Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

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

Detection of Optical Flows on the Trajectories of Feature Points Using the Cellular Nonlinear Neural Networks

셀룰라 비선형 네트워크를 이용한 특징점 궤적 상에서 Optical Flow 검출

  • 손혼락 (전북대학교 메카트로닉스 연구센터) ;
  • 김형숙 (전북대학교 전자정보공학부)
  • Published : 2000.11.01
Download PDF
⟨ Previous Next ⟩

Abstract

The Cellular Noninear Networks structure for Distance Transform(DT) and the robust optical flow detection algorithm based on the DT are proposed. For some applications of optical flows such as target tracking and camera ego-motion computation, correct optical flows at a few feature points are more useful than unreliable one at every pixel point. The proposed algorithm is for detecting the optical flows on the trajectories only of the feature points. The translation lengths and the directions of feature movements are detected on the trajectories of feature points on which Distance Transform Field is developed. The robustness caused from the use of the Distance Transform and the easiness of hardware implementation with local analog circuits are the properties of the proposed structure. To verify the performance of the proposed structure and the algorithm, simulation has been done about various images under different noisy environment.

거리 변환(Distance Transform)을 수행할 수 있는 셀룰라 비선형 네트워크 구조와 특징 점들의 제적 상에서 거리 변환을 이용한 optical flow 검출 방법을 제안하였다. 움직이는 물체의 추적이나 카메라의 움직임 파악 같은 응용 분야에서는 수가 적더라도 정확하고 확실한 optical flow가 더 중요하다. 본 연구는 특징점들의 이동 궤적 상에서 거리 변환 기법을 이용하여 거리 변환 필드(Distance Transform Field)를 생성시키고 거리 변환 필드상에서 궤적의 움직인 거리 값과 방향을 추출함으로써 optical flow를 구하는 방법이다. 이 방법은 영상 정보를 거리 정보로 변환하여 사용하게 되므로 잡음의 영향을 적게 받으며 필요한 연산들이 아날로그 회로에 의해 처리되므로 처리 속도가 빠르고, 지역적 처리 특성을 갖기 때문에 하드웨어 구현이 용이하다는 특징이 있다. 또한, 본 연구에서는 제안한 알고리즘의 핵심부분을 하드웨어로 구현하기 위해 셀룰라 비선형 네트워크(Celluar Nonlinear Neural Network)구조를 제안하였다. 제안한 구조와 알고리즘을 검증하기 위해 다양한 영상과 환경에 대한 시뮬레이션을 수행하여 결과를 제시하였다.

Keywords

References

  1. S. M. Smith, ASSET-2 : Real-time motion segment and object tracking, Real-Time Imaging, Academic Press, