基于体密度变化率的点云多平面检测算法

doi:10.3724/SP.J.1087.2013.01411

计算机应用 ›› 2013, Vol. 33 ›› Issue (05): 1411-1419.DOI: 10.3724/SP.J.1087.2013.01411

基于体密度变化率的点云多平面检测算法

储珺,吴侗,王璐

南昌航空大学计算机视觉研究所，南昌 330063

收稿日期:2012-11-12 修回日期:2012-12-30 出版日期:2013-05-01 发布日期:2013-05-08
通讯作者: 储珺
作者简介:储珺(1967-),女，江苏宜兴人，教授，博士生导师，博士，主要研究方向：图像处理、机器人视觉、模式识别；吴侗(1985-),男，河北唐山人，硕士研究生，主要研究方向：模式识别、三维重建；王璐(1984-),女，湖北黄冈人，助教，硕士，主要研究方向：图像处理、模式识别。
基金资助:
国家自然科学基金资助项目(61263046);江西省科技计划项目(2009BGB03200)

Multi-plane detection algorithm of point clouds based on volume density change rate

CHU Jun,WU Tong,WANG Lu

Institute of Computer Vision, Nanchang Hangkong University, Nanchang Jiangxi 330063, China

Received:2012-11-12 Revised:2012-12-30 Online:2013-05-08 Published:2013-05-01
Contact: CHU Jun

摘要/Abstract

摘要： 针对以往点云多平面检测算法运算时间长、检测结果的准确性易受噪声影响这一问题，提出了一种基于点云几何统计特征的多平面检测算法。该方法首先根据体密度变化率对点云进行粗分割，然后利用多元随机抽样一致性算法(Multi-RANSAC)进行多平面拟合，最后提出了一种新的合并约束条件对拟合的初始平面进行优化合并。实验结果证明，该算法易于实现，能有效减少累积噪声对检测结果的影响，提高平面检测的正确率，极大地减少了计算时间开销。

关键词: 平面检测, 点云分割, 随机抽样一致性算法, 平面拟合, 体密度

Abstract: Most existing methods for detecting plane in point cloud cost long operation time, and the result of detection is susceptible to noise. To address these problems, this paper put forward a kind of multi-plane detection algorithm based on geometric statistical characteristics of the point clouds. The proposed method coarsely segmented point clouds according to the change rate of the volume density firstly, then used the Multi-RANSAC to fit planes, at last the authors proposed a new merge-constraint condition to combine and optimize the initial fitted planes. The experimental results show that the method in this paper is easy to realize, can effectively reduce the influence of cumulative noise to the detection results, improve the plane detection accuracy and also greatly reduce the computing time.

Key words: plane detection, point cloud segmentation, RANdom SAmple Consensus (RANSAC), plane fitting, volume density

中图分类号:

TP391.41

储珺吴侗王璐. 基于体密度变化率的点云多平面检测算法[J]. 计算机应用, 2013, 33(05): 1411-1419.

CHU Jun WU Tong WANG Lu. Multi-plane detection algorithm of point clouds based on volume density change rate[J]. Journal of Computer Applications, 2013, 33(05): 1411-1419.

参考文献

［1］BOYKOV Y, VEKSLER O, ZABIH R. Fast approximate energy minimization via graph cuts ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(11): 1222-1239.

［2］WANG Z L, CAI B G, YI F Z, et al. Reviews on planar region detection for visual navigation of mobile robot under unknown environment ［J］. Automation and Robotics, 2012, 123(2): 593-601.

［3］POPPINGA J, VASKEVICIUS N, BIRK A, et al.Fast plane detection and polygonalization in noisy 3D range image ［C］// IROS 2008: IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway: IEEE, 2008: 3378-3383.

［4］GALLUP D,FRAHM J,POLLEFEYS M. Piecewise planar and nonplanar stereo for urban scene reconstruction ［C］// 2010 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2010: 1418-1425.

［5］JOCHEM A, HOFLE B, RUTZINGER M,et al.Automatic roof plane detection and analysis in airborne LiDAR point clouds for solar potential assessment ［J］. Sensors, 2009, 9(7): 5241-5262.

［6］XIAO J, ZHANG J H, ZHANG J W. Fast plane detection for SLAM from noisy range images in both structured and unstructured environments ［C］// 2011 International Conference on Mechatronics and Automation. Piscataway: IEEE, 2011: 1768-1773.

