DOI QR코드

DOI QR Code

Automatic Target Recognition for Camera Calibration

카메라 캘리브레이션을 위한 자동 타겟 인식

  • Kim, Eui Myoung (Dept. of Spatial Information Engineering, Namseoul University) ;
  • Kwon, Sang Il (Dept. of GIS Engineering, Namseoul University)
  • Received : 2018.11.19
  • Accepted : 2018.12.10
  • Published : 2018.12.31

Abstract

Camera calibration is the process of determining the parameters such as the focal length of a camera, the position of a principal point, and lens distortions. For this purpose, images of checkerboard have been mainly used. When targets were automatically recognized in checkerboard image, the existing studies had limitations in that the user should have a good understanding of the input parameters for recognizing the target or that all checkerboard should appear in the image. In this study, a methodology for automatic target recognition was proposed. In this method, even if only a part of the checkerboard image was captured using rectangles including eight blobs, four each at the central portion and the outer portion of the checkerboard, the index of the target can be automatically assigned. In addition, there is no need for input parameters. In this study, three conditions were used to automatically extract the center point of the checkerboard target: the distortion of black and white pattern, the frequency of edge change, and the ratio of black and white pixels. Also, the direction and numbering of the checkerboard targets were made with blobs. Through experiments on two types of checkerboards, it was possible to automatically recognize checkerboard targets within a minute for 36 images.

카메라 캘리브레이션은 카메라의 초점거리, 주점위치, 렌즈왜곡 등의 매개변수를 결정하는 작업으로 이를 위해서 주로 체커보드를 촬영한 영상을 사용하고 있다. 체커보드 영상에서 타겟을 자동으로 인식할 때 기존의 연구는 사용자가 타겟인식을 위한 입력 매개변수를 잘 이해하고 있어야 하거나 영상에서 체커보드가 모두 나타나야 하는 한계점이 있었다. 이에 본 연구에서는 체커보드 중심부와 외곽부분에 각각 4개씩 8개의 블랍을 포함하는 직사각형을 이용하여 체커보드 영상의 일부만 촬영된 경우에도 자동으로 타겟점의 번호를 부여할 수 있고 별도의 입력 매개 변수 없이 자동으로 타겟을 인식하는 방법을 제안하였다. 본 연구에서 체커보드 타겟의 중심점을 자동으로 추출하기 위해서 흑백패턴의 왜곡, 경계선 변화빈도, 흑백픽셀의 비율의 3가지 조건을 이용하였다. 또한 체커보드의 방향성과 번호부여는 블랍을 이용하였다. 두 가지 타입의 체커보드에 대한 실험을 통해서 36장의 영상에 대해 1분 이내의 짧은 시간에 체커보드 타겟을 자동으로 인식할 수 있었다.

Keywords

GCRHBD_2018_v36n6_525_f0001.png 이미지

Fig. 1. Chessboard target

GCRHBD_2018_v36n6_525_f0002.png 이미지

Fig. 2. Checkerboard target

GCRHBD_2018_v36n6_525_f0003.png 이미지

Fig. 3. Structure of blob

GCRHBD_2018_v36n6_525_f0004.png 이미지

Fig. 4. Methodology of target extraction

GCRHBD_2018_v36n6_525_f0005.png 이미지

Fig. 5. Circular search of pixel values based on extracted keypoint

GCRHBD_2018_v36n6_525_f0006.png 이미지

Fig. 6. Condition of the distortion of black and white pattern

GCRHBD_2018_v36n6_525_f0007.png 이미지

Fig. 7. Condition of the frequency of edge change

GCRHBD_2018_v36n6_525_f0008.png 이미지

Fig. 8. Condition of the ratio of black and white pixel

GCRHBD_2018_v36n6_525_f0009.png 이미지

Fig. 9. Procedure of identifying the number of blobs

GCRHBD_2018_v36n6_525_f0010.png 이미지

Fig. 10. Angle calculation of polygon

GCRHBD_2018_v36n6_525_f0011.png 이미지

Fig. 11. Determining the rectangle containing blob

GCRHBD_2018_v36n6_525_f0012.png 이미지

Fig. 12. Identifying the blob contained within rectangle

GCRHBD_2018_v36n6_525_f0013.png 이미지

Fig. 13. Mis-detected target

GCRHBD_2018_v36n6_525_f0014.png 이미지

Fig. 15. Angle calculation between targets

GCRHBD_2018_v36n6_525_f0015.png 이미지

Fig. 16. Define the direction of blobs

GCRHBD_2018_v36n6_525_f0016.png 이미지

Fig. 17. Comparison of line length using rectangle containing blob for direction determination

