Optics and Precision Engineering, Volume. 30, Issue 16, 1988(2022)

Scene recognition for 3D point clouds: a review

Wen HAO1,2、*, Wenjing ZHANG1,2, Wei LIANG1,2, Zhaolin XIAO1,2, and Haiyan JIN1,2
Author Affiliations
  • 1School of Computer Science and Engineering, Xi'an University of Technology, Xi'an70048, China
  • 2Shaanxi Key Laboratory for Network Computing and Security Technology, Xi’an710048, China
  • show less
    Figures & Tables(14)
    Images of the same scene at different times and illumination in the dataset Oxford RobotCar[6]
    Classification of scene recognition algorithms for point clouds
    Flowchart of SegMatch algorithm
    Flowchart of Seed algorithm
    Chronological overview of scene recognition for point clouds
    Network architecture of PointNetVLAD[58]
    Network architecture of LPD-Net[19]
    Network architecture of Semantic Graph[61]
    • Table 1. Network models based on learning to obtain features

      View table
      View in Article

      Table 1. Network models based on learning to obtain features

      网络模型年份网络主干结构关键技术数据
      PointNetVLAD582018PointNet,NetVLAD转换网络T-Net、多层感知机、对称函数Oxford Robotcar
      PCAN baseline162019PointNet,NetVLAD转换网络T-Net、多层感知机、对称函数、SAG层Oxford Robotcar
      DAGC baseline592020DGCNN, NetVLAD双注意力模块、EdgeConvOxford Robotcar
      SOE-Net172021PointSift, NetVLADPointOE模块Oxford Robotcar
      AttDLNet182021RangeNet++注意力模块KITTI
      ARIConv622021DenseNet注意旋转不变卷积Oxford Robotcar
      Lpd-Net192019DGCNN, NetVLAD十维几何特征计算、转换网络、动态图网络Oxford Robotcar
      SRNet602020Static Graph Convolution (SGC), NetVLADSGC模块、三层空间注意力模块Oxford Robotcar
      SemGraph612020RangeNet++,DGCNNEdgeConv、图相似性匹配模块KITTI
      EPC-Net632021EPCNet, Grouped VLAD多层ProxyConvOxford Robotcar
      MinkLoc3D242021Feature Pyramid Network architecture局部特征提取网络、广义均值池Oxford Robotcar
      DH3D642020PointNet, NetVLADFlexConv、挤压和激励模块Oxford RobotCar
      TransLoc3D252021External Transformer, NetVLAD自适应感受野模块, 3D稀疏卷积模块Oxford Robotcar
      SVT-Net262021Sparse Voxel Transformers基于原子的稀疏体素变换器、基于聚类的稀疏体素变换器Oxford Robotcar
    • Table 2. Dataset for scene recognition of point cloud

      View table
      View in Article

      Table 2. Dataset for scene recognition of point cloud

      数据集传感器移动平台变化场景相机

      IMU

      频率/Hz

      数据总量
      Oxford RobotCar[6]2017SICK LMS-151车辆不同季节、光照、动态目标遮挡、建筑物改造等综合变化与干扰室外3单目1×1223.15TB
      KITTI odometry[70-71]2013Velodyne HDL-64E车辆室外2双目1×10180 GB
      North Campus Long Term (NCLT)[72]2016Velodyne HDL-32ESegway机器人不同季节、光照、植被等综合变化校园(室内、室外)

      6单目(全向)

      4单目

      1×100

      1×200

      2.95 TB
      MulRan[73]2020

      Ouster OS1-64

      Navtech CIR204-H

      车辆不同时间段会议中心、校园、高速公路、河边道路--387 GB
      Ford[74]2011Velodyne HDL-64E车辆福特研究院、密歇根州迪尔伯恩市中心1单目1×100100 GB
      SEU-FX[75]2019速腾聚创 RS-32车辆不同天气、时间、光照条件城市道路、校园场景双目1×30-
    • Table 3. Network parameter quantity and runtime of different scene recognition models

      View table
      View in Article

      Table 3. Network parameter quantity and runtime of different scene recognition models

      ModelNetwork parameter quantity/MBRuntime per frame/ms
      PointNetVLAD5819.7815
      PCAN1620.4255
      Lpd-Net1919.8126
      Minkloc3D241.121
    • Table 4. 3D local descriptor dimension

      View table
      View in Article

      Table 4. 3D local descriptor dimension

      DescriptorSize
      SHOT33352
      USC341 960
      FPFH3533
      Gestalt3D13130
      NBLD141 408
      ISHOT481 344
    • Table 5. Scene recognition results based on deep learning

      View table
      View in Article

      Table 5. Scene recognition results based on deep learning

      MethodsAverage recall @1%
      OxfordU.S.R.A.B.D.
      PointNetVLAD5880.31%72.63%60.27%65.3%
      PCAN baseline1683.81%79.05%71.18%66.82%
      DAGC baseline5987.49%83.49%75.68%71.21%
      SOE-Net1796.4%93.17%91.47%88.45%
      SRNet6094.56%94.33%89.23%83.49%
      Lpd-net1994.92%96%90.46%89.14%
      EPC-Net6394.74%96.52%88.58%84.92%
      MinkLoc3D2497.9%95%91.2%88.5%
      TransLoc3D2598.5%94.9%91.5%88.4%
      SVT-Net2697.8%96.5%92.7%90.7%
    • Table 6. F1 max scores on the KITTI dataset

      View table
      View in Article

      Table 6. F1 max scores on the KITTI dataset

      Methods000205060708Mean
      M2DP150.8360.7810.7720.8960.8610.1690.719
      ScanContext440.9370.8580.9550.9980.9220.8110.914
      Locus300.9830.7620.9810.9921.00.9310.942
      PointNetVLAD580.8820.7910.7340.9530.7670.1290.709
      SemGraph610.9600.8590.8970.9440.9840.7830.904
    Tools

    Get Citation

    Copy Citation Text

    Wen HAO, Wenjing ZHANG, Wei LIANG, Zhaolin XIAO, Haiyan JIN. Scene recognition for 3D point clouds: a review[J]. Optics and Precision Engineering, 2022, 30(16): 1988

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Information Sciences

    Received: Nov. 27, 2021

    Accepted: --

    Published Online: Sep. 22, 2022

    The Author Email: Wen HAO (haowensxsf@163.com)

    DOI:10.37188/OPE.20223016.1988

    Topics