Stereo System for Tracking Moving Object using Log-Polar Transformation and ZDF

로그폴라 변환과 ZDF를 이용한 이동 물체 추적 스테레오 시스템

  • Published : 2002.01.01

Abstract

Active stereo vision system allows us to localize a target object by passing only the features of small disparities without heavy computation for identifying the target. This simple method, however, is not applicable to the situations where a distracting background is included or the target and other objects are located on the zero disparity area simultaneously To alleviate these problems, we combined filtering with foveation which employs high resolution in the center of the visual field and suppresses the periphery which is usually less interesting. We adopted an image pyramid or log-polar transformation for foveated imaging representation. We also extracted the stereo disparity of the target by using projection to keep the stereo disparity small during tracking. Our experiments show that log-polar transformation is superior to either an image pyramid or traditional method in separating a target from the distracting background and fairly enhances the tracking performance.

능동 스테레오 비젼 시스템은 목표물 판별을 위해서 간단한 연산만으로 작은 시차값을 가지는 특징들만을 통과시킴으로써 목표물 위치 측정을 가능케 한다. 그런데 이 간단한 방법은, 복잡한 배경이 포함되거나 시차가 영인 영역에 다른 물체들도 동시에 존재하면 적용이 어렵게 된다. 이러한 문제점들을 해결하기 위하여, 본 논문에서는 시야 중심 영역의 해상도는 높이고 일반적으로 중요도가 낮은 주변의 해상도는 감소시키는 포비에이션 기법을 필터링 방법과 결합시켰다 포비에이트 영상 표현을 위하여 영상 피라미드 또는 로그폴라 변환을 사용하였다. 또한 추적이 수행되는 동안에 스테레오 시차가 작은 값이 유지되도록 투영을 이용하여 스테레오 시차를 추출하였다. 실험 결과는 로그폴라 변환이 복잡한 배경으로부터 목표물을 분리하는 제안된 방법이 영상 피라미드 또는 기존 방법보다 우수하며, 추적성능을 상당히 개선함을 보여주고 있다.

Keywords

References

  1. D.J. Coombs, 'Tracking Objects with Eye Movements,' Proc. of the Topical Meeting on Image Understanding and Machine Vision, Optical Society of America, June 1989
  2. D. H. Ballard and C.M. Brown, 'Principles of Animate Vision,' GVGIP: Image Understanding, Vol. 56, No. 1, pp. 3-21, 1992 https://doi.org/10.1016/1049-9660(92)90081-D
  3. D. J. Coombs and C. M. Brown, 'Real-Time Binocular Smooth Pursuit,' International Journal of Computer Vision, Vol. 11, No. 2, pp. 147-164, 1993 https://doi.org/10.1007/BF01469226
  4. M. Tanaka, N. Maru, and F. Miyazaki, 'Binocular Gaze Holding of a Moving Object with the Active Stereo Vision System,' Proc. the 2nd IEEE Workshop on Applications of Computer Vision, pp. 250-255, Sarasota, Florida, USA, 1994 https://doi.org/10.1109/ACV.1994.341318
  5. S. Rougeaux, N. Kita, Y. Kuniyoshi, S. Sakane, F. Chavand, 'Binocular Tracking Based on Virtual Horopters,' IROS'94, Vol. 3, pp. 2052-2057, 1994 https://doi.org/10.1109/IROS.1994.407582
  6. N. Oshiro, N. Maru, ;A. Nishikawa, and F. Miyazaki, 'Binocular Tracking using Log Polar Mapping,' IROS'96, Vol. 2, pp. 791-798, November 1996 https://doi.org/10.1109/IROS.1996.571053
  7. M. Tistarelli and G. Sandini, 'Dynamic Aspects in Active Vision,' CVGIP: Image Understanding, Vol. 56, No. 1, pp. 108-129, 1992 https://doi.org/10.1016/1049-9660(92)90089-L
  8. A. Bernardino and J. Santos-Victor, 'Visual Behaviours for Binocular Tracking,' 2nd EuroMicro Workshop on Advanced Mobile Robotics-Eurobot97, Brescia, Italy, October 1997 https://doi.org/10.1109/EURBOT.1997.633543
  9. R. A. Messner and H. H. Szu, 'An Image Processing Architecture for Real Time Generation of Scale and Rotation Invariant Patterns,' Computer Vision, Graphics, and Image Processing, Vol. 31, No. 1, pp. 50-66, July 1995 https://doi.org/10.1016/S0734-189X(85)80075-X
  10. R. S. Wallace, P. Ong, B. B. Bederson, and E. L. Schwartz, 'Space Variant Image Processing,' International Journal of Computer Vision, Vol. 13, No. 1, pp. 71-90, 1994 https://doi.org/10.1007/BF01420796
  11. T. J. Olson and R. J. Lockwood, 'Fixation-based Filtering,' Proc. of the SPIE Intelligent Robots and Computer Vision XI Conference, pp. 685-696, 1992 https://doi.org/10.1117/12.131572
  12. J. R. Taylor and T. J. Olson, 'Precise vergence control in complex scenes,' SPIE Vol. 2056 Intelligent Robots and Computer Vision XII, pp. 20-30, 1993 https://doi.org/10.1117/12.150226
  13. T. J. Olson and D. J. Coombs, 'Real-Time Vergence Control for Binocular Robots,' International Journal of Computer Vision, Vol. 7, No. 1, pp. 67-89, 991 https://doi.org/10.1007/BF00130490
  14. A. Maki and T. Uhlin, 'Disparity selection in binocular pursuit,' Technical report, KTH (Royal Institute of Technology), 1995
  15. M. Okutomi and T. Kanade, 'A Multiple-baseline Stereo,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 15, No. 4, pp. 353-363, April 1993 https://doi.org/10.1109/34.206955