基于卷积神经网络的车辆位姿估计算法Vehicle Pose Estimation Algorithm Based on Convolution Neural Network
周苏,郑淼,郑守建,金杰
摘要(Abstract)：
针对基于双目视觉和激光雷达对车辆进行位姿估计时计算量大、成本高等问题,提出一种单目视觉位姿估计算法,设计多任务卷积神经网络作为车辆位置和姿态估计的网络。将目标车辆视为刚体,分别对其尺寸、姿态角、3D中心点建模,以KITTI数据集中相关数据对模型进行训练,并分析训练后的网络,估计模型的计算速度和精度。结果表明,该位姿估计网络实时性良好,帧速率达50帧/s,平均姿态角相似度达86.14%。
关键词(KeyWords)：
基金项目(Foundation):
作者(Author): 周苏,郑淼,郑守建,金杰
DOI: 10.19620/j.cnki.1000-3703.20201056
参考文献(References)：
- [1]KU J,MOZIFIAN M,LEE J,et al.Joint 3D Proposal Generation and Object Detection from View Aggregation[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS),2018:1-8.
- [2]LI P,CHEN X,SHEN S.Stereo R-CNN Based 3D Object Detection for Autonomous Driving[C]//2019 IEEE/CVFConference on Computer Vision and Pattern Recognition(CVPR),2019:7636-7644.
- [3]PON A D,KU J,LI C,et al.Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS),2019:3459-3466.
- [4]QIN Z,WANG J,LU Y.Triangulation Learning Network:from Monocular to Stereo 3D Object Detection[J].2019IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR),2019:7607-7615.
- [5]CHEN Y C,SU T F,LAI S H.Integrated Vehicle and Lane Detection with Distance Estimation[M]//Computer VisionACCV 2014 Workshops.Switzerland:Springer Cham,2014:473-485.
- [6]KI Y P,SUN Y H.Robust Range Estimation with a Monocular Camera for Vision-Based Forward Collision Warning System[J].The Scientific World Journal,2014:1-9.
- [7]刘强,潘明,李永伟.基于FPGA的汽车单目测距系统设计[J].液晶与显示,2014,29(3):422-428.LIU Q,PAN M,LI Y W.Design of Vehicle Monocular Ranging System Based on FPGA[J].Chinese Journal of Liquid Crystals and Displays,2014,29(3):422-428.
- [8]RODDICK T,KENDALL A,ROBERTO C.Orthographic Feature Transform for Monocular 3D Object Detection[C]//The British Machine Vision Conference(BMVC),2018:1-15.
- [9]QIN T,LI P,SHEN S.VINS-Mono:A Robust and Versatile Monocular Visual-Inertial State Estimator[J].IEEETransactions on Robotics,2018,34(4):1004-1020.
- [10]ZHANG Z.A Flexible New Technique for Camera Calibration[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2000,22(11):1330-1334.
- [11]MADSEN R E,HANSEN L K,WINTHER O.Singular Value Decomposition and Principal Component Analysis[J].Neural Networks,2004(1):1-5.
- [12]CHEN T,LU S,FAN J.S-CNN:Subcategory-Aware Convolutional Networks for Object Detection[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2018,40(10):2522-2528.
- [13]GEIGER A,LENZ P,URTASUN R.Are We Ready for Autonomous Driving the KITTI Vision Benchmark Suite[C]//IEEE Conference on Computer Vision and Pattern Recognition,2012:3354-3361.