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.
- [1] Accessed in Feb. 2022. Manifold. https://en.wikipedia.org/wiki/Manifold.Google Scholar
- [2] Accessed in June 2021. Nonlinear dimensionality reduction. https://en.wikipedia.org/wiki/Nonlinear_dimensionality_reduction.Google Scholar
- [3] . 2022. OctAttention: Octree-based large-scale contexts model for point cloud compression. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).Google Scholar
Cross Ref
- [4] . 2014. 3D object recognition in cluttered scenes with local surface features: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 11 (2014), 2270–2287.Google Scholar
Cross Ref
- [5] . 2020. Point2Node: Correlation learning of dynamic-node for point cloud feature modeling. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 10925–10932.Google Scholar
Cross Ref
- [6] . 2021. Learning semantic segmentation of large-scale point clouds with random sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021).Google Scholar
Cross Ref
- [7] . 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), 2485–2498.Google Scholar
Cross Ref
- [8] . 2015. Recognition of planar segments in point cloud based on wavelet transform. IEEE Transactions on Industrial Informatics 11, 2 (2015), 342–352.Google Scholar
- [9] . 2018. PointSift: A sift-like network module for 3D point cloud semantic segmentation. arXiv preprint arXiv:1807.00652 (2018).Google Scholar
- [10] . 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. 863–872.Google Scholar
Cross Ref
- [11] . 2018. SO-Net: Self-organizing network for point cloud analysis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9397–9406.Google Scholar
Cross Ref
- [12] . 2018. PointCNN: Convolution on x-transformed points. In Advances in Neural Information Processing Systems. 820–830.Google Scholar
- [13] . 2022. Semantic point cloud upsampling. IEEE Transactions on Multimedia (2022), 1–1.Google Scholar
- [14] . 2020. FPConv: Learning local flattening for point convolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
Cross Ref
- [15] . 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 Scholar
- [16] . 2018. Attentional ShapeContextNet for point cloud recognition. In IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
- [17] . 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), 51–58.Google Scholar
Cross Ref
- [18] . 2020. Differentiable manifold reconstruction for point cloud denoising. In Proceedings of the 28th ACM International Conference on Multimedia. 1330–1338.Google Scholar
Digital Library
- [19] . 2021. Revisiting 2D convolutional neural networks for graph-based applications. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021).Google Scholar
Cross Ref
- [20] . 2015. VoxNet: A 3D convolutional neural network for real-time object recognition. In 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. 922–928.Google Scholar
Digital Library
- [21] . 2017. Geometric deep learning on graphs and manifolds using mixture model CNNs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5115–5124.Google Scholar
Cross Ref
- [22] . 2011. KinectFusion: Real-time dense surface mapping and tracking. In 2011 10th IEEE International Symposium on Mixed and Augmented Reality. 127–136.Google Scholar
Digital Library
- [23] . 2020. MMFN: Multimodal information fusion networks for 3D model classification and retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 4 (2020), 1–22.Google Scholar
Digital Library
- [24] . 2017. PointNet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 652–660.Google Scholar
- [25] . 2017. PointNet++: Deep hierarchical feature learning on point sets in a metric space. In Advances in Neural Information Processing Systems. 5099–5108.Google Scholar
Digital Library
- [26] . 2021. Learning inner-group relations on point clouds. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 15477–15487.Google Scholar
Cross Ref
- [27] . 2009. Fast point feature histograms (FPFH) for 3D registration. In IEEE International Conference on Robotics and Automation. 3212–3217.Google Scholar
Digital Library
- [28] . 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. 10529–10538.Google Scholar
Cross Ref
- [29] . 2022. Rate-distortion optimized graph for point cloud attribute coding. IEEE Signal Processing Letters 29 (2022), 922–926.Google Scholar
Cross Ref
- [30] . 2021. Layer-wise geometry aggregation framework for lossless LiDAR point cloud compression. IEEE Transactions on Circuits and Systems for Video Technology 31, 12 (2021), 4603–4616.Google Scholar
Cross Ref
- [31] . 2015. Multi-view convolutional neural networks for 3D shape recognition. In Proceedings of the IEEE International Conference on Computer Vision. 945–953.Google Scholar
Digital Library
- [32] . 2018. Tangent convolutions for dense prediction in 3D. CoRR abs/1807.02443 (2018).Google Scholar
- [33] . 2008. Visualizing data using t-SNE.Journal of Machine Learning Research 9, 11 (2008).Google Scholar
- [34] . 2019. Dynamic graph CNN for learning on point clouds. ACM Transactions on Graphics 38, 5 (2019), 1–12.Google Scholar
Digital Library
- [35] . 2019. PointConv: Deep convolutional networks on 3D point clouds. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
Cross Ref
- [36] . 2015. 3D ShapeNets: A deep representation for volumetric shapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1912–1920.Google Scholar
- [37] . 2021. Walk in the cloud: Learning curves for point clouds shape analysis. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 915–924.Google Scholar
Cross Ref
- [38] . 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. 3173–3182.Google Scholar
Cross Ref
- [39] . 2018. SpiderCNN: Deep learning on point sets with parameterized convolutional filters. In Proceedings of the European Conference on Computer Vision. 87–102.Google Scholar
Digital Library
- [40] . 2018. SPNet: Deep 3D object classification and retrieval using stereographic projection. In Proceedings of the Asian Conference on Computer Vision. 691–706.Google Scholar
- [41] . 2021. PVT: Point-voxel transformer for 3D deep learning. arXiv preprint arXiv:2108.06076 (2021).Google Scholar
- [42] . 2022. PointOT: Interpretable geometry-inspired point cloud generative model via optimal transport. IEEE Transactions on Circuits and Systems for Video Technology (2022), 1–1.Google Scholar
- [43] . 2018. A graph-CNN for 3D point cloud classification. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing. 6279–6283.Google Scholar
Digital Library
- [44] . 2018. Road-segmentation-based curb detection method for self-driving via a 3D-LiDAR sensor. IEEE Transactions on Intelligent Transportation Systems 19, 12 (2018), 3981–3991.Google Scholar
Digital Library
- [45] . 2019. PointWeb: Enhancing local neighborhood features for point cloud processing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5565–5573.Google Scholar
Cross Ref
Index Terms
Exploiting Manifold Feature Representation for Efficient Classification of 3D Point Clouds
Recommendations
Riemannian Manifold Learning
Recently, manifold learning has been widely exploited in pattern recognition, data analysis, and machine learning. This paper presents a novel framework, called Riemannian manifold learning (RML), based on the assumption that the input high-dimensional ...
Face feature extraction and recognition based on discriminant subclass-center manifold preserving projection
Manifold learning is an effective dimensional reduction technique for face feature extraction, which, generally speaking, tends to preserve the local neighborhood structures of given samples. However, neighbors of a sample often comprise more inter-...
Biologically inspired feature manifold for scene classification
Biologically inspired feature (BIF) and its variations have been demonstrated to be effective and efficient for scene classification. It is unreasonable to measure the dissimilarity between two BIFs based on their Euclidean distance. This is because ...






Comments