［7］DESCHAUD J E, GOULETTE F. A fast and accurate plane detection algorithm for large noisy point clouds using filtered normals and voxel growing ［EB/OL］.［2012-10-02］.http://campwww.informatik.tu-muenchen.de/3DPVT2010/data/media/e-proceeding/papers/paper111.pdf.

［8］FISCHLER M A, BOLLES R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography ［J］. Communications of the Association for Computing Machinery, 1981, 24(6): 381-395.

［9］SCHNABEL R, WAHL R, KLEIN R. Efficient RANSAC for point-cloud shape detection ［J］.Computer Graphics Forum, 2007, 26(2): 214-226.

［10］YANG M Y, FORETNER W. Plane detection in point cloud data ［C］// Proceedings of the 2nd International Conference on Machine & Control Guidance. Bonn: Institue für Geodsie and Geoinformation Universitt Bonn, 2010: 95-104.
［11］DUDA R O, HART P E. Use of the Hough transformation to detect lines and curves in pictures ［R］. Menlo Park, California,USA: SRI International Artificial Intelligence Center, 1971.

［12］KIRYATI N, ELDAR Y, BRUCKSTEIN A M. A probabilistic Hough transform ［J］. Pattern Recognition, 1991, 24(4): 303-316.

［13］CENSI A, CARPIN S. HSM3D: Feature-less global 6DOF scan-matching in the Hough/Radon domain ［C］//

ICRA'09: Proceedings of the 2009 IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 2009: 3899-3906.

［14］ZAHARIA T, PRETEUX F. Shape-based retrieval of 3D mesh models ［C］// Proceedings of the 2002 IEEE International Conference on Multimedia and Expo. Piscataway: IEEE, 2002, 1: 437-440.

［15］BORRMANN D, ELSEBERG J, LINGEMANN K, et al. The 3D Hough transform for plane detection in point clouds: a review and new accumulator design ［J］. 3D Research, 2011, 2(3): 1-13.

［16］YL-JSKI A, KIRYATI N. Adaptive termination of voting in the probabilistic circular Hough transform ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(9): 911-915.

［17］TARSHA-KURDI F, LANDES T, GRUSSENMEYER P. Hough transform and extended RANSAC algorithms for automatic detection of 3D building roof planes from LiDAR data ［C］// ISPRS Proceedings of Workshop Laser scanning, 2007. Espoo, Finland: HAL-CCSD, 2007, XXXVI(1): 407-412.

［18］ZULIANI M, KENNEY C, MANJUNATH B. The multi-RANSAC algorithm and its application to detect planar homographies ［C］// International Conference on Image Processing. Piscataway: IEEE,2005:153-156.

［19］Institute of Computer Science, Knowledge-based Systems Research Group. Robotic 3D scan repository ［EB/OL］.［2012-10-17］. http://kos.informatik.uni-osnabrueck.de/3Dscans/.

［20］SNAVELY N. Bundler: Structure from Motion (SfM) for unordered image collections ［EB/OL］. ［2012-08-11］. http://phototour.cs.washington.edu/bundler/.

[1]	何传阳, 王平, 张晓华, 宋丹妮. 基于智能监控的中小人群异常行为检测[J]. 计算机应用, 2016, 36(6): 1724-1729.
[2]	张翔宇, 田庆国, 葛宝臻. 三维人体点云模型多约束肢体分割[J]. 计算机应用, 2015, 35(3): 830-834.
[3]	刘进. 自适应的基于点云的CAD模型重建方法[J]. 计算机应用, 2013, 33(09): 2617-2622.
[4]	薛振华王萍张楚涵蔡思佳. 图像匹配中去除误配的对抗性优化方法的改进[J]. 计算机应用, 2012, 32(11): 3157-3160.
[5]	曾晓奇· 董子龙章国锋华炜. 基于边的自适应实时三维跟踪[J]. 计算机应用, 2011, 31(01): 20-24.
[6]	曲天伟安波陈桂兰. 改进的RANSAC算法在图像配准中的应用[J]. 计算机应用, 2010, 30(07): 1849-1851.

基于体密度变化率的点云多平面检测算法

Multi-plane detection algorithm of point clouds based on volume density change rate

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics