of the lines connecting them. When estimating normals at these points, we only consider points with the same label as neighbors. This allows us to avoid estimating normals in high curvature areas. We evaluate our approach on various data, both self-recorded and publicly available, acquired using various sparse LiDAR sensors. We show that using our method for normal estimation leads to normals that are more robust in areas with high curvature which leads to maps of higher quality. We also show that our method only incurs a constant factor runtime overhead with respect to a lightweight baseline normal estimation procedure and is therefore suited for operation in computationally demanding environments.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. Voronoi-based variational reconstruction of unoriented point sets. In Proc. of the Eurographics Symp. on Geometry Processing, pages 39–48, 2007.
  2. N. Amenta and M. Bern. Surface reconstruction by voronoi filtering. Proc. Fourteenth Annual Symp. on Comp. Geom., pages 39–48, 1998.
  3. l11{}_{1}start_FLOATSUBSCRIPT 1 end_FLOATSUBSCRIPT-sparse reconstruction on sharp pointset surfaces. In ACM Trans. on Graphics (TOG), volume 29, 2010.
  4. Fast and accurate computation of surface normals from range images. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2011.
  5. J. Behley and C. Stachniss. Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments. In Proc. of Robotics: Science and Systems (RSS), 2018.
  6. Nesti-net: Normal estimation for unstructured 3d point clouds using convolutional neural networks. In Proc. of the IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pages 10104–10112, 2019.
  7. I. Bogoslavskyi and C. Stachniss. Fast range image-based segmentation of sparse 3d laser scans for online operation. In Proc. of the IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2016.
  8. I. Bogoslavskyi and C. Stachniss. Efficient Online Segmentation for Sparse 3D Laser Scans. Photogrammetrie – Fernerkundung – Geoinformation (PFG), 85(1):41–52, 2017.
  9. A. Boulch and R. Marlet. Deep learning for robust normal estimation in unstructured point clouds. Computer Graphics Forum, 35:281–290, 2016.
  10. Spatio-Temporal Non-Rigid Registration of 3D Point Clouds of Plants. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2020.
  11. Range Image-based LiDAR Localization for Autonomous Vehicles. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2021.
  12. Normal estimation for point clouds: A comparison study for a voronoi based method. In Proc. of the Eurographics Symp. on Geometry Processing, pages 39–46, 2005.
  13. Pcpnet: Learning local shape properties from raw point clouds. Computer Graphics Forum, 37(2):75–85, 2018.
  14. The hilti slam challenge dataset, 2021.
  15. Surface reconstruction from unorganized points. In Proc. of the Intl. Conf. on Computer Graphics and Interactive Techniques (SIGGRAPH), 1992.
  16. Normnet: Point-wise normal estimation network for three-dimensional point cloud data. Intl. Journal of Advanced Robotic Systems, 16, 2019.
  17. Deep iterative surface normal estimation. Proc. of British Machine Vision Conference (BMVC), pages 11244–11253, 2020.
  18. Robust normal estimation for point clouds with sharp features. Computer & Graphics, 34(2):94–106, 2010.
  19. Hsurf-net: Normal estimation for 3d point clouds by learning hyper surfaces. In Proc. of the Advances in Neural Information Processing Systems (NIPS), 2022.
  20. Low rank matrix approximation for 3d geometry filtering. IEEE Trans. on Visualization and Computer Graphics, 28(4):1835–1847, 2022.
  21. Mask-Based Panoptic LiDAR Segmentation for Autonomous Driving. IEEE Robotics and Automation Letters (RA-L), 8(2):1141–1148, 2023.
  22. N.J. Mitra and A. Nguyen. Estimating surface normals in noisy point cloud data. In Proc. of the Nineteeth Annual Symp. on Computation Geometry, pages 322–328, 2003.
  23. Unsupervised Class-Agnostic Instance Segmentation of 3D LiDAR Data for Autonomous Vehicles. IEEE Robotics and Automation Letters (RA-L), 7(4):8713–8720, 2022.
  24. Tele-operated lunar rover navigation using lidar. In Proc. of the Intl. Symp. on Artificial Intelligence, Robotics and Automation in Space (I-SAIRAS), 2012.
  25. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2017.
  26. Lidar applications in precision agriculture for cultivating crops: A review of recent advances. Computers and Electronics in Agriculture, 207:107737, 2023.
  27. A. Robinson and C. Cherry. Results of a prototype television bandwidth compression scheme. In Proceedings of the IEEE, volume 55, pages 356–364, 1967.
  28. Denoising point sets via l0subscript𝑙0l_{0}italic_l start_POSTSUBSCRIPT 0 end_POSTSUBSCRIPT minimization. Computer Aided Geometric Design, 35–36:2–15, 2015.
  29. Poisson Surface Reconstruction for LiDAR Odometry and Mapping. In Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA), 2021.
  30. KISS-ICP: In Defense of Point-to-Point ICP – Simple, Accurate, and Robust Registration If Done the Right Way. IEEE Robotics and Automation Letters (RA-L), 8(2):1029–1036, 2023.
  31. Deep point cloud normal estimation via triplet learning. In Proc. of the IEEE Intl. Conf. on Multimedia and Expo, 2022.
  32. Z. Wang and V. Prisacariu. Neighbourhood-insensitive point cloud normal estimation network. Proc. of British Machine Vision Conference (BMVC), 2020.
  33. Surface and normal ensembles for surface reconstruction. Computer-Aided Design, 39(5):408–420, 2007.
  34. Robust point cloud normal estimation via neighborhood reconstruction. Advances in Mechnical Engineering, 11(4), 2019.
  35. J. Zhang and S. Singh. LOAM: Lidar Odometry and Mapping in Real-time. In Proc. of Robotics: Science and Systems (RSS), 2014.
  36. Point cloud normal estimation via low-rank subspace clustering. Computer & Graphics, 37(6):697–706, 2013.
  37. Quality point cloud normal estimation by guided least squares representation. Computer & Graphics, 51:106–116, 2005.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now