• DocumentCode
    1735758
  • Title

    The landmarks aegion extraction algorithm based on target in three-dimensional measurement system

  • Author

    Xiong, Xianming ; Hu, Xianjun ; Zhang, Shaobing

  • Author_Institution
    Electr. Eng. & Autom. Dept., Guilin Univ. of Electron. Technol., Guilin, China
  • fYear
    2012
  • Firstpage
    59
  • Lastpage
    62
  • Abstract
    In this paper one landmarks region extraction algorithm based on target in three-dimensional measurement system was introduced. In the three-dimensional measurement system based on target in which the spatial relationship of measured point and landmarks is known, extracting landmarks region exactly is the key to improve the reliability and accuracy of three-dimensional measurement system. The landmarks region extraction algorithm based on two regional contour tracking was proposed in this paper. This algorithm uses Gaussian filter for image filtering which can remove possible noise, and selects the Otsu as threshold value for the thresholding of image, and then uses morphological and two regional contour tracking method for a reasonable landmarks region extraction. Experimental results show that the algorithm can meet the landmarks region extraction requirements under the condition of complex light and large field of measurement.
  • Keywords
    feature extraction; filtering theory; image denoising; measurement systems; object tracking; reliability; target tracking; Gaussian filter; Otsu value; image filtering; image thresholding; landmark region extraction algorithm; regional contour tracking method; reliability; three-dimensional measurement system; threshold value; Algorithm design and analysis; Cameras; Filtering; Interference; Noise; Position measurement; Sea measurements; Landmarks region extraction; Regional contour tracking; Three-dimensional measurement system;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Control, Automatic Detection and High-End Equipment (ICADE), 2012 IEEE International Conference on
  • Conference_Location
    Beijing
  • Print_ISBN
    978-1-4673-1331-5
  • Type

    conf

  • DOI
    10.1109/ICADE.2012.6330099
  • Filename
    6330099