• Acta Optica Sinica
  • Vol. 38, Issue 8, 0815014 (2018)
Gang Wang1、2、*, Zhongchen Shi1、2, Yang Shang1、2、*, and Qifeng Yu1、2、*
Author Affiliations
  • 1 College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, Hunan 410073, China
  • 2 Hunan Provincial Key Laboratory of Image Measurement and Vision Navigation, Changsha, Hunan 410073, China
  • show less
    DOI: 10.3788/AOS201838.0815014 Cite this Article Set citation alerts
    Gang Wang, Zhongchen Shi, Yang Shang, Qifeng Yu. Automatic Extraction of Diagonal Markers Based on Template Matching and Peaks of Gradient Histogram[J]. Acta Optica Sinica, 2018, 38(8): 0815014 Copy Citation Text show less
    Results of different stages in getting candidate markers. (a) Template matching; (b) response map by NCC; (c) NCC thresholding; (d) candidate markers; (e) ordering thresholding; (f) Gaussian filtering
    Fig. 1. Results of different stages in getting candidate markers. (a) Template matching; (b) response map by NCC; (c) NCC thresholding; (d) candidate markers; (e) ordering thresholding; (f) Gaussian filtering
    Detection graphs of diagonal lines with LSD. (a) Topography of the diagonal marker; (b) extraction results of LSD; (c) lines merging results
    Fig. 2. Detection graphs of diagonal lines with LSD. (a) Topography of the diagonal marker; (b) extraction results of LSD; (c) lines merging results
    Oriented gradient of the diagonal marker. (a) Gradient directions; (b) histogram of original image; (c) histogram of original image rotated 45°
    Fig. 3. Oriented gradient of the diagonal marker. (a) Gradient directions; (b) histogram of original image; (c) histogram of original image rotated 45°
    Flowchart of diagonal markers' automatic extraction method
    Fig. 4. Flowchart of diagonal markers' automatic extraction method
    Robustness test. (a) Different illuminations; (b) different perspectives; (c) complex environment
    Fig. 5. Robustness test. (a) Different illuminations; (b) different perspectives; (c) complex environment
    Universality test. (a) Square diagonal marker; (b) coded circular diagonal marker; (c) checkerboard
    Fig. 6. Universality test. (a) Square diagonal marker; (b) coded circular diagonal marker; (c) checkerboard
    Results of checkerboard corner detection
    Fig. 7. Results of checkerboard corner detection
    Image numberMaximum deviations /pixelAverage deviations /pixelDeviations ≤0.1 pixel /%
    10.31300.017099.29
    20.22230.016498.57
    30.20680.016698.57
    40.32670.019595.00
    50.27770.018298.57
    60.41730.022197.86
    70.14270.015198.57
    80.09880.0147100
    Table 1. Deviations of checkerboard corner detection by two methods
    Gang Wang, Zhongchen Shi, Yang Shang, Qifeng Yu. Automatic Extraction of Diagonal Markers Based on Template Matching and Peaks of Gradient Histogram[J]. Acta Optica Sinica, 2018, 38(8): 0815014
    Download Citation