Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Pedestrian-Based Variational Bayesian Self-Calibration of Surveillance Cameras

보행자 기반의 변분 베이지안 감시 카메라 자가 보정

  • Received : 2019.07.09
  • Accepted : 2019.07.19
  • Published : 2019.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Pedestrian-based camera self-calibration methods are suitable for video surveillance systems since they do not require complex calibration devices or procedures. However, using arbitrary pedestrians as calibration targets may result in poor calibration accuracy due to the unknown height of each pedestrian. To solve this problem in the real surveillance environments, this paper proposes a novel Bayesian approach. By assuming known statistics on the height of pedestrians, we construct a probabilistic model that takes into account uncertainties in both the foot/head locations and the pedestrian heights, using foot-head homology. Since solving the model directly is infeasible, we use variational Bayesian inference, an approximate inference algorithm. Accordingly, this makes it possible to estimate the height of pedestrians and to obtain accurate camera parameters simultaneously. Experimental results show that the proposed algorithm is robust to noise and provides accurate confidence in the calibration.

보행자 기반의 카메라 자가 보정 방법들은 복잡한 보정 장치나 절차가 필요하지 않기 때문에 비디오 감시 시스템에 적합하다. 하지만 임의 보행자를 보정 대상으로 사용하는 경우 보행자들의 키를 모르기 때문에 보정 정확도가 저하될 수 있다. 본 논문은 실제 감시 환경에서 이 문제를 해결하기 위한 베이지안 보정 방법을 제안한다. 제안하는 방법에서는 감시 지역 사람들의 키에 대한 통계가 있다고 가정하고, 발-머리 호몰로지(foot-head homology)를 사용하여, 발과 머리의 좌표와 보행자 키의 불확실성을 모두 고려하는 확률 모델을 구성한다. 이 확률 모델을 직접 푸는 것은 난해하므로, 본 연구에서는 근사적 방법인 변분 베이지안 추론(variational Bayesian inference)을 사용한다. 따라서, 이를 통해 관측된 보행자들의 키를 추정함과 동시에 정확한 카메라 파라미터를 구할 수 있다. 다양한 실험을 통해 제안된 방법이 노이즈에 강하며, 보정에 대한 정확한 신뢰도를 제공함을 보였다.

Keywords

References

  1. G. Fuhr and C. R. Jung, "Camera Self-Calibration Based on Nonlinear Optimization and Applications in Surveillance Systems," IEEE Transactions on Circuits and Systems for Video Technology, vol. 27, no. 5, pp. 1132-1142, May. 2017. https://doi.org/10.1109/TCSVT.2015.2511812
  2. N. Krahnstoever, and P. R. S. Mendonca, "Bayesian Autocalibration for Surveillance," in Proceeding of the 10th IEEE International Conference on Computer Vision, pp. 1858-1865, 2005.
  3. J. Liu, R. Collins, and Y. Liu, "Surveillance Camera Autocalibration based on Pedestrian Height Distributions," in Proceedings of the British Machine Vision Conference, pp. 117.1-117.11, 2011.
  4. G. M. Y. E. Brouwers, M. H. Zwemer, R. G. J. Wijnhoven, and P. H. N. de With, "Automatic Calibration of Stationary Surveillance Cameras in the Wild," in Proceedings of European Conference on Computer Vision, pp. 743-759, 2016.
  5. S. Huang, X. Ying, J. Rong, Z. Shang, and H. Zha, "Camera Calibration from Periodic Motion of a Pedestrian," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3025-3033, 2016.
  6. Z. Tang. Y. Lin, K. Lee, J. Hwang, J. Chuang, and Z. Fang, "Camera self-calibration from tracking of moving persons," in 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 265-270, 2016.
  7. X. Li, Y. Cheng, and T. Zhang, "Robust extrinsic calibration from pedestrians," Signal Processing: Image Communication, vol. 55, no. C, pp. 106-120, July. 2017. https://doi.org/10.1016/j.image.2017.03.006
  8. C. M. Bishop, Pattern Recognition and Machine Learning, 1st ed. Springer, 2006.
  9. R. Hartley, and A. Zisserman, Multiple View Geometry in Computer Vision, 2rd ed. Cambridge University Press, 2003.
  10. J. Berclaz, F. Fleuret, E. Turetken, and P. Fua, "Multiple Object Tracking Using K-Shortest Paths Optimization," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 9, pp. 1806-1819, Sep. 2011. https://doi.org/10.1109/TPAMI.2011.21
  11. H. Possegger, M. Ruther, S. Sternig, T. Mauthner, M. Klopschitz, P. M. Roth, and H. Bischof, "Unsupervised Calibration of Camera Networks and Virtual PTZ Cameras," in Proceedings of Computer Vision Winter Workshop (CVWW), pp. 1-8, 2012.
  12. J. Redmon, and A. Farhadi, "YOLO9000: Better, Faster, Stronger," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517-6525, 2017.