DOI QR코드

DOI QR Code

Useful Image Back-projection Properties in Cameras under Planar and Vertical Motion

평면 및 수직 운동하는 카메라에서 유용한 영상 역투영 속성들

  • Kim, Minhwan (School of Computer Science and Engineering, College of Information and Biomedical Engineering, Pusan National University) ;
  • Byun, Sungmin (School of Computer Science and Engineering, College of Information and Biomedical Engineering, Pusan National University)
  • Received : 2022.07.19
  • Accepted : 2022.07.27
  • Published : 2022.07.31

Abstract

Autonomous vehicles equipped with cameras, such as robots, fork lifts, or cars, can be found frequently in industry sites or usual life. Those cameras show planar motion because the vehicles usually move on a plane. Sometimes the cameras in fork lifts moves vertically. The cameras under planar and vertical motion provides useful properties for horizontal or vertical lines that can be found easily and frequently in our daily life. In this paper, some useful back-projection properties are suggested, which can be applied to horizontal or vertical line images captured by a camera under planar and vertical motion. The line images are back-projected onto a virtual plane that is parallel to the planar motion plane and has the same orientation at the camera coordinate system regardless of camera motion. The back-projected lines on the virtual plane provide useful information for the world lines corresponding to the back-projected lines, such as line direction, angle between two horizontal lines, length ratio of two horizontal lines, and vertical line direction. Through experiments with simple plane polygons, we found that the back-projection properties were useful for estimating correctly the direction and the angle for horizontal and vertical lines.

Keywords

Acknowledgement

This work was supported by a 2-Year Research Grant of Pusan National University

References

  1. J.W. An and Y. Ko, "Ceiling-Based Localization of Indoor Robots Using Ceiling-Looking 2D-LiDAR Rotation Module," Journal of Korea Multimedia Society, Vol. 22, No. 7, pp. 780-789, 2019. https://doi.org/10.9717/KMMS.2019.22.7.780
  2. J. Lee, "Recognition Techniques Applied to Autonomous Cars," Korea Multimedia Society, Vol. 19, No. 4, pp. 18-27, 2015.
  3. J. Xiao, H. Lu, L. Zhang, and J. Zhang, "Pallet Recognition and Localization using an RGB-D Camera," International J ournal of Advanced Robotic Systems, Vol. 14, Issue 6, 2017, (https://doi.org/10.1177/1729881417737799).
  4. S. Byun and M. Kim, "Real-time Positioning and Orienting of Pallets Based on Monocular Vision," Proceeding of 20th International Conference on Tools with Artificial Intelligence (ICTAI), pp. 505-508, 2008.
  5. S. Byun and M. Kim, "Pallet Measurement Method for Automatic Pallet Engaging in Real-Time," Journal of Korea Multimedia Society, Vol. 14, No. 2, pp. 171-181, 2011. https://doi.org/10.9717/KMMS.2011.14.2.171
  6. M. Kim, S. Byun, and J. Kim, "A Vision Based Pallet Measurement Method by Estimating 3D Direction of A Line Parallel to The Ground," Journal of Korea Multimedia Society, Vol. 23, No. 10, pp. 1229-1235, 2020. https://doi.org/10.9717/KMMS.2020.23.10.1229
  7. S. Choi and S. Park, "A Numerical Solution to 2-Point Relative Pose Estimation Problem under Planar Motion," Proceeding of Conference on Information and Control Systems, pp. 376-378, 2014.
  8. Z. Zhang, A Flexible New Technique for Camera Calibration, Technical Report MSRTR-98-71, 1998.
  9. R. Hartley and A. Zisserman, Multiview Geometry in Computer Vision, Cambridge University Press, Cambridge, 2003.
  10. OpenCV: Open Source Computer Vision Library, https://opencv.org/ (accessed July 1, 2022).