DOI QR코드

DOI QR Code

Height Estimation of pedestrian based on image

영상기반 보행자 키 추정 방법

  • Received : 2014.07.10
  • Accepted : 2014.09.19
  • Published : 2014.09.30

Abstract

Object recognition is one of the key technologies of the monitoring system for the prevention of various intelligent crimes. The height is one of the physical information of a person, and it may be important information for identification of the person. In this paper, a method which can detect pedestrians from CCTV images and estimate the height of the detected objects, is proposed. In this method, GMM (Gaussian Mixture Model) method was used to separate the moving object from the background and the pedestrian was detected using the conditions such as the width-height ratio and the size of the candidate objects. The proposed method was applied to the CCTV video, and the height of the pedestrian at far-distance, middle- distance, near-distance was estimated for the same person, and the accuracy was evaluated. Experimental results showed that the proposed method can estimate the height of the pedestrian as the accuracy of 97% for the short-range, 98% for the medium-range, and more than 97% for the far-range. The image sizes for the same pedestrian are different as the position of him in the image, it is shown that the proposed algorithm can estimate the height of pedestrian for various position effectively.

객체인식은 지능적이고 다양화된 범죄 예방을 위한 영상 감시 시스템에서 중요한 기술 중 하나이다. 사람의 신체 정보인 키는 그 대상이 가지고 있는 신체적인 특징 중 하나로 신원을 확인하는데 중요한 정보가 될 수 있다. 본 논문에서는 CCTV 영상으로부터 보행자를 검출하고 검출된 객체인 보행자의 키를 추정하는 방법을 제안하였다. 이를 위하여 GMM(Gaussian Mixture Model) 방식을 이용하여 움직이는 객체를 분리하고, 분리된 후보 객체들의 가로세로 비율, 크기 등의 조건을 이용하여 보행자를 검출하였다. 제안한 방법을 CCTV 영상에 적용하고 동일 보행자에 대하여 근거리, 중거리, 원거리의 위치에서 키를 추정하고 정확성을 평가하였다. 실험결과 근거리에서 97%, 중거리에서 98%, 원거리에서 97% 이상의 정확도로 키 추정이 가능함을 보였다. 또한 영상내의 보행자는 위치에 따라 크기가 다르지만 실험을 통하여 제안하는 방법이 보행자의 위치에 관계없이 키를 추정하는데 효과적임을 확인하였다.

Keywords

References

  1. H.-M. Moon and S.-B. Pan, "The Human Identification Method in Video Surveillance System," The Korean Institute of Information Technology, vol. 8, no. 5, May 2010, pp. 199-206.
  2. H.-M. Moon and S-B. Pan, "The Analysis of De-identification for Privacy Protection in Intelligent Video Surveillance System," The Korean Institute of Information Technology, vol. 9, no. 7, July 2011, pp. 189-200.
  3. D.-H. Kim, J.-Y. Lee, H.-S. Yoon, and E.-Y. Cha, "A Non-cooperative user authentication system in robot environments," IEEE Trans. Comsumer Electronics, vol. 53, no. 2, May 2007, pp. 804-811. https://doi.org/10.1109/TCE.2007.381763
  4. A. Bovyrin and K. Rodyushkin, "Human height prediction and roads estimation for advanced video surveillance systems," In Proc. IEEE Conf. on Advanced Video and Signal Based Surveillance, vol. 15-16, Como, Italy, Sept. 2005, pp. 219-223.
  5. E. Jeges, I. Kispal, and Z. Hornak, "Measuring human height using calibrated cameras," In Proc. IEEE Conf. on Human System Interactions, vol. 25-27, Krakow, Poland, May 2008, pp. 755-760.
  6. H.-T. Kim, G.-H. Lee, J.-S. Park, and Y.-S. Yu, "Vehicle Detection in Tunnel using Gaussian Mixture Model and Mathematical Morphological Processing," J. of the Korean Institute of Electronic Communication Sciences, vol. 7, no. 5, Oct. 2012, pp. 967-974.
  7. M.-W. Kim, C.-M. Oh, D. Aurrahman, Y.-G. Ahn, and C.-W. Lee, "The Virtual Screen Using Skin tone and GMM Foreground Segmentation," Conf. of The Korea Information Processing Society, vol. 15, no. 1, Kyungil University, Korea, May 2008, pp. 179-181.
  8. D. Koller, J. Weber, T. Huang, J. malik, G. Ogasawara, B. Rao, and S. Russell, "Towards Robust Automatic Traffic Scene Analysis in Real-time," Proc. ICPR'94, vol. 1, Lake Buena Vista, Florida, Oct. 1994, pp. 126-131.
  9. C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," Proc. IEEE CVPR 1994, vol. 2, Fort Collins, Colorado, June 1999, pp. 246-252.
  10. A. Elgammal, D. Harwood, and L. S. Davis, "Non-parametric model for background subtraction," Proc. ECCV 2000, vol. 1843, Dublin, Ireland, June 2000, pp. 751-767.

Cited by

  1. Video Based Pedestrian Height Estimation Using Winer Optimization vol.19, pp.2, 2016, https://doi.org/10.9717/kmms.2016.19.2.264