首页 > 论文 > 光学学报 > 40卷 > 20期(pp:2015001--1)

基于分层墨卡托投影的激光雷达点云数据局部特征描述

Local Feature Description of LiDAR Point Cloud Data Based on Hierarchical Mercator Projection

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为了高效提取激光雷达点云数据的局部几何结构特征,实现三维(3D)目标的配准、检测和识别,提出了一种基于分层墨卡托投影(HMec)的局部点云特征描述子。首先,采用传统方法进行特征提取;然后,利用具有保角特性的墨卡托投影,将3D点云数据的局部邻域点分层投影到多个墨卡托平面上;最后,分别统计各墨卡托平面的分布直方图,得到特征点的局部特征描述子。HMec特征描述子能很好地保留点云的局部几何结构特征,从而提高特征描述子的辨别力。在Bologna和3DMatch数据集上的测试结果表明,相比其他9种局部特征描述子,HMec特征描述子的辨别力更强、噪声鲁棒性更好。

Abstract

In order to efficiently extract the local geometric structure features of LiDAR point cloud data and realize the registration, detection and recognition of three-dimensional (3D) targets, a local point cloud feature descriptor based on hierarchical Mercator projection (HMec) is proposed in this paper. First, the traditional method is used for feature extraction. Then, the local neighborhood points of 3D point cloud data are projected onto multiple Mercator planes using the Mercator projection with conformal feature. Finally, the local feature descriptors of feature points are obtained by counting the histogram of each Mercator plane. HMec feature descriptor can retain the local geometric structure features of point cloud, so as to improve the discrimination of feature descriptor. The test results on Bologna and 3DMatch datasets show that HMec feature descriptors have stronger discrimination and better noise robustness than the other nine local feature descriptors

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TN249

DOI:10.3788/AOS202040.2015001

所属栏目:机器视觉

收稿日期:2020-05-13

修改稿日期:2020-07-06

网络出版日期:2020-10-01

作者单位    点击查看

顾尚泰:中国人民解放军国防科技大学电子科学学院, 湖南 长沙 410073
王玲:中国人民解放军国防科技大学电子科学学院, 湖南 长沙 410073
马燕新:中国人民解放军国防科技大学气象海洋学院, 湖南 长沙 410073
马超:中国人民解放军国防科技大学电子科学学院, 湖南 长沙 410073

联系人作者:顾尚泰(shangtai_gu@163.com); 王玲(wanglanne@139.com);

【1】Aldoma A, Vincze M, Blodow N, et al. CAD-model recognition and 6DOF pose estimation using 3D cues . [C]∥2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), November 6-13, 2011, Barcelona, Spain. New York: IEEE. 2011, 585-592.

【2】Rusu R B, Bradski G, Thibaux R, et al. Fast 3D recognition and pose using the viewpoint feature histogram . [C]∥2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, October 18-22, 2010, Taipei, Taiwan, China. New York: IEEE. 2010, 2155-2162.

【3】Johnson A E, Hebert M. Using spin images for efficient object recognition in cluttered 3D scenes [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1999, 21(5): 433-449.Johnson A E, Hebert M. Using spin images for efficient object recognition in cluttered 3D scenes [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1999, 21(5): 433-449.

【4】Guo Y L, Sohel F, Bennamoun M, et al. Rotational projection statistics for 3D local surface description and object recognition [J]. International Journal of Computer Vision. 2013, 105(1): 63-86.

【5】Hu J B, Liu Z, Zhang P F, et al. Feature extraction of scattered point clouds based on discrete Morse theory [J]. Acta Optica Sinica. 2019, 39(6): 0615002.
胡佳贝, 刘喆, 张鹏飞, 等. 基于离散Morse理论的散乱点云特征提取 [J]. 光学学报. 2019, 39(6): 0615002.

【6】Liu J, Bai D. 3D point cloud registration algorithm based on feature matching [J]. Acta Optica Sinica. 2018, 38(12): 1215005.
刘剑, 白迪. 基于特征匹配的三维点云配准算法 [J]. 光学学报. 2018, 38(12): 1215005.

【7】Ren Q C. Method for extraction of point cloud feature line [J]. Laser & Optoelectronics Progress. 2019, 56(6): 062803.
任前程. 一种点云特征线提取方法 [J]. 激光与光电子学进展. 2019, 56(6): 062803.

【8】Simo-Serra E, Trulls E, Ferraz L, et al. Discriminative learning of deep convolutional feature point descriptors . [C]∥2015 IEEE International Conference on Computer Vision (ICCV), December 7-13, 2015, Santiago, Chile. New York: IEEE. 2015, 118-126.

【9】Charles R Q, Su H, Kaichun M, et al. PointNet: deep learning on point sets for 3D classification and segmentation . [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 77-85.

【10】Qi C R, Yi L, Su H, et al. PointNet++: deep hierarchical feature learning on point sets in a metric space [2020-04-20].https: ∥arxiv.[2020-04-20]. 0, org/abs/1706: 02413.

【11】Zeng A, Song S R, Nie?ner M, et al. 3DMatch: learning local geometric descriptors from RGB-D reconstructions . [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017, 199-208.

【12】Khoury M, Zhou Q Y, Koltun V. Learning compact geometric features . [C]∥2017 IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: IEEE. 2017, 153-161.

【13】Yang Y Q, Feng C, Shen Y R, et al. FoldingNet: point cloud auto-encoder via deep grid deformation . [C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 2018, 206-215.

【14】Yew Z J, Lee G H. 3DFeat-Net: weakly supervised local 3D features for point cloud registration [M]. ∥Ferrari V, Hebert M, Sminchisescu C, et al. Computer Vision-ECCV 2018. Lecture Notes in Computer Science. Cham: Springer. 2016, 11219: 630-646.

【15】Zhao B, Xi J T. Efficient and accurate 3D modeling based on a novel local feature descriptor [J]. Information Sciences. 2020, 512: 295-314.

【16】Tombari F, Salti S, Stefano L. Unique signatures of histograms for local surface description [M]. ∥Daniilidis K, Maragos P, Paragios N, et al. Computer Vision-ECCV 2010. Lecture Notes in Computer Science. Berlin, Heidelberg: Springer. 2010, 6313: 356-369.

【17】Novatnack J, Nishino K. Scale-dependent/invariant local 3D shape descriptors for fully automatic registration of multiple sets of range images [M]. ∥Forsyth D, Torr P, Zisserman A, et al. Computer Vision-ECCV 2008. Lecture Notes in Computer Science. Berlin, Heidelberg: Springer. 2008, 5304: 440-453.

【18】Sun Y, Abidi M A. Surface matching by 3D point''''s fingerprint . [C]∥Proceedings Eighth IEEE International Conference on Computer Vision, ICCV 2001, July 7-14, 2001, Vancouver, BC, Canada. New York: IEEE. 2001, 263-269.

【19】Levoy M, Gerth J, Curless B, et al. -05-07)[2020-04-25] . http: ∥graphics.stanford.edu/data/3Dscanrep/. 2005.

【20】Guo Y, Sohel F A, Bennamoun M, et al. TriSI: a distinctive local surface descriptor for 3D modeling and object recognition . [C]∥Conference 8th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, February 21-24, 2013, Barcelona, Spain. Barcelona, Spain: Scitepress. 2013, 1: 86-93.

引用该论文

Gu Shangtai,Wang ling,Ma Yanxin,Ma Chao. Local Feature Description of LiDAR Point Cloud Data Based on Hierarchical Mercator Projection[J]. Acta Optica Sinica, 2020, 40(20): 2015001

顾尚泰,王玲,马燕新,马超. 基于分层墨卡托投影的激光雷达点云数据局部特征描述[J]. 光学学报, 2020, 40(20): 2015001

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF