Three-Dimensional Object Detection of Radar Point Cloud Based on Sparse Transformer

doi:10.19678/j.issn.1000-3428.0062440

Abstract

Abstract: With the development of computer vision technology, three-dimensional object detection algorithms based on point cloud are widely used in automatic driving, robot control and other application scenarios.Aiming at the problems of poor robustness and low detection accuracy of three-dimensional object detection algorithms based on point cloud, under the condition of sparse point cloud, this study proposes three-dimensional object detection algorithm based on the sparse Transformer.In the attention matrix generation stage, a sparse Transformer module is used to select the Top-t weight elements explicitly to retain the most favorable weight elements for feature extraction, reduce the impact of environmental noise on robustness, and accelerate the running speed of the Transformer module.In the regression stage, the bounding box generated by the coarse regression module based on spatial features is used as the initial anchor frame of the detection-head module for the subsequent fine regression operation of the bounding box.A loss function based on voxel for 3D object detection is proposed to accurately measure category, position regression, and direction losses.The experimental results on the KITTI dataset show that compared with the PointPillars algorithm, the average accuracy of the proposed algorithm is improved by 3.46%.It can effectively improve the detection accuracy of point cloud three- dimensional targets and has better robustness.Compared with the running speed of the original Transformer module, the average running speed of the proposed sparse Transformer module on point cloud image is improved by about 0.54 frame/s.

Key words: machine vision, three-dimensional object detection, sparse Transformer, coarse regression, loss function

摘要： 随着计算机视觉技术的发展，基于点云的三维目标检测算法被广泛应用于自动驾驶、机器人控制等领域。针对点云稀疏条件下基于点云三维目标检测算法鲁棒性较差、检测精度低的问题，提出基于稀疏Transformer的三维目标检测算法。在注意力矩阵生成阶段，通过稀疏Transformer模块显式选择Top-t个权重元素，以保留有利于特征提取的权重元素，在降低环境噪点对鲁棒性影响的同时加快Transformer模块的运行速度。在回归阶段，将基于空间特征粗回归模块生成的边界框作为检测头模块的初始锚框，用于后续边界框的精细回归操作。设计基于体素的三维目标检测算法的损失函数，以精确地衡量类别损失、位置回归损失和方向损失。在KITTI数据集上的实验结果表明，相比PointPillars算法，该算法的平均精度均值提高3.46%，能有效提高点云三维目标的检测精度且具有较优的鲁棒性。相比原始Transformer模块，所提稀疏Transformer模块在点云图像上的平均运行速度加快了约0.54 frame/s。

关键词: 机器视觉, 三维目标检测, 稀疏Transformer, 粗回归, 损失函数

CLC Number:

TP391

HAN Lei, GAO Yongbin, SHI Zhicai. Three-Dimensional Object Detection of Radar Point Cloud Based on Sparse Transformer[J]. Computer Engineering, 2022, 48(11): 104-110,144.

韩磊, 高永彬, 史志才. 基于稀疏Transformer的雷达点云三维目标检测[J]. 计算机工程, 2022, 48(11): 104-110,144.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0062440

http://www.ecice06.com/EN/Y2022/V48/I11/104

Figures/Tables 12

References

[1] 刘丹, 马世霞.融合超像素3D与Appearance特征的可行驶区域检测[J].计算机工程, 2017, 43(7):293-297. LIU D, MA S X.Travelable area detection fusing superpixel 3D and apperance feature[J].Computer Engineering, 2017, 43(7):293-297.(in Chinese)
[2] PARK Y, LEPETIT V, WOO W.Multiple 3D object tracking for augmented reality[C]//Proceedings of the 7th International Symposium on Mixed and Augmented Reality.Washington D.C., USA:IEEE Press, 2008:117-120.
[3] 葛俊彦, 史金龙, 周志强, 等.基于三维检测网络的机器人抓取方法[J].仪器仪表学报, 2021, 41(8):146-153. GE J Y, SHI J L, ZHOU Z Q, et al.A robotic grasping method based on three-dimensional detection network[J].Chinese Journal of Scientific Instrument, 2021, 41(8):146-153.(in Chinese)
[4] 方海国.基于深度学习的3D目标检测与抓取研究[D].湘潭:湘潭大学, 2020. FANG H G.Research on 3D object detection and grasping technology based on deep learning[D].Xiangtan:Xiangtan University, 2020.(in Chinese)
[5] 迟旭然, 裴伟, 朱永英, 等.Fast Stereo-RCNN三维目标检测算法[J].小型微型计算机系统, 2022, 43(10):2157-2167. CHI X R, PEI W, ZHU Y Y, et al.Fast Stereo-RCNN 3D target detection algorithm[J].Journal of Chinese Computer Systems, 2022, 43(10):2157-2167.(in Chinese)
[6] QIN Z Y, WANG J L, LU Y.MonoGRNet:a geometric reasoning network for monocular 3D object localization[EB/OL].[2021-07-20].https://arxiv.org/pdf/1811.10247.pdf.
[7] WANG Y, CHAO W L, GARG D, et al.Pseudo-LiDAR from visual depth estimation:bridging the gap in 3D object detection for autonomous driving[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:8437-8445.
[8] 于洁潇, 张美琪, 苏育挺.基于双目视觉的三维车辆检测算法[J].激光与光电子学进展, 2021, 58(2):301-306. YU J X, ZHANG M Q, SU Y T.Three-dimensional vehicle detection algorithm based on binocular vision[J].Laser & Optoelectronics Progress, 2021, 58(2):301-306.(in Chinese)
[9] SHIN K, KWON Y P, TOMIZUKA M.RoarNet:a robust 3D object detection based on region approximation refinement[C]//Proceedings of Intelligent Vehicles Symposium.Washington D.C., USA:IEEE Press, 2019:2510-2515.
[10] HUANG T T, LIU Z, CHEN X W, et al.EPNet:enhancing point features with image semantics for 3D object detection[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2020:35-52.
[11] 王海, 刘明亮, 蔡英凤, 等.基于激光雷达与毫米波雷达融合的车辆目标检测算法[J].江苏大学学报(自然科学版), 2021, 42(4):389-394. WANG H, LIU M L, CAI Y F, et al.Vehicle target detection algorithm based on fusion of lidar and millimeter wave radar[J].Journal of Jiangsu University (Natural Science Edition), 2021, 42(4):389-394.(in Chinese)
[12] 江泽宇, 赵芸.基于边缘卷积的三维目标识别算法[J].浙江科技学院学报, 2021, 33(3):214-219. JIANG Z Y, ZHAO Y.3D target recognition algorithm based on edge convolution[J].Journal of Zhejiang University of Science and Technology, 2021, 33(3):214-219.(in Chinese)
[13] 刘高天, 段锦, 范祺, 等.基于改进RFBNet算法的遥感图像目标检测[J].吉林大学学报(理学版), 2021, 59(5):1188-1198. LIU G T, DUAN J, FAN Q, et al.Target detection for remote sensing image based on improved RFBNet algorithm[J].Journal of Jilin University(Science Edition), 2021, 59(5):1188-1198.(in Chinese)
[14] ZHOU Y, TUZEL O.VoxelNet:end-to-end learning for point cloud based 3D object detection[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:4490-4499.
[15] LANG A H, VORA S, CAESAR H, et al.PointPillars:fast encoders for object detection from point clouds[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:12689-12697.
[16] SHI W J, RAJKUMAR R.Point-GNN:graph neural network for 3D object detection in a point cloud[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:1708-1716.
[17] 杨永光.基于点云的目标检测方法研究[D].南京:南京邮电大学, 2020. YANG Y G.Research on point cloud based on object detection algorithm[D].Nanjing:Nanjing University of Posts and Telecommunications, 2020.(in Chinese)
[18] BERG A C, FU C Y, SZEGEDY C, et al.SSD:single shot multi-box detector[C]//Proceedings of the European Conference on Computer Vision.Berlin, Germany:Springer, 2016:21-37.
[19] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.New York, USA:ACM Press, 2017:6000-6010.
[20] ZHAO G X, LIN J Y, ZHANG Z Y, et al.Sparse Transformer:concentrated attention through explicit selection[EB/OL].[2021-07-20].https://arxiv.org/abs/1912.11637.
[21] BA J L, KIROS J R, HINTON G E.Layer normalization[EB/OL].[2021-07-20].https://arxiv.org/pdf/1607.06450.pdf.
[22] YAN Y, MAO Y, LI B.SECOND:sparsely embedded convolutional detection[J].Sensors, 2018, 18(10):3337.
[23] XU J, MA Y X, HE S H, et al.3D-GIoU:3D generalized intersection over union for object detection in point cloud[J].Sensors, 2019, 19(19):4093-4108.
[24] SHI S S, WANG Z, SHI J P, et al.From points to parts:3D object detection from point cloud with part-aware and part-aggregation network[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(6):836-842.
[25] SHI S S, WANG X G, LI H S.PointRCNN:3D object proposal generation and detection from point cloud[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:770-779.
[26] LIU Z, ZHAO X, HUANG T T, et al.TANet:robust 3D object detection from point clouds with triple attention[C]//Proceedings of the 24th AAAI Conference on Artificial Intelligence.New York, USA:AAAI Press, 2020:11677-11684.

Please choose a citation manager

Content to export