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［23］

［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]	付鸿林, 张太红, 杨雅婷, 艾孜麦提·艾瓦尼尔, 马博. 基于生成对抗网络的维语场景文字修改网络[J]. 计算机与现代化, 2024, 0(01): 41-46.
[2]	王秋忆, 周浩, 郑婷婷. 改进RetinaNet的电力设备目标检测方法[J]. 计算机与现代化, 2024, 0(01): 47-52.
[3]	林启钊, 彭志平, 郭棉, 崔得龙. 基于双向多步预测的炉管温度场重构方法[J]. 计算机与现代化, 2024, 0(01): 53-58.
[4]	李亚平, 王军防, 余红梅, 窦一民, 肖媛, 田继林. Regformer：基于稀疏注意力的输油管道水力压降预测方法[J]. 计算机与现代化, 2024, 0(01): 59-66.
[5]	周成诚, 曾庆军, 杨康, 胡家铭, 韩春伟. 基于高效通道注意力模块的运动想象脑电识别[J]. 计算机与现代化, 2023, 0(12): 19-23.
[6]	邱凯星, 冯广. 基于双重特征注意力的多标签图像分类模型[J]. 计算机与现代化, 2023, 0(12): 41-47.
[7]	张浩洋, 尹梓名, 乐珺怡, 沈达聪, 束翌俊, 杨自逸, 孔祥勇, 龚伟. 3D-SPRNet: 一种基于并行解码器和双注意力机制的胆囊癌分割模型[J]. 计算机与现代化, 2023, 0(12): 59-66.
[8]	张伯泉, 麦海鹏, 陈嘉敏, 逄锦聚. 基于高灰度值注意力机制的脑白质高信号分割[J]. 计算机与现代化, 2023, 0(12): 67-75.
[9]	宁娟, 周庆华, 曾小为. 改进YOLOv7算法在西林瓶轧盖缺陷检测中的应用[J]. 计算机与现代化, 2023, 0(12): 82-86.
[10]	王宇航, 董宝良, 公超, 尚真真, 姚康宁. 基于意图识别的空中群目标动态威胁评估[J]. 计算机与现代化, 2023, 0(12): 100-104.
[11]	罗明杰, 冯开平. 基于沙漏结构与注意力机制的轻量级人脸表情识别方法[J]. 计算机与现代化, 2023, 0(11): 89-94.
[12]	张嘉琪, 徐啟蕾. 基于NAM-YOLO网络的苹果缺陷检测算法[J]. 计算机与现代化, 2023, 0(10): 53-58.
[13]	叶思佳, 魏延, 杜韩宇, 邓金枝. 结合注意力机制的HRNet图像语义分割算法[J]. 计算机与现代化, 2023, 0(10): 65-69.
[14]	陈嘉敏, 张伯泉, 麦海鹏. 基于特征融合的海马体分割[J]. 计算机与现代化, 2023, 0(08): 1-6.
[15]	刘续, 查可可. 一种用于机场特种车辆作业的环境目标识别方法[J]. 计算机与现代化, 2023, 0(08): 18-24.