GCRHBD_2018_v36n6_525_f0017.png 이미지

Fig. 18. Labeling of targets

GCRHBD_2018_v36n6_525_f0018.png 이미지

Fig. 19. Sequential numbering of target points

GCRHBD_2018_v36n6_525_f0019.png 이미지

Fig. 20. Detection of rectangles containing blobs for projective transformation

GCRHBD_2018_v36n6_525_f0020.png 이미지

Fig. 21. Result of homography transformation

GCRHBD_2018_v36n6_525_f0021.png 이미지

Fig. 22. Location of the target from reference and template images

GCRHBD_2018_v36n6_525_f0022.png 이미지

Fig. 23. More than one keypoint

GCRHBD_2018_v36n6_525_f0023.png 이미지

Fig. 25. Canon EOS 800D

GCRHBD_2018_v36n6_525_f0024.png 이미지

Fig. 26. Two types of checkerboard

GCRHBD_2018_v36n6_525_f0025.png 이미지

Fig. 27. Captured images of checkerboard type A

GCRHBD_2018_v36n6_525_f0026.png 이미지

Fig. 28. Captured images of checkerboard type B

GCRHBD_2018_v36n6_525_f0027.png 이미지

Fig. 29. Area ratio of a checkerboard in the image(11%)

GCRHBD_2018_v36n6_525_f0028.png 이미지

Fig. 30. Area ratio of a checkerboard in the image(4%)

GCRHBD_2018_v36n6_525_f0029.png 이미지

Fig. 14. Target array in four edges

GCRHBD_2018_v36n6_525_f0030.png 이미지

Fig. 24. one keypoint

Table 1. Camera setting

GCRHBD_2018_v36n6_525_t0001.png 이미지

Table 2. Detection rate of checkerboard targets

GCRHBD_2018_v36n6_525_t0002.png 이미지

References

  1. Kwon, S.I. and Kim, E.M. (2018), Blob configuration for target estimation of multi-camera checker board images, 2018 Joint fall conference, 18 November 2018, Jeju, Korea, pp. 50-51.
  2. Fursattel, P., Dotenco, S., Placht, S., Balda, M., Maier, A., and Riess, C. (2016), OCPAD - Occluded checkerboard pattern detector, 2016 IEEE Winter Conference on Applications of Computer Vision, 7-10 March 2016, NY, USA, pp. 1-9.
  3. Lari, Z., Habib, A., Mazaheri, M., and Al-Durgham, K. (2013), Multi-camera system calibration with built-in relative orientation constraints(part 2) - Automation, implementation, and experimental results, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, Vol. 32, No. 3, pp. 205-216. https://doi.org/10.7848/ksgpc.2014.32.3.205
  4. Habib, A., Lari, Z., Kwak, E., and Al-Durgham, K. (2013), Automated detection, localization, and identification of signalized targets and their impact on digital camera calibration, Revista Brasileira de Cartografia, Vol. 65, No. 4, pp. 785-803.
  5. Oh, S.Y. and Cho, N.I. (2016), Finding locating checker board using corner detection and interpolation, 2016 Conference of The Korean Society Of Broad Engineers, The Korean Society Of Broad Engineers, 4 November 2016, Seoul, Korea, pp. 165-168.
  6. Park, J.M., Lee, J.I., Cho, J.B., and Lee, J.W. (2015), Precise detection of coplanar checkerboard corner points for stereo camera calibration using a single frame, Journal of Institute of Control, Robotics and Systems, Vol. 21, No. 7, pp. 602-608. (in Korean with English abstract) https://doi.org/10.5302/J.ICROS.2015.15.0011
  7. Placht, S., Mengue, E.A., Hofmann, H., Schaller, C., and Balda, M. (2014), ROCHADE: Robust Checkerboard Advanced Detection for Camera Calibration, 2014 European Conference on Computer Vision, 6-12 September 2014, Zurich, Switzerland, pp. 766-779.
  8. Rufli, M., Scaramuzza, D., and Siegwart, R. (2008), Automatic detection of checkerboards on blurred and distorted images, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, Intelligent Robots and Systems, 22-26 September 2008, Nice, France, pp. 3121-3126.
  9. Yu, Y.J. (2015), Automatic Checkerboard Corner Detection for Camera Calibration, Master's thesis, Dongkuk University, Seoul, Korea, 49p.

Cited by

  1. 체커보드의 유형에 따른 스테레오 카메라 캘리브레이션의 정확도 비교 vol.38, pp.6, 2020, https://doi.org/10.7848/ksgpc.2020.38.6.511
  2. 근거리 사진측량을 위한 스테레오 카메라의 안정성 분석 vol.39, pp.3, 2018, https://doi.org/10.7848/ksgpc.2021.39.3.123