skip to main content
research-article

Exploiting Manifold Feature Representation for Efficient Classification of 3D Point Clouds

Authors Info & Claims
Published:23 January 2023Publication History
Skip Abstract Section

Abstract

In this paper, we propose an efficient point cloud classification method via manifold learning based feature representation. Different from conventional methods, we use manifold learning algorithms to embed point cloud features for better considering the geometric continuity on the surface. Then, the nature of point cloud can be acquired in low dimensional space, and after being concatenated with features in the original three-dimensional (3D) space, both the capability of feature representation and the classification network performance can be improved. We explore three traditional manifold algorithms (i.e., Isomap, Locally-Linear Embedding, and Laplacian eigenmaps) in detail, and finally, we select the Locally-Linear Embedding (LLE) algorithm due to its low complexity and locality consistency preservation. Furthermore, we propose a neural network based manifold learning (NNML) method to implement manifold learning based non-linear projection. Experiments demonstrate that the proposed two manifold learning methods can obtain better performances than the state-of-the-art methods, and the obtained mean class accuracy (mA) and overall accuracy (oA) can reach 91.4% and 94.4%, respectively. Moreover, because of the improved feature learning capability, the proposed NNML method can also have better classification accuracy on models with prominent geometric shapes. To further demonstrate the advantages of PointManifold, we extend it as a plug and play method for point cloud classification task, which can be directly used with existing methods and gain a significant improvement.

REFERENCES

  1. [1] Accessed in Feb. 2022. Manifold. https://en.wikipedia.org/wiki/Manifold.Google ScholarGoogle Scholar
  2. [2] Accessed in June 2021. Nonlinear dimensionality reduction. https://en.wikipedia.org/wiki/Nonlinear_dimensionality_reduction.Google ScholarGoogle Scholar
  3. [3] Fu Chunyang, Li Ge, Song Rui, Gao Wei, and Liu Shan. 2022. OctAttention: Octree-based large-scale contexts model for point cloud compression. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).Google ScholarGoogle ScholarCross RefCross Ref
  4. [4] Guo Yulan, Bennamoun Mohammed, Sohel Ferdous, Lu Min, and Wan Jianwei. 2014. 3D object recognition in cluttered scenes with local surface features: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 11 (2014), 22702287.Google ScholarGoogle ScholarCross RefCross Ref
  5. [5] Han Wenkai, Wen Chenglu, Wang Cheng, Li Xin, and Li Qing. 2020. Point2Node: Correlation learning of dynamic-node for point cloud feature modeling. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 1092510932.Google ScholarGoogle ScholarCross RefCross Ref
  6. [6] Hu Qingyong, Yang Bo, Xie Linhai, Rosa Stefano, Guo Yulan, Wang Zhihua, Trigoni Niki, and Markham Andrew. 2021. Learning semantic segmentation of large-scale point clouds with random sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021).Google ScholarGoogle ScholarCross RefCross Ref
  7. [7] Hu Shi-Min, Cai Jun-Xiong, and Lai Yu-Kun. 2020. Semantic labeling and instance segmentation of 3D point clouds using patch context analysis and multiscale processing. IEEE Transactions on Visualization and Computer Graphics 26, 7 (2020), 24852498.Google ScholarGoogle ScholarCross RefCross Ref
  8. [8] Jakovljevic Zivana, Puzovic Radovan, and Pajic Miroslav. 2015. Recognition of planar segments in point cloud based on wavelet transform. IEEE Transactions on Industrial Informatics 11, 2 (2015), 342352.Google ScholarGoogle Scholar
  9. [9] Jiang Mingyang, Wu Yiran, Zhao Tianqi, Zhao Zelin, and Lu Cewu. 2018. PointSift: A sift-like network module for 3D point cloud semantic segmentation. arXiv preprint arXiv:1807.00652 (2018).Google ScholarGoogle Scholar
  10. [10] Klokov Roman and Lempitsky Victor. 2017. Escape from cells: Deep KD-networks for the recognition of 3D point cloud models. In Proceedings of the IEEE International Conference on Computer Vision. 863872.Google ScholarGoogle ScholarCross RefCross Ref
  11. [11] Li Jiaxin, Chen Ben M., and Lee Gim Hee. 2018. SO-Net: Self-organizing network for point cloud analysis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 93979406.Google ScholarGoogle ScholarCross RefCross Ref
  12. [12] Li Yangyan, Bu Rui, Sun Mingchao, Wu Wei, Di Xinhan, and Chen Baoquan. 2018. PointCNN: Convolution on x-transformed points. In Advances in Neural Information Processing Systems. 820830.Google ScholarGoogle Scholar
  13. [13] Li Zhuangzi, Li Ge, Li Thomas H., Liu Shan, and Gao Wei. 2022. Semantic point cloud upsampling. IEEE Transactions on Multimedia (2022), 11.Google ScholarGoogle Scholar
  14. [14] Lin Yiqun, Yan Zizheng, Huang Haibin, Du Dong, Liu Ligang, Cui Shuguang, and Han Xiaoguang. 2020. FPConv: Learning local flattening for point convolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google ScholarGoogle ScholarCross RefCross Ref
  15. [15] Liu Kangcheng, Gao Zhi, Lin Feng, and Chen Ben M.. 2020. FG-Net: Fast large-scale LiDAR point clouds understanding network leveraging correlated feature mining and geometric-aware modelling. arXiv preprint arXiv:2012.09439 (2020).Google ScholarGoogle Scholar
  16. [16] Liu Sainan. 2018. Attentional ShapeContextNet for point cloud recognition. In IEEE Conference on Computer Vision and Pattern Recognition.Google ScholarGoogle Scholar
  17. [17] Luo Ren C. and Chen Shen Yu. 2016. Human pose estimation in 3-D space using adaptive control law with point-cloud-based limb regression approach. IEEE Transactions on Industrial Informatics 12, 1 (2016), 5158.Google ScholarGoogle ScholarCross RefCross Ref
  18. [18] Luo Shitong and Hu Wei. 2020. Differentiable manifold reconstruction for point cloud denoising. In Proceedings of the 28th ACM International Conference on Multimedia. 13301338.Google ScholarGoogle ScholarDigital LibraryDigital Library
  19. [19] Lyu Yecheng, Huang Xinming, and Zhang Ziming. 2021. Revisiting 2D convolutional neural networks for graph-based applications. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021).Google ScholarGoogle ScholarCross RefCross Ref
  20. [20] Maturana Daniel and Scherer Sebastian. 2015. VoxNet: A 3D convolutional neural network for real-time object recognition. In 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. 922928.Google ScholarGoogle ScholarDigital LibraryDigital Library
  21. [21] Monti Federico, Boscaini Davide, Masci Jonathan, Rodola Emanuele, Svoboda Jan, and Bronstein Michael M.. 2017. Geometric deep learning on graphs and manifolds using mixture model CNNs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 51155124.Google ScholarGoogle ScholarCross RefCross Ref
  22. [22] Newcombe Richard A., Izadi Shahram, Hilliges Otmar, Molyneaux David, Kim David, Davison Andrew J., Kohi Pushmeet, Shotton Jamie, Hodges Steve, and Fitzgibbon Andrew. 2011. KinectFusion: Real-time dense surface mapping and tracking. In 2011 10th IEEE International Symposium on Mixed and Augmented Reality. 127136.Google ScholarGoogle ScholarDigital LibraryDigital Library
  23. [23] Nie Weizhi, Liang Qi, Wang Yixin, Wei Xing, and Su Yuting. 2020. MMFN: Multimodal information fusion networks for 3D model classification and retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 4 (2020), 122.Google ScholarGoogle ScholarDigital LibraryDigital Library
  24. [24] Qi Charles R., Su Hao, Mo Kaichun, and Guibas Leonidas J.. 2017. PointNet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 652660.Google ScholarGoogle Scholar
  25. [25] Qi Charles Ruizhongtai, Yi Li, Su Hao, and Guibas Leonidas J.. 2017. PointNet++: Deep hierarchical feature learning on point sets in a metric space. In Advances in Neural Information Processing Systems. 50995108.Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. [26] Ran Haoxi, Zhuo Wei, Liu Jun, and Lu Li. 2021. Learning inner-group relations on point clouds. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 1547715487.Google ScholarGoogle ScholarCross RefCross Ref
  27. [27] Rusu Radu Bogdan, Blodow Nico, and Beetz Michael. 2009. Fast point feature histograms (FPFH) for 3D registration. In IEEE International Conference on Robotics and Automation. 32123217.Google ScholarGoogle ScholarDigital LibraryDigital Library
  28. [28] Shi Shaoshuai, Guo Chaoxu, Jiang Li, Wang Zhe, Shi Jianping, Wang Xiaogang, and Li Hongsheng. 2020. PV-RCNN: Point-voxel feature set abstraction for 3D object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1052910538.Google ScholarGoogle ScholarCross RefCross Ref
  29. [29] Song Fei, Li Ge, Gao Wei, and Li Thomas H.. 2022. Rate-distortion optimized graph for point cloud attribute coding. IEEE Signal Processing Letters 29 (2022), 922926.Google ScholarGoogle ScholarCross RefCross Ref
  30. [30] Song Fei, Shao Yiting, Gao Wei, Wang Haiqiang, and Li Thomas. 2021. Layer-wise geometry aggregation framework for lossless LiDAR point cloud compression. IEEE Transactions on Circuits and Systems for Video Technology 31, 12 (2021), 46034616.Google ScholarGoogle ScholarCross RefCross Ref
  31. [31] Su Hang, Maji Subhransu, Kalogerakis Evangelos, and Learned-Miller Erik. 2015. Multi-view convolutional neural networks for 3D shape recognition. In Proceedings of the IEEE International Conference on Computer Vision. 945953.Google ScholarGoogle ScholarDigital LibraryDigital Library
  32. [32] Tatarchenko Maxim, Park Jaesik, Koltun Vladlen, and Zhou Qian-Yi. 2018. Tangent convolutions for dense prediction in 3D. CoRR abs/1807.02443 (2018).Google ScholarGoogle Scholar
  33. [33] Maaten Laurens Van der and Hinton Geoffrey. 2008. Visualizing data using t-SNE.Journal of Machine Learning Research 9, 11 (2008).Google ScholarGoogle Scholar
  34. [34] Wang Yue, Sun Yongbin, Liu Ziwei, Sarma Sanjay E., Bronstein Michael M., and Solomon Justin M.. 2019. Dynamic graph CNN for learning on point clouds. ACM Transactions on Graphics 38, 5 (2019), 112.Google ScholarGoogle ScholarDigital LibraryDigital Library
  35. [35] Wu Wenxuan, Qi Zhongang, and Fuxin Li. 2019. PointConv: Deep convolutional networks on 3D point clouds. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google ScholarGoogle ScholarCross RefCross Ref
  36. [36] Wu Zhirong, Song Shuran, Khosla Aditya, Yu Fisher, Zhang Linguang, Tang Xiaoou, and Xiao Jianxiong. 2015. 3D ShapeNets: A deep representation for volumetric shapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 19121920.Google ScholarGoogle Scholar
  37. [37] Xiang Tiange, Zhang Chaoyi, Song Yang, Yu Jianhui, and Cai Weidong. 2021. Walk in the cloud: Learning curves for point clouds shape analysis. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 915924.Google ScholarGoogle ScholarCross RefCross Ref
  38. [38] Xu Mutian, Ding Runyu, Zhao Hengshuang, and Qi Xiaojuan. 2021. PAConv: Position adaptive convolution with dynamic kernel assembling on point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 31733182.Google ScholarGoogle ScholarCross RefCross Ref
  39. [39] Xu Yifan, Fan Tianqi, Xu Mingye, Zeng Long, and Qiao Yu. 2018. SpiderCNN: Deep learning on point sets with parameterized convolutional filters. In Proceedings of the European Conference on Computer Vision. 87102.Google ScholarGoogle ScholarDigital LibraryDigital Library
  40. [40] Yavartanoo Mohsen, Kim Eu Young, and Lee Kyoung Mu. 2018. SPNet: Deep 3D object classification and retrieval using stereographic projection. In Proceedings of the Asian Conference on Computer Vision. 691706.Google ScholarGoogle Scholar
  41. [41] Zhang Cheng, Wan Haocheng, Liu Shengqiang, Shen Xinyi, and Wu Zizhao. 2021. PVT: Point-voxel transformer for 3D deep learning. arXiv preprint arXiv:2108.06076 (2021).Google ScholarGoogle Scholar
  42. [42] Zhang Ruonan, Chen Jingyi, Gao Wei, Li Ge, and Li Thomas H.. 2022. PointOT: Interpretable geometry-inspired point cloud generative model via optimal transport. IEEE Transactions on Circuits and Systems for Video Technology (2022), 11.Google ScholarGoogle Scholar
  43. [43] Zhang Yingxue and Rabbat Michael. 2018. A graph-CNN for 3D point cloud classification. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing. 62796283.Google ScholarGoogle ScholarDigital LibraryDigital Library
  44. [44] Zhang Yihuan, Wang Jun, Wang Xiaonian, and Dolan John M.. 2018. Road-segmentation-based curb detection method for self-driving via a 3D-LiDAR sensor. IEEE Transactions on Intelligent Transportation Systems 19, 12 (2018), 39813991.Google ScholarGoogle ScholarDigital LibraryDigital Library
  45. [45] Zhao Hengshuang, Jiang Li, Fu Chi-Wing, and Jia Jiaya. 2019. PointWeb: Enhancing local neighborhood features for point cloud processing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 55655573.Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. Exploiting Manifold Feature Representation for Efficient Classification of 3D Point Clouds

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in

      Full Access

      • Published in

        cover image ACM Transactions on Multimedia Computing, Communications, and Applications
        ACM Transactions on Multimedia Computing, Communications, and Applications  Volume 19, Issue 1s
        February 2023
        504 pages
        ISSN:1551-6857
        EISSN:1551-6865
        DOI:10.1145/3572859
        • Editor:
        • Abdulmotaleb El Saddik
        Issue’s Table of Contents

        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        • Published: 23 January 2023
        • Online AM: 29 July 2022
        • Accepted: 16 May 2022
        • Revised: 8 March 2022
        • Received: 19 September 2021
        Published in tomm Volume 19, Issue 1s

        Permissions

        Request permissions about this article.

        Request Permissions

        Check for updates

        Qualifiers

        • research-article
        • Refereed
      • Article Metrics

        • Downloads (Last 12 months)327
        • Downloads (Last 6 weeks)33

        Other Metrics

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Full Text

      View this article in Full Text.

      View Full Text

      HTML Format

      View this article in HTML Format .

      View HTML Format
      About Cookies On This Site

      We use cookies to ensure that we give you the best experience on our website.

      Learn more

      Got it!