Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 55, Issue 12, 122802(2018)

Individual Tree Crown Extraction in High Resolution Remote Sensing Image Based on Iterative H-minima Improved Watershed Algorithm

Wenxiu Teng1,2, Xiaorong Wen1,2、*, Ni Wang3,4, and Huihui Shi3
Author Affiliations
  • 1 College of Forest, Nanjing Forestry University, Nanjing, Jiangsu 210037, China
  • 2 Co-Innovation Center for Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing, Jiangsu 210037, China
  • 3 School of Geographic Information and Tourism, Chuzhou University, Chuzhou, Anhui 239000, China
  • 4 Anhui Engineering Laboratory of Geographical Information Intelligent Sensor and Service, Chuzhou, Anhui 239000, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (10)
    Equations (0)
    References (21)
    Cited By (2)
    Tools
    Paper Information
    Topics
    Figures & Tables(10)
    Process of image preprocessing. (a) Original image; (b) gray image; (c) image after morphological open operation; (d) gradient image; (e) image after mean filter denoising; (f) binary image

    Fig. 1. Process of image preprocessing. (a) Original image; (b) gray image; (c) image after morphological open operation; (d) gradient image; (e) image after mean filter denoising; (f) binary image

    Download full size
    Marker extraction results with different h values. (a) h=1; (b) h=2; (c) h=3

    Fig. 2. Marker extraction results with different h values. (a) h=1; (b) h=2; (c) h=3

    Download full size
    Process of overlap markers detection. (a) Original image; (b) tree crown markers when h is 1; (c) tree crown markers when h is 2; (d) image with marker dilation; (e) filtered image; (f) marked image

    Fig. 3. Process of overlap markers detection. (a) Original image; (b) tree crown markers when h is 1; (c) tree crown markers when h is 2; (d) image with marker dilation; (e) filtered image; (f) marked image

    Download full size
    Images obtained with different h values. (a) h=1; (b) h=2; (c) h=3; (d) h=4; (e) h=5; (f) h=6

    Fig. 4. Images obtained with different h values. (a) h=1; (b) h=2; (c) h=3; (d) h=4; (e) h=5; (f) h=6

    Download full size
    Tree crown extraction. (a) Original image; (b) detection marker; (c) traditional algorithm; (d) proposed algorithm in this paper

    Fig. 5. Tree crown extraction. (a) Original image; (b) detection marker; (c) traditional algorithm; (d) proposed algorithm in this paper

    Download full size
    Symmetric growth principle

    Fig. 6. Symmetric growth principle

    Download full size
    Result of markers growth

    Fig. 7. Result of markers growth

    Download full size
    Individual tree crown extraction. (a) Remote sensing image of sample 1; (b) reference tree crown of sample 1; (c) extraction of sample 1 with marker-controlled watershed segmentation algorithm; (d) extraction of sample 1 with proposed algorithm in this paper; (e) remote sensing image of sample 2; (f) reference tree crown of sample 2; (g) extraction of sample 2 with marker-controlled watershed segmentation algorithm; (h) extraction of sample 2 with proposed algorithm in this paper

    Fig. 8. Individual tree crown extraction. (a) Remote sensing image of sample 1; (b) reference tree crown of sample 1; (c) extraction of sample 1 with marker-controlled watershed segmentation algorithm; (d) extraction of sample 1 with proposed algorithm in this paper; (e) remote sensing image of sample 2; (f) reference tree crown of sample 2; (g) extraction of sample 2 with marker-controlled watershed segmentation algorithm; (h) extraction of sample 2 with proposed algorithm in this paper

    Download full size

    • Table 1. Accuracy assessment of individual tree position

      View table

      Table 1. Accuracy assessment of individual tree position

      SampleAlgorithmDetectionnumberReferencenumberCorrectnumberDetectionrate /%Producer'saccuracy /%User'saccuracy /%
      Sample 1Marker-controlledwatershed algorithm84927191.3077.1784.52
      Proposed algorithmin this paper939286101.0993.4892.47
      Sample 2Marker-controlledwatershed algorithm71835785.5468.6780.28
      Proposed algorithmin this paper848381101.2097.5996.43

    • Table 2. Accuracy assessment of tree crown contour

      View table

      Table 2. Accuracy assessment of tree crown contour

      SampleAlgorithmDetectionnumberReferencenumberCorrectnumberRelativeerror /%Accuracyrate /%Recallrate /%Fmeasurement /%
      Sample 1Marker-controlledwatershed algorithm84925216.5161.9056.5259.09
      Proposed algorithmin this paper9392844.4190.3291.3090.81
      Sample 2Marker-controlledwatershed algorithm71834813.2167.6157.8362.34
      Proposed algorithmin this paper8483793.0594.0595.1894.61
    Tools

    Get Citation

    Copy Citation Text

    Wenxiu Teng, Xiaorong Wen, Ni Wang, Huihui Shi. Individual Tree Crown Extraction in High Resolution Remote Sensing Image Based on Iterative H-minima Improved Watershed Algorithm[J]. Laser & Optoelectronics Progress, 2018, 55(12): 122802

    Download Citation

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

    Category: Remote Sensing and Sensors

    Received: Apr. 11, 2018

    Accepted: Jun. 21, 2018

    Published Online: Aug. 1, 2019

    The Author Email: Xiaorong Wen (njw9872e@163.com)

    DOI:10.3788/LOP55.122802

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology