Acta Optica Sinica, Volume. 39, Issue 3, 0315003(2019)

Moving Shadow Detection Based on Regional Radiation Consistency

Haiyong Chen, Lizhong Qie, and Kun Liu*
Author Affiliations
  • School of Artifical Intelligent, Hebei University of Technology, Tianjin 300130, China
  • show less
    Figures & Tables(9)
    Illustration of PCC classification process
    Framework of shadow detection and object mask growth
    Illustration of region growth and Vibe object mask fusion
    (a) Result of region growth and mask fusion. (a) Ground truth image; (b) super-pixel segmentation image; (c) segmentation of moving object; (d) classified PCC result; (e) first stage of shadow PCC growth(green part); (f) second stage of shadow PCC growth(red part); (g) result of object PCC growth; (h) result of object mask fusion
    Experimental results of highway I sequence
    Algorithm processing in different scenarios
    Test results of 5 algorithms
    • Table 1. Appraisal results of five algorithms%

      View table

      Table 1. Appraisal results of five algorithms%

      MethodPerformance
      CampusHallwayHighway ILabBusStation
      rsξrsξrsξrsξrsξ
      Ref. [26]35.3386.8278.4369.4957.8482.4846.3385.8880.7963.5
      Ref. [27]57.3848.0882.5381.7286.2358.6882.8775.0888.6161.5
      Ref. [28]79.9958.9255.1779.864.0582.2952.4980.5485.353.52
      Ref. [29]78.6758.1484.5678.7591.0058.1459.1281.3573.2484.24
      Proposed method80.9888.283.1385.7986.0182.5379.5485.8183.1388.95
    • Table 2. Growth rate and accuracy of object mask

      View table

      Table 2. Growth rate and accuracy of object mask

      ParameterVideo sequence
      CampusHallwayHighway ILabBusStation
      γ11.448.693.9311.838.32
      δ96.7595.5296.8195.3494.25
    Tools

    Get Citation

    Copy Citation Text

    Haiyong Chen, Lizhong Qie, Kun Liu. Moving Shadow Detection Based on Regional Radiation Consistency[J]. Acta Optica Sinica, 2019, 39(3): 0315003

    Download Citation

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

    Category: Machine Vision

    Received: Apr. 20, 2018

    Accepted: Nov. 8, 2018

    Published Online: May. 10, 2019

    The Author Email:

    DOI:10.3788/AOS201939.0315003

    Topics