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

A fixed-point implementation and performance analysis of EGML moving object detection algorithm

EGML 이동 객체 검출 알고리듬의 고정소수점 구현 및 성능 분석

  • An, Hyo-sik (School of Electronic Engineering, Kumoh National Institute of Technology) ;
  • Kim, Gyeong-hun (School of Electronic Engineering, Kumoh National Institute of Technology) ;
  • Shin, Kyung-wook (School of Electronic Engineering, Kumoh National Institute of Technology)
  • Received : 2015.06.24
  • Accepted : 2015.07.31
  • Published : 2015.08.20
Download PDF
⟨ Previous Next ⟩

Abstract

An analysis of hardware design conditions of moving object detection (MOD) algorithm is described, which is based on effective Gaussian mixture learning (EGML). A simulation model of EGML algorithm is implemented using OpenCV, and the effects of some parameter values on background learning time and MOD sensitivity are analyzed for various images. In addition, optimal design conditions for hardware implementation of EGML-based MOD algorithm are extracted from fixed-point simulations for various bit-widths of parameters. The proposed fixed-point model of the EGML-based MOD uses only half of the bit-width at the expense of the loss of MOD performance within 0.5% when compared with floating-point MOD results.

EGML (effective Gaussian mixture learning) 기반 이동 객체 검출 (moving object detection; MOD) 알고리듬의 하드웨어 구현을 위한 설계조건을 분석하였다. EGML 알고리듬을 OpenCV 소프트웨어로 구현하고 다양한 영상들에 대한 시뮬레이션을 통해 배경학습 시간과 이동 객체 검출에 영향을 미치는 파라미터 조건을 분석하였다. 또한, 고정소수점 시뮬레이션을 통해 파라미터들의 비트 길이가 이동 객체 검출 성능에 미치는 영향을 평가하고, 최적 하드웨어 설계 조건을 도출하였다. 본 논문의 파라미터 비트 길이를 적용한 고정소수점 이동 객체 검출 모델은 부동소수점 연산 대비 약 절반의 비트 길이를 사용하면서 MOD 성능의 차이는 0.5% 이하이다.

Keywords

Acknowledgement

Grant : 사물인터넷 기반 영상보안용 초저전력 SoC 핵심 IP 기술 개발

References

  1. J. Hsiehm, S. Yu, Y. Chen, and W. Hu, “Automatic traffic surveillance system for vehicle tracking and classification,” IEEE transactions on Intelligent Transportation Systems, vol. 7, no 2, pp. 175-187, 2006. https://doi.org/10.1109/TITS.2006.874722
  2. J. Black, S. Velastin, and B. Boghossian, “A real time surveillance system for metropolitan railways,” IEEE Conf. on Advanced Video and Signal Based Surveillance, pp. 189-194, Sep. 2005.
  3. C. Stauffer, and W. Grimson, “Adaptive background mixture models for real-time tracking,” Proc. Computer Vision and Pattern Recognition, vol. 2, pp. 246-252, Jun. 1999.
  4. D. Lee, “Effective Gaussian Mixture Learning for Video Background Subtraction,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 27, no. 5, pp. 827-832, May 2005. https://doi.org/10.1109/TPAMI.2005.102
  5. S. Kulchandani, and J. Dangarwala, “Moving object detection: Review of recent research trends,” Pervasive Computing (ICPC), 2015 International Conference, Jan. 2015.
  6. M. Piccardi, “Background subtraction techniques: A review,” Proc. IEEE Int. Conf. Syst., Man Cybern., vol. 4, pp. 3099-3104, Oct. 2004.
  7. K. Kim, T. Chalidabhongse, D. Harwood, and L. Davis, “Real-time foreground-background segmentation using code-book model,” Real-Time Imag., Special Issue on Video Object Processing, vol. 11, pp. 172-185, Jun. 2005.
  8. A. Elgammal, R. Duraiswami, D. Harwood, and L.S. Davis, “Background and foreground modeling using nonparametric kernel density estimation for visual surveillance,” Proc. IEEE, vol. 90, no. 7, pp. 1151-1163, Jul. 2002. https://doi.org/10.1109/JPROC.2002.801448
  9. Xia Dong, Kedian Wang, and Guohua Jia, “Moving Object and Shadow Detection Based on RGB Color Space and Edge Ratio,” IEEE 2nd International Conf. on Image and Signal Processing, pp. 1 -5, Oct. 2009.
  10. Jin Min Choi, Hyung Jin Chang, Yung Jun Yoo, and Jin Young Choi, “Robust moving object detection against fast illumiation change,” Computer Vision and Image Understanding, pp. 179-193, 2012. https://doi.org/10.1016/j.cviu.2011.10.007
  11. Jinhai Xiang, Heng Fan, Honghong Liao, Jun Xu, Weiping Sun, and Shengsheng Yu, “Moving object detection and Shadow Removing under Changing Illumination Condition,” Mathematical Problems in Engineering, pp. 1-10, Feb. 2014.
  12. P. Suo, and Y. Wang, “An improved adaptive background modeling algorithm based on Gaussian Mixture Model,” ICSP 2008. 9th International Conference on, Oct. 2008.
  13. P.-L. St-Charles, G.-A. Bilodeau, and R. Bergevin, “A Self-Adjusting Approach to Change Detection Based on Background Word Consensus,” IEEE Winter Conference on Applications of Computer Vision (WACV), Jan. 6-9, 2015.
  14. M. Hofmann, P. Tiefenbacher, and G. Rigoll, “Background Segmentation with Feedback: The Pixel-Based Adaptive Segmenter,” Proc. of IEEE Workshop on Change Detection, June, 2012.
  15. M. Van Droogenbroeck, and O. Paquot, “Background Subtraction: Experiments and Improvements for ViBe,” Proc of IEEE Workshop on Change Detection, CVPR, June, 2012
  16. J. S Lim, “Hardware Implementation of Background Subtraction Algorithm,” Graduate School, Kyungbuk University, Dec. 2006.