Finding Planes in LiDAR Point Clouds for Real-Time Registration

Finding Planes in LiDAR Point Clouds for Real-Time Registration. Grant, W‥, Voorhies, R‥, & Itti, L. In Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Nov, 2013.
abstract bibtex

We present a robust plane finding algorithm that when combined with plane-based frame-to-frame registration gives accurate real-time pose estimation. Our plane extraction is capable of handling large and sparse datasets such as those generated from spinning multi-laser sensors such as the Velodyne HDL-32E LiDAR. We test our algorithm on frame-to-frame registration in a closed-loop indoor path comprising 827 successive 3D laser scans (over 57 million points), using no additional information (e.g., odometry, IMU). Our algorithm outperforms, in both accuracy and time, three state-of-the-art methods, based on iterative closest point (ICP), plane-based randomized Hough transform, and planar region growing.

@inproceedings{ Grant_etal13iros,
  author = {W.S. Grant and R.C. Voorhies and L. Itti},
  title = {Finding Planes in LiDAR Point Clouds for Real-Time Registration},
  abstract = {We present a robust plane finding algorithm that when combined with
          plane-based frame-to-frame registration gives accurate real-time
          pose estimation.  Our plane extraction is capable of handling large
          and sparse datasets such as those generated from spinning multi-laser sensors such as the Velodyne HDL-32E
          LiDAR.  We test our algorithm on frame-to-frame registration
          in a closed-loop indoor path comprising 827 successive 3D laser
          scans (over 57 million points), using no additional information
          (e.g., odometry, IMU). Our algorithm outperforms, in both accuracy
          and time, three state-of-the-art methods, based on iterative closest
          point (ICP), plane-based randomized Hough transform, and planar
          region growing.},
  booktitle = {Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year = {2013},
  month = {Nov},
  review = {full/conf},
  type = {bb},
  if = {2013 acceptance rate: 43%}
}

Downloads: 0

{"_id":{"_str":"5298a1a19eb585cc26000917"},"__v":0,"authorIDs":[],"author_short":["Grant, W‥","Voorhies, R‥","Itti, L."],"bibbaseid":"grant-voorhies-itti-findingplanesinlidarpointcloudsforrealtimeregistration-2013","bibdata":{"html":"<div class=\"bibbase_paper\"> \n\n\n<span class=\"bibbase_paper_titleauthoryear\">\n\t<span class=\"bibbase_paper_title\"><a name=\"Grant_etal13iros\"> </a>Finding Planes in LiDAR Point Clouds for Real-Time Registration.</span>\n\t<span class=\"bibbase_paper_author\">\nGrant, W‥; Voorhies, R‥; and Itti, L.</span>\n\t\n</span>\n\n\n\nIn\n<i>Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)</i>, Nov 2013.\n\n\n\n\n\n<br class=\"bibbase_paper_content\"/>\n\n<span class=\"bibbase_paper_content\">\n \n \n \n <a href=\"javascript:showBib('Grant_etal13iros')\"\n class=\"bibbase link\">\n \n\t\n\t\n\t\n BibTeX\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n  \n <a class=\"bibbase_abstract_link bibbase link\"\n href=\"javascript:showAbstract('Grant_etal13iros')\">\n Abstract\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n \n\n \n \n \n</span>\n\n<div class=\"well well-small bibbase\" id=\"bib_Grant_etal13iros\"\n style=\"display:none\">\n <pre>@inproceedings{ Grant_etal13iros,\n author = {W.S. Grant and R.C. Voorhies and L. Itti},\n title = {Finding Planes in LiDAR Point Clouds for Real-Time Registration},\n abstract = {We present a robust plane finding algorithm that when combined with\n plane-based frame-to-frame registration gives accurate real-time\n pose estimation. Our plane extraction is capable of handling large\n and sparse datasets such as those generated from spinning multi-laser sensors such as the Velodyne HDL-32E\n LiDAR. We test our algorithm on frame-to-frame registration\n in a closed-loop indoor path comprising 827 successive 3D laser\n scans (over 57 million points), using no additional information\n (e.g., odometry, IMU). Our algorithm outperforms, in both accuracy\n and time, three state-of-the-art methods, based on iterative closest\n point (ICP), plane-based randomized Hough transform, and planar\n region growing.},\n booktitle = {Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},\n year = {2013},\n month = {Nov},\n review = {full/conf},\n type = {bb},\n if = {2013 acceptance rate: 43%}\n}</pre>\n</div>\n\n\n<div class=\"well well-small bibbase\" id=\"abstract_Grant_etal13iros\"\n style=\"display:none\">\n We present a robust plane finding algorithm that when combined with plane-based frame-to-frame registration gives accurate real-time pose estimation. Our plane extraction is capable of handling large and sparse datasets such as those generated from spinning multi-laser sensors such as the Velodyne HDL-32E LiDAR. We test our algorithm on frame-to-frame registration in a closed-loop indoor path comprising 827 successive 3D laser scans (over 57 million points), using no additional information (e.g., odometry, IMU). Our algorithm outperforms, in both accuracy and time, three state-of-the-art methods, based on iterative closest point (ICP), plane-based randomized Hough transform, and planar region growing.\n</div>\n\n\n</div>\n","downloads":0,"bibbaseid":"grant-voorhies-itti-findingplanesinlidarpointcloudsforrealtimeregistration-2013","role":"author","year":"2013","type":"bb","title":"Finding Planes in LiDAR Point Clouds for Real-Time Registration","review":"full/conf","month":"Nov","key":"Grant_etal13iros","if":"2013 acceptance rate: 43%","id":"Grant_etal13iros","booktitle":"Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","bibtype":"inproceedings","bibtex":"@inproceedings{ Grant_etal13iros,\n author = {W.S. Grant and R.C. Voorhies and L. Itti},\n title = {Finding Planes in LiDAR Point Clouds for Real-Time Registration},\n abstract = {We present a robust plane finding algorithm that when combined with\n plane-based frame-to-frame registration gives accurate real-time\n pose estimation. Our plane extraction is capable of handling large\n and sparse datasets such as those generated from spinning multi-laser sensors such as the Velodyne HDL-32E\n LiDAR. We test our algorithm on frame-to-frame registration\n in a closed-loop indoor path comprising 827 successive 3D laser\n scans (over 57 million points), using no additional information\n (e.g., odometry, IMU). Our algorithm outperforms, in both accuracy\n and time, three state-of-the-art methods, based on iterative closest\n point (ICP), plane-based randomized Hough transform, and planar\n region growing.},\n booktitle = {Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},\n year = {2013},\n month = {Nov},\n review = {full/conf},\n type = {bb},\n if = {2013 acceptance rate: 43%}\n}","author_short":["Grant, W‥","Voorhies, R‥","Itti, L."],"author":["Grant, W.S.","Voorhies, R.C.","Itti, L."],"abstract":"We present a robust plane finding algorithm that when combined with plane-based frame-to-frame registration gives accurate real-time pose estimation. Our plane extraction is capable of handling large and sparse datasets such as those generated from spinning multi-laser sensors such as the Velodyne HDL-32E LiDAR. We test our algorithm on frame-to-frame registration in a closed-loop indoor path comprising 827 successive 3D laser scans (over 57 million points), using no additional information (e.g., odometry, IMU). Our algorithm outperforms, in both accuracy and time, three state-of-the-art methods, based on iterative closest point (ICP), plane-based randomized Hough transform, and planar region growing."},"bibtype":"inproceedings","biburl":"http://ilab.usc.edu/publications/src/ilab.bib","downloads":0,"search_terms":["finding","planes","lidar","point","clouds","real","time","registration","grant","voorhies","itti"],"title":"Finding Planes in LiDAR Point Clouds for Real-Time Registration","year":2013,"dataSources":["wedBDxEpNXNCLZ2sZ"]}