Chinese Journal of Lasers, Volume. 50, Issue 13, 1310001(2023)

A Method for Ground Filtering of Laser Point Cloud and Extraction of Tunnel Wall and Target Sphere

Yong Li1,3, Yinzheng Luo1, Qipeng Pu1, Mingfei Han2、*, and Feng Shuang1
Author Affiliations
  • 1Guangxi Key Laboratory of Intelligent Control and Maintenance of Power Equipment, School of Electrical Engineering, Guangxi University, Nanning 530004, Guangxi, China
  • 2Department of Digital Information, Hebei Institute of International Business and Economics, Qinhuangdao 066311,Hebei, China
  • 3Artificial Intelligence Key Laboratory of Sichuan Province, Yibin 644000, Sichuan, China
  • show less
    Figures & Tables(13)
    Flowchart of the proposed algorithm. (a) Ground filtering processing; (b) tunnel wall extraction process; (c) target ball extraction process
    Flowchart of ground filtering algorithm combining RANSAC plane fitting with pass-through filtering based on normal evaluation
    Tunnel wall and target ball processing state at each stage. (a) DBSCAN coarse segmentation of region of interest; (b) area where target balls may be distributed; (c) tunnel wall; (d) spherical surface fitting; (e) visualization of fitting target balls; (f) distribution of fitted target balls in original tunnel
    Original tunnel point cloud data. (a) Schematic of Scene 1; (b) schematic of Scene 2
    Schematic of volume of intersecting part of two spheres
    Poor filtering effect. (a) Ground owe-filtering during pass-through filtering; (b) ground over-filtering during pass-through filtering; (c) ground anomaly during RANSAC plane fitting
    Filtering error accuracy and Kappa coefficient distribution. (a) Total error of nine filtering methods; (b) Kappa coefficient of nine filtering methods
    Ground filtering effects for Scene 1 ( red point indicates tunnel ground point cloud and blue point indicates non-tunnel ground point cloud). (a) Ground truth; (b) method 1; (c) method 2; (d) method 3; (e) method 4; (f) method 5; (g) method 6; (h) method 7; (i) method 8; (j) our method
    Ground filtering effect for Scene 2 ( red point indicates tunnel ground point cloud and blue point indicates non-tunnel ground point cloud). (a) Ground truth; (b) method 1; (c) method 2; (d) method 3; (e) method 4; (f) method 5; (g) method 6; (h) method 7; (i) method 8; (j) our method
    • Table 1. Point statistics of experimental dataset

      View table

      Table 1. Point statistics of experimental dataset

      Scene

      Quantity of ground

      points

      Quantity of off-ground points
      Scene 1213968613360430
      Scene 28700633024774
    • Table 2. Construction modes of each ground filtering method

      View table

      Table 2. Construction modes of each ground filtering method

      MethodGround filter method
      Method 1Cloth simulation filter(CSF)19
      Method 2Slope filter21
      Method 3Region growing filter26
      Method 4Grid elevation filter35
      Method 5Pass-through filter
      Method 6RANSAC
      Method 7RANSAC+normal estimation
      Method 8RANSAC+normal estimation+pass-through filter
      OursVoxel downsampling+RANSAC+normal estimation+pass-through filter
    • Table 3. Filtering accuracy evaluation results

      View table

      Table 3. Filtering accuracy evaluation results

      SceneMethoda0b0c0d0EType I /%ETypeⅡ /%ETotal /%KKappa /%Time /s
      Scene 1Method 1211794621740220753131396771.001.651.5693.6743.56
      Method 2941344119834253821335504856.010.047.7757.3992.59
      Method 3111426810254184478671291256347.923.359.5054.959869.62
      Method 418646642674318086151309299912.852.003.5085.2746.11
      Method 5213966026385993129744370.012.892.4990.274.337
      Method 6128013285955418281335860240.170.015.5671.92354.45
      Method 7156768057200629781335745226.730.023.7182.45360.44
      Method 820367491029376954133534764.810.050.7196.96357.36
      Ours21240601562668303132921270.730.500.5497.758.73
      Scene 2Method 18315253853816897428558004.435.595.3385.4212.78
      Method 26997081703557154301762019.570.244.5685.9222.89
      Method 3264733605330510681251409369.5716.8828.6514.09899.45
      Method 4855390146738715729376171.692.882.6192.6811.60
      Method 58700402313378028909940.034.423.4490.611.18
      Method 67086151614482211302256318.560.074.2087.0588.77
      Method 77566471134163674302110013.040.123.0190.9394.38
      Method 886901610476328529614890.122.091.6595.3692.13
      Ours86832817354354029812340.201.441.1696.713.50
      Average accuracy of our method for two scenes0.470.970.8597.236.12
    • Table 4. Fitting results of target sphere

      View table

      Table 4. Fitting results of target sphere

      SphereMethodRadius /mCenter coordinateEdistance /mRfit /%
      Sphere 01

      RMS

      Manual+RANSAC

      Manual+NLS

      DBRTS+NLS

      0.07035

      0.07027

      0.07167

      0.07128

      [3.83904,-16.09806,902.3149]

      [3.83896,-16.09745,902.3160]

      [3.83973,-16.09924,902.3151]

      [3.83933,-16.09884,902.3151]

      0.00129 0.00138

      0.00136

      98.4655 99.9975

      99.8583

      Sphere 02

      RMS

      Manual+RANSAC

      Manual+NLS

      DBRTS+NLS

      0.07106

      0.07208

      0.07153

      0.07099

      [0.31248,-12.10221,901.3812]

      [0.31056,-12.10076,901.3817]

      [0.31239,-12.10131,901.3812]

      [0.31255,-12.10242,901.3810]

      0.00160 0.00091

      0.00029

      99.1556 99.7815

      99.5304

      Sphere 03

      RMS

      Manual+RANSAC

      Manual+NLS

      DBRTS+NLS

      0.07080

      0.07219

      0.06996

      0.06954

      [13.3178,-1.87194,901.2911]

      [13.3082,-1.87553,901. 2895]

      [13.3148,-1.87130,901.28954]

      [13.3143,-1.87129901.28960]

      0.01036

      0.00339 0.00387

      91.6317 94.4794

      92.9250

    Tools

    Get Citation

    Copy Citation Text

    Yong Li, Yinzheng Luo, Qipeng Pu, Mingfei Han, Feng Shuang. A Method for Ground Filtering of Laser Point Cloud and Extraction of Tunnel Wall and Target Sphere[J]. Chinese Journal of Lasers, 2023, 50(13): 1310001

    Download Citation

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

    Category: remote sensing and sensor

    Received: May. 10, 2022

    Accepted: Aug. 1, 2022

    Published Online: Jun. 6, 2023

    The Author Email: Mingfei Han (66073183@qq.com)

    DOI:10.3788/CJL220845

    Topics