AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
WORK In this paper we presented two novel 3D robust features which characterize the local geometry around a point, namely the Point Feature Histogram and its fast variant, the Fast Point Feature Histograms

Fast point feature histograms (FPFH) for 3D registration

ICRA, pp.3212-3217, (2009)

被引用2340|浏览395
EI WOS
下载 PDF 全文
引用
微博一下

摘要

In our recent work [1], [2], we proposed Point Feature Histograms (PFH) as robust multi-dimensional features which describe the local geometry around a point p for 3D point cloud datasets. In this paper, we modify their mathematical expressions and perform a rigorous analysis on their robustness and complexity for the problem of 3D regist...更多

代码

数据

0
简介
  • In this paper the authors tackle the problem of consistently aligning various overlapping 3D point cloud data views into a complete model, known as 3D registration.
  • Without any information on their initial pose in space or the datasets’ overlapping areas, the problem is even more difficult and most optimization techniques are susceptible to fail in finding the best possible solution.
  • This is because the function to be optimized is multidimensional and has local optimum solutions possibly close to the global one.
  • A lot of the work done in 3D registration falls into the second category, and the most popular registration method to date is indubitably the Iterative Closest Point (ICP) algorithm [5], [6]
重点内容
  • In this paper we tackle the problem of consistently aligning various overlapping 3D point cloud data views into a complete model, known as 3D registration
  • To validate the Fast Point Feature Histograms space on data representing realworld scenes encountered in mobile robotics applications, we performed several experiments using the outdoor datasets from [2]
  • The sample consensus based method does not suffer from these shortcomings
  • WORK In this paper we presented two novel 3D robust features which characterize the local geometry around a point, namely the Point Feature Histogram (PFH) and its fast variant, the Fast Point Feature Histograms
  • We have presented a sample consensus based initial alignment algorithm (SAC-IA) which performs fast searches in an exhaustive Fast Point Feature Histograms correspondence space to find a good alignment solution which can be further refined using a nonlinear optimization method
  • Our future plans are to investigate the robustness of the feature histogram spaces for noisier point cloud data, coming from stereo or Time Of Flight cameras. Another direction of future research is to learn classifiers in the Fast Point Feature Histograms space that could be applied for fast scene segmentation, similar to our previous work in [1]
结果
  • EXPERIMENTAL RESULTS ON NOISY DATA

    To validate the FPFH space on data representing realworld scenes encountered in mobile robotics applications, the authors performed several experiments using the outdoor datasets from [2].
  • Table I presents a comparison between the two initial alignment methods, namely the previously proposed Greedy Initial Alignment (GIA) and the Sample Consensus Initial Alignment (SAC-IA), for determining the best registration solution between the two datasets presented in the left part of Figure 9.
  • The combinatorial nature of GIA makes it extremely slow for large datasets, and a workaround is to use downsampled versions of the data
  • This results in FPFH features being “averaged”, and most of the fine details can be lost.
结论
  • CONCLUSIONS AND FUTURE WORK

    In this paper the authors presented two novel 3D robust features which characterize the local geometry around a point, namely the Point Feature Histogram (PFH) and its fast variant, the FPFH.
  • The authors' future plans are to investigate the robustness of the feature histogram spaces for noisier point cloud data, coming from stereo or Time Of Flight cameras.
  • Another direction of future research is to learn classifiers in the FPFH space that could be applied for fast scene segmentation, similar to the previous work in [1].
表格
  • Table1: INITIAL ALIGNMENT RESULTS FOR THE LJUBLJANA OUTDOOR DATASET
Download tables as Excel
基金
  • Acknowledgements This work is supported by the CoTeSys (Cognition for Technical Systems) cluster of excellence
引用论文
  • R. B. Rusu, Z. C. Marton, N. Blodow, and M. Beetz, “Learning Informative Point Classes for the Acquisition of Object Model Maps,” in Proceedings of the 10th International Conference on Control, Automation, Robotics and Vision (ICARCV), Hanoi, Vietnam, December 17-20, 2008.
    Google ScholarLocate open access versionFindings
  • R. B. Rusu, N. Blodow, Z. C. Marton, and M. Beetz, “Aligning Point Cloud Views using Persistent Feature Histograms,” in Proceedings of the 21st IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Nice, France, September 22-26, 2008.
    Google ScholarLocate open access versionFindings
  • L. Silva, O. R. P. Bellon, and K. L. Boyer, “Precision Range Image Registration Using a Robust Surface Interpenetration Measure and Enhanced Genetic Algorithms,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 5, pp. 762–776, 2005.
    Google ScholarLocate open access versionFindings
  • O. Cordon, S. Damas, and J. Santamarıa, “A fast and accurate approach for 3D image registration using the scatter search evolutionary algorithm,” Pattern Recogn. Lett., vol. 27, no. 11, 2006.
    Google ScholarLocate open access versionFindings
  • P. J. Besl and N. D. McKay, “A Method for Registration of 3-D Shapes,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 14, 1992.
    Google ScholarLocate open access versionFindings
  • Z. Zhang, “Iterative Point Matching for Registration of Free-Form Curves, Tech. Rep. RR-1658.
    Google ScholarFindings
  • A. Gruen and D. Akca, “Least squares 3D surface and curve matching,” International Journal of Photogrammetry and Remote Sensing, vol. 59, pp. 151–174, May 2005.
    Google ScholarLocate open access versionFindings
  • A. W. Fitzgibbon, “Robust Registration of 2D and 3D Point Sets,” in Proceedings of the British Machine Vision Conference, 2001.
    Google ScholarLocate open access versionFindings
  • N. Gelfand, N. J. Mitra, L. J. Guibas, and H. Pottmann, “Robust Global Registration,” in Proc. Symp. Geom. Processing, 2005.
    Google ScholarLocate open access versionFindings
  • A. Makadia, A. I. Patterson, and K. Daniilidis, “Fully Automatic Registration of 3D Point Clouds,” in CVPR ’06: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, pp. 1297–1304.
    Google ScholarLocate open access versionFindings
  • A. Johnson and M. Hebert, “Using spin images for efficient object recognition in cluttered 3D scenes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 5, May 1999.
    Google ScholarLocate open access versionFindings
  • G. Sharp, S. Lee, and D. Wehe, “ICP registration using invariant features,” 2002.
    Google ScholarFindings
  • S. Rusinkiewicz and M. Levoy, “Efficient variants of the ICP algorithm,” 3-D Digital Imaging and Modeling, 2001. Proceedings. Third International Conference on, pp. 145–152, 2001.
    Google ScholarLocate open access versionFindings
  • A. Nuchter, K. Lingemann, and J. Hertzberg, “Cached k-d tree search for ICP algorithms,” in Proceedings of the Sixth International Conference on 3-D Digital Imaging and Modeling (3DIM), 2007.
    Google ScholarLocate open access versionFindings
  • R. B. Rusu, Z. C. Marton, N. Blodow, and M. Beetz, “Persistent Point Feature Histograms for 3D Point Clouds,” in Proceedings of the 10th International Conference on Intelligent Autonomous Systems, 2008.
    Google ScholarLocate open access versionFindings
  • R. B. Rusu, Z. C. Marton, N. Blodow, M. Dolha, and M. Beetz, “Towards 3D Point Cloud Based Object Maps for Household Environments,” Robotics and Autonomous Systems Journal (Special Issue on Semantic Knowledge), 2008.
    Google ScholarLocate open access versionFindings
  • N. Gelfand, L. Ikemoto, S. Rusinkiewicz, and M. Levoy, “Geometrically stable sampling for the ICP algorithm,” in Fourth International Conference on 3D Digital Imaging and Modeling (3DIM), oct 2003.
    Google ScholarLocate open access versionFindings
  • A. Barla, F. Odone, and A. Verri, “Histogram intersection kernel for image classification,” in Proceedings of International Conference on Image Processing (ICIP), 2003.
    Google ScholarLocate open access versionFindings
您的评分 :
0

 

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科