Journal of the Institute of Electronics Engineers of Korea SC (전자공학회논문지SC)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Distance Estimation Method using Enhanced Adaptive Fuzzy Strong Tracking Kalman Filter Based on Stereo Vision

스테레오 비전에서 향상된 적응형 퍼지 칼만 필터를 이용한 거리 추정 기법

  • 임영철 (대구경북과학기술연구원) ;
  • 이충희 (대구경북과학기술연구원) ;
  • 권순 (대구경북과학기술연구원) ;
  • 이종훈 (대구경북과학기술연구원)
  • Published : 2008.11.25
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose an algorithm that can estimate the distance using disparity based on stereo vision system, even though the obstacle is located in long ranges as well as short ranges. We use sub-pixel interpolation to minimize quantization errors which deteriorate the distance accuracy when calculating the distance with integer disparity, and also we use enhanced adaptive fuzzy strong tracking Kalman filter(EAFSTKF) to improve the distance accuracy and track the path optimally. The proposed method can solve the divergence problem caused by nonlinear dynamics such as various vehicle movements in the conventional Kalman filter(CKF), and also enhance the distance accuracy and reliability. Our simulation results show that the performance of our method improves by about 13.5% compared to other methods in point of root mean square error rate(RMSER).

본 논문에서는 스테레오 비전에서 시차를 이용하여 근거리뿐만 아니라 원거리의 장애 물체에 대해서도 신뢰성 있는 거리를 추정하기 위한 알고리즘을 제안한다. 시차를 이용한 거리 측정에서 양자화 오차는 원거리에서의 거리 정확도를 떨어뜨리게 되므로, 이를 최소화하기 위해 부화소 보간법(sub-pixel interpolation)을 이용하여 시차 정확도를 향상시키고 거리 정확도 및 경로 추적의 최적화를 위해서 향상된 적응형 퍼지 칼만 필터(EAFSTKF : Enhanced Adaptive Fuzzy Strong Tracking Kalman Filter)를 사용한다. 제안한 방법은 차량과 같이 다양한 동적인 움직임에 의한 비선형성에 대하여 기존 칼만 필터에서 발생되는 발산 문제(divergence problem)를 해결할 수 있고, 거리의 정확도 및 신뢰도도 높일 수 있다. 몬테카를로(Monte Carlo) 방법을 이용한 모의실험 결과 제안한 방법은 기존 방법들과 거리 오차율(RMSER : Root Mean Square Error Rate)을 비교하였을 때, strong tracking Kalman filter(STKF)에 비하여 성능이 약 13.5%정도 향상되었음을 보여준다.

Keywords

References

  1. A. N. Ndjeng, S. Glaser and D. Gruyer, 'A Multiple Model Localization System for Outdoor Vehicles,-IEEE Intelligent Vehicles Symposium, pp. 1050-1055 June 2007
  2. B. Mobus, A. Joos, and U. Kolbe, 'Multi-target multi-object radar tracking,' in Proc. IEEE Intelligent Vehicles Symposium, pp. 489 - 494, June 2003
  3. J. Wang, F. Gao, S. Shi, and J. Wang, 'A New Method for Distance and Relative Velocity Measurement in Vehicle Collision Warning System,' in Proc. IEEE Intelligent Systems Design and Applications, pp. 1142 - 1147, Oct. 2006
  4. Y. -L. Chen, and C. -A. Wnag, 'Vehicle Safety Distance Warning System: A Novel Algorithm for Vehicle Safety Distance Calculating Between Moving Cars,' in Proc. IEEE Vehicular Technology Conference, pp. 2570 - 2574, April 2007
  5. S. Birchfield, and C. Tomasi, 'A pixel dissimilarity measure that is insensitive to image sampling,' IEEE Trans. Pattern Analysis an Machine Intelligence, Vol. 20, No. 4, pp. 401 - 406, April 1998 https://doi.org/10.1109/34.677269
  6. M. Shimizu, and M. Okutomi, 'Precise sub-pixel estimation on area-based matching,' in Proc. IEEE International Conference on Computer Vision, Vol. 1, pp. 90 - 97, July 2001.(455)
  7. S. Nedevschi, R. Danescu, D. Frentiu, T. Marita, F. Oniga, C. Pocol, R. Schmidt, and T. Graf, 'High accuracy stereo vision system for far distance obstacle detection,' in Proc. IEEE Intelligent Vehicles Symposium, pp. 292 - 297, June 2004
  8. E. Z. Psarakis, and G. D. Evangelidis, 'An enhanced correlation-based method for stereo correspondence with subpixel accuracy,' in Proc. IEEE International Conference on Computer Vision, Vol. 1, pp. 907 - 912, Oct. 2005
  9. D. H. Zhou and P. M. Frank, 'Strong tracking Kalman filtering of non-linear time-varying stochastic systems with colored noise: Application to parameter estimation and empirical robustness analysis,' Int. J. Control, Vol. 65, no. 2, pp. 295-307, Sep. 1996 https://doi.org/10.1080/00207179608921698
  10. H. You, S. Qiang, Y. -L. Dong, Y. Jian, 'Adaptive Tracking Algorithm Based on Modified Strong Tracking Filter,' Radar, CIE, pp. 1-4, Oct. 2006
  11. P. Pan, X. Feng, F. Li, 'Self-adaptive Constant Acceleration Model and Its Tracking Algorithm Based on STF,' International Conference on Mechatronics and Automation, pp. 3784-3789, Aug. 2007
  12. Y. -C. Lim, C. -H. Lee, S. Kwon, and W. -Y. Jung, 'Distance Estimation Algorithm for Both Long and Short Ranges Based on Stereo Vision System,' IEEE Intelligent Vehicles Symposium, pp. 841-846, June 2008
  13. W. Jin, X. Zhan, 'A Modified Kalman Filtering via Fuzzy Logic System for ARVs Location,' International Conference on Mechatronics and Automation, pp. 711-716, Aug. 2007
  14. D. -J. J, C. -M. Huang, 'An Adaptive Fuzzy Strong Tracking Kalman Filter for GPS/INS Navigation,' IECON 2007, pp. 2266-2271, Nov. 2007
  15. D. -J. Jwo, S. -H. Wang, 'Adaptive Fuzzy Strong Tracking Extended Kalman Filtering for GPS Navigation,' IEEE Sensors Journal, Vol. 7, no. 5, pp. 778-789, May. 2007 https://doi.org/10.1109/JSEN.2007.894148