基于注意力机制的高效点云识别方法

doi:10.3969/j.issn.1006-2475.2020.08.008

摘要/Abstract

摘要： 在点云识别中，将点云数据映射成二维图片或者还原成三维空间等方法具有计算量大、场景通用性差的缺点。为此，本文提出一种基于注意力机制的深度残差学习网络的方法。本文方法通过注意力机制获得点云中不同点的权重分布和关键点，直接利用点云数据进行高效地识别。通过实验对比了多种不同方法在ModelNet40等数据集上的识别能力。结果表明，与基于二维图片方法、基于三维空间的方法以及直接处理点云的方法相比，本文方法在保证高识别精度的同时，具有参数量小、计算量小、更高效等优点。

关键词: 点云识别, 注意力机制, 残差学习, 参数量小, 高效

Abstract: For point cloud recognition, methods of mapping point cloud data into two-dimensional pictures or restoring it to three-dimensional space have some shortcomings, such as large computation complexity and poor universality of scene. To address the problems, this paper proposes a method of deep residual learning network based on attention mechanism. The method obtains the weight distribution and key points of different points in the point cloud by the attention mechanism, and directly uses the point cloud data for efficient recognition. By the experiment, this paper studies and compares the recognition ability of different methods on the datasets MNIST and ModelNet40. The experimental results show that, compared with the methods respectively based on two-dimensional pictures, based on three-dimensional space and point cloud processing directly, the proposed method has the advantages of small parameter, small calculation and higher efficiency while ensuring high recognition accuracy.

Key words: point cloud recognition, attention mechanism, residual learning, small parameter； efficient

中图分类号:

TP301.6

林钦壮, 何昭水. 基于注意力机制的高效点云识别方法[J]. 计算机与现代化, 2020, 0(08): 51-55.

LIN Qin-zhuang, HE Zhao-shui. Method of Efficient Point Cloud Recognition Based on Attention Mechanism[J]. Computer and Modernization, 2020, 0(08): 51-55.

参考文献

［1］ MMOLI F, SAPIRO G. A theoretical and computational framework for isometry invariant recognition of point cloud data［J］. Foundations of Computational Mathematics, 2005,5(3):313-347.
［2］ CHEN L, LI Q Q, ZHU Q W, et al. 3D LiDAR point cloud based intersection recognition for autonomous driving［C］// Proceedings of the IEEE Intelligent Vehicles Symposium. 2012:456-461.
［3］董敏,陈铁桩,杨浩. 基于Mesh的地面激光点云分离方法研究［J］. 计算机工程, 2019,45(6):32-36.
［4］ WANG J H, LINDENBERGH R, MENENTI M. SigVox: A 3D feature matching algorithm for automatic street object recognition in mobile laser scanning point clouds［J］. ISPRS Journal of Photogrammetry and Remote Sensing, 2017,128:111-129.
［5］ SFIKAS K, PRATIKAKIS I, THEOHARIS T. Ensemble of PANORAMA-based convolutional neural networks for 3D model classification and retrieval［J］. Computers & Graphics, 2017,71:208-218.
［6］ XU D F, ANGUELOV D, JAIN A. PointFusion: Deep sensor fusion for 3D bounding box estimation［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018:244-253.
［7］ PATHAK K, BIRK A, VASKEVICIUS N, et al. Fast registration based on noisy planes with unknown correspondences for 3-D mapping［J］. IEEE Transactions on Robotics, 2010,26(3):424-441.
［8］ VETRIVEL A, GERKE M, KERLE N, et al. Disaster damage detection through synergistic use of deep learning and 3D point cloud features derived from very high resolution oblique aerial images, and multiple-kernel-learning［J］. ISPRS Journal of Photogrammetry and Remote Sensing, 2017,140:45-59.
［9］ LECUN Y, BENGIO Y, HINTON G. Deep learning［J］. Nature, 2015,521(7553): 436-444.
［10］SU H, MAJI S, KALOGERAKIS E, et al. Multi-view convolutional neural networks for 3D shape recognition［C］// Proceedings of the IEEE International Conference on Computer Vision. 2015:945-953.
［11］KANEZAKIA, MATSUSHITA Y, NISHIDA Y. RotationNet: Joint object categorization and pose estimation using multiviews from unsupervised viewpoints［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018:5010-5019.
［12］MATURANA D, SCHERER S. VoxNet: A 3D convolutional neural network for real-time object recognition［C］// Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. 2015:922-928.
［13］WU Z R, SONG S R, KHOSLA A, et al. 3D ShapeNets: A deep representation for volumetric shapes［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015:1912-1920.
［14］CHARLESR Q, SU H, MO K C, 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. 2017:77-85.
［15］CHARLESR Q, LI Y, SU H, et al. PointNet+〖KG-*3〗+: Deep hierarchical feature learning on point sets in a metric space［C］// Advances in Neural Information Processing Systems. 2017:5099-5108.
［16］ITTI L, KOCH C. Computational modelling of visual attention［J］. Nature Reviews Neuroscience, 2001,2(3):194-203.
［17］LUONG M T, PHAM H, MANNING C D. Effective approaches to attention-based neural machine translation［C］// Proceedings of the Conference on Empirical Methods in Natural Language Processing. 2015:1412-1421.
［18］CHEN L C, YANG Y, WANG J, et al. Attention to scale: Scale-aware semantic image segmentation［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016:3640-3649.
［19］IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift［C］// Proceedings of the 32th International Conference on Machine Learning. 2015:448-456.
［20］NAIR V, HINTON G E. Rectified linear units improve restricted Boltzmann machines［C］// Proceedings of the 27th International Conference on Machine Learning.2010:807-814.
［21］HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016:770-778.
［22］LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition［J］. Proceedings of the IEEE, 1998,86(11):2278-2324.
［23］SIMARD P, STEINKRAUS D, PLATT J C. Best practices for convolutional neural networks applied to visual document analysis［C］// Proceedings of the 7th International Conference on Document Analysis and Recognition. 2003:958-963.

[1]	何思达, 陈平华. 基于意图的轻量级自注意力序列推荐模型[J]. 计算机与现代化, 2024, 0(12): 1-9.
[2]	赵晨阳, 薛涛, 刘俊华. 基于改进Stable Diffusion的时尚服饰图案生成[J]. 计算机与现代化, 2024, 0(12): 15-23.
[3]	黄庭培1, 马禄彪1, 李世宝2, 刘建航1. 基于WiFi和原型网络的手势识别方法[J]. 计算机与现代化, 2024, 0(12): 34-39.
[4]	张晓东1, 白广芝1, 李敏1, 李昊洋2. 基于经验小波变换的油气井产量预测模型 [J]. 计算机与现代化, 2024, 0(12): 53-58.
[5]	刘云海1, 冯广1, 吴晓婷2, 杨群2. 复杂施工场景下的安全帽佩戴检测算法[J]. 计算机与现代化, 2024, 0(12): 66-71.
[6]	谷岳, 邓松峰, 沈霁, 穆文涛, 赵恩棋. 基于改进YOLOv8的SAR舰船目标检测算法[J]. 计算机与现代化, 2024, 0(12): 78-83.
[7]	王艳媛, 茅正冲. 中英文场景文本图像的检测和识别算法[J]. 计算机与现代化, 2024, 0(12): 84-90.
[8]	李钧超1, 尤菲1, 张超2, 苏乐乐2, 龚龑2. 基于新型多目标浣熊优化算法的BiLSTM-Attention#br# 预测模型及误差分析[J]. 计算机与现代化, 2024, 0(11): 70-76.
[9]	张宇1, 2, 黎靖1, 2, 马铭1, 2, 王众祥1, 2, 孙妍1, 2. YOLOLW:一个新的轻量级目标检测模型[J]. 计算机与现代化, 2024, 0(11): 91-98.
[10]	祁贤, 刘大铭, 常佳鑫. 基于改进自注意力机制的多视图三维重建[J]. 计算机与现代化, 2024, 0(11): 106-112.
[11]	杨骏1, 胡为1, 朱文福2. 基于改进MobileNetV3的视觉SLAM回环检测算法[J]. 计算机与现代化, 2024, 0(10): 21-26.
[12]	魏学诚1, 江凌云1, 李研2, 何非2. 改进YOLOv5的路侧单目视角小目标检测算法[J]. 计算机与现代化, 2024, 0(10): 27-34.
[13]	杜猛俊1, 李昂1, 童俊1, 钱锦1, 康恺1, 王若丁1, 靳文星2. 基于改进极限学习算法的电力信息数据融合模型[J]. 计算机与现代化, 2024, 0(10): 61-64.
[14]	杨世军1, 狄广义1, 高军1, 陈见飞1, 王耀坤1, 季晓晗2. 跨模态注意力融合和信息感知的情感一致检测[J]. 计算机与现代化, 2024, 0(10): 113-119.
[15]	候聪颖, 杨文清, 王召, 程聪. 基于时频自注意力残差时序卷积网络的语音增强[J]. 计算机与现代化, 2024, 0(09): 20-24.