基于MANet的三维点云特征提取方法研究

doi:10.3778/j.issn.1002-8331.2103-0037

摘要/Abstract

摘要： 在三维点云数据特征提取过程中，点云数据本身的稀疏性和不规则性会影响输入数据的全局特征表示，且现有方法未考虑不同特征通道的重要性差异，不利于点云特征的全局优化。提出一种基于多分组表征和注意力机制的MANet网络进行三维点云特征描述。为获得完整的点云特征信息，将点云数据输入多分组表征模块获得初始点云特征。为学习点云不同通道的重要性，引入新的通道注意力机制强调对特征表示重要的通道，抑制不重要的通道，进一步优化特征表示。将优化后的特征输入点云分类网络，实验结果表明，多分组表征可以感知局部信息，注意力机制能够优化全局特征表示，所提方法能够对点云数据进行有效学习，有助于提高点云分类的鲁棒性和准确率。在ModelNet10/40分类数据集上总体准确率（overall accuracy）分别达到95.1%和92.5%，在ScanNet和SHREC15数据集上总体准确率分别为78.6%和97.2%，上述结果均优于PointNet++网络。

关键词: 三维点云, 特征提取, 多分组表征, 注意力机制, 深度学习

Abstract: For feature extraction of 3D point cloud data, the sparsity and irregularity of the point cloud data can affect its global feature representation and the existing methods do not consider the importance difference of different feature channels, which is not conducive to the global optimization of point cloud features. A novel MANet network based on multi-group representation and attention mechanism is proposed for 3D point cloud feature representation. Firstly, to obtain complete point cloud feature information, the point cloud data are input into the multi-group representation module to obtain the initial representation of the point cloud. Then, to learn the importance of different channels in point cloud, channel attention mechanism is introduced to emphasize the important channels for feature representation and suppress the unimportant channels, which optimizes the feature representation further. Finally, the optimized features are input into point cloud classification network. Experimental results show that multi-group representation can perceive local information, attention mechanism can optimize global feature representation, and the proposed method can effectively learn point cloud data, which helps to improve the robustness and accuracy of point cloud classification and component segmentation. The overall accuracy of ModelNet10/40 is 95.1% and 92.5% respectively, the overall accuracy of ScanNet and SHREC15 datasets reaches 78.6% and 97.2% respectively, all outperforming the PointNet++.

Key words: 3D point cloud, feature extraction, multi-group representation, attention mechanism, deep learning

王宝乐, 霍占强. 基于MANet的三维点云特征提取方法研究[J]. 计算机工程与应用, 2022, 58(19): 267-275.

WANG Baole, HUO Zhanqiang. Research on Feature Extraction of 3D Point Cloud Based on MANet[J]. Computer Engineering and Applications, 2022, 58(19): 267-275.

参考文献

[1] 田永林，沈宇，李强，等.平行点云：虚实互动的点云生成与三维模型进化方法[J].自动化学报，2020，46（12）：2572-2582.
TIAN Y L，SHEN Y，LI Q，et al.Parallel point clouds：Point clouds generation and 3D model evolution via virtual-real interaction[J].Acta Automatica Sinica，2020，46（12）：2572-2582.
[2] 廖瑞杰，杨绍发，孟文霞，等.SegGraph：室外场景三维点云闭环检测算法[J].计算机研究与发展，2019，56（2）：338-348.
LIAO R J，YANG S F，MENG W X，et al.SegGraph：An algorithm for loop-closure detection in outdoor scenes using 3D point clouds[J].Journal of Computer Research and Development，2019，56（2）：338-348.
[3] BOLD N，ZHANG C，AKASHI T.3D point cloud retrieval with bidirectional feature Match[J].IEEE Access，2019，7（11）：164194-164202.
[4] PRAKHYA S M，LIU B，LIN W，et al.B-SHOT：A binary 3D feature descriptor for fast Keypoint matching on 3D point clouds[J].Auton Robots，2017，41（7）：1501-1520.
[5] 鲁斌，范晓明.基于改进自适应[k]均值聚类的三维点云骨架提取的研究[J].自动化学报，2020，45（10）：1-13.
LU B，FAN X M.Research on 3D point cloud skeleton extraction based on improved adaptive k-means clustering[J].Acta Automatica Sinica，2020，45（10）：1-13.
[6] RUSU R B，MARTON Z C，BLODOW N，et al.Learning informative point classes for the acquisition of object model maps[C]//Proceedings of the 10th International Conference on Control，Automation，Robotics and Vision，2008：643-650.
[7] RUSU R B，BRADSKI G，THIBAUX R，et al.Fast 3D recognition and pose using the viewpoint feature histogram[C]//Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems，2010：2155-2162.
[8] SUN J，OVSJANIKOV M，GUIBAS L.A concise and provably informative multi-scale signature based on heat diffusion[J].Computer Graphics Forum，2009，28（5）：1383-1392.
[9] HANG S，SUBHRANSU M，EVANGELOS K，et al.Multi-view convolutional neural networks for 3D shape recognition[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：945-953.
[10] LECUN，Y，BOSER，B，DENKER，et al.Backpropagation applied to handwritten zip code recognition[J].Neural Computation，1989，1（4）：541-551.
[11] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//Proceedings of the 3rd International Conference on Learning Representations，2015：1-14.
[12] DENG Z，LATECKI J.Amodal detection of 3D objects：Inferring 3D bounding boxes from 2D ones in RGB-depth images[C]//Proceedings of Conference on Computer Vision and Pattern Recognition，2017：398-406.
[13] ENGELCKE M，RAO D，WANG Z，et al.Vote3deep：Fast object detection in 3D point clouds using efficient convolutional neural networks[C]//Proceedings of IEEE International Conference on Robotics and Automation，2017：1355-1361.
[14] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：Towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2017，39（6）：1137-1149.
[15] LAHOUD J，GHANEM B.2D-driven 3D object detection in RGB-D images[C]//Proceedings of 2017 IEEE International Conference on Computer Vision，2017：4622-4630.
[16] MATURANA D，SCHERER S.VoxNet：A 3D convolutional neural network for real-time object recognition[C]//Proceedings of 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems，2015：922-928.
[17] WU N Z，SONG S，KHOSLA A，et al.3D ShapeNets：A deep representation for volumetric shapes[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition，2015：1912-1920.
[18] TCHAPMI L.SEGCloud：Semantic segmentation of 3D point clouds[C]//Proceedings of International Conference on 3D Vision，2017：537-547.
[19] QI C R，SU H，MO K，et al.PointNet：Deep learning on point sets for 3D classification and segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：652-660.
[20] QI C R，YI L，SU H，et al.PointNet++：Deep hierarchical feature learning on point sets in a metric space[C]//Advances in Neural Information Processing Systems，2017：5099-5108.
[21] YE X Q，LI J M，HUANG H X，et al.3D recurrent neural networks with context fusion for point cloud semantic segmentation[C]//Proceedings of the European Conference on Computer Vision，2018：403-417.
[22] LI Y，BU R，SUN M，et al.PointCNN：Convolution on X-transformed points[C]//Advances in Neural Information Processing Systems，2018：828-838.
[23] LIN Z H，FENG M W，CICERO NOGUEIRA S.A self-attentive sentence embedding[C]//Proceedings of International Conference on Learning Representations，2017：3-5.
[24] SINGH P，MAZUMDER P，NAMBOODIRI V P.Accuracy Booster：Performance boosting using feature map re-calibration[C]//Proceedings of 2020 IEEE Winter Conference on Applications of Computer Vision，2020：873-882.
[25] ZHU X，CHENG D，ZHANG Z，et al.An empirical study of spatial attention mechanisms in deep networks[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision，2019：6687-6696.
[26] RUSSAKOVSKY O，DENG J，SU H，et al.ImageNet large scale visual recognition challenge[J].International Journal of Computer Vision，2015，115（3）：211-252.
[27] LIN T Y，MAIRE M，BELONGIE S，et al.Microsoft COCO：Common objects in context[C]//Proceedings of European Conference on Computer Vision，2014：740-755.
[28] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[29] ZHAO H，TIAN M，SUN S，et al.Spindle net：Person re-identification with human body region guided feature decomposition and fusion[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：1077-1085.
[30] CIGNONI P，CALLIERI M，CORSINI M，et al.MeshLab：An open-source mesh processing tool[C]//Proceedings of the Eurographics Italian Chapter Conference，2008：129-136.
[31] DAI A.ScanNet：Richly-annotated 3D reconstructions of indoor scenes[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：1-22.
[32] LIAN Z，ZHANG J，CHOI S，et al.Non-rigid 3D shape retrieval[C]//Proceedings of the Eurographics Workshop on 3D Object Retrieval，2015：107-120.
[33] QI C R，SU H，NIEBNER M，et al.Volumetric and multi-view CNNs for object classification on 3D data[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition，2016：5648-5656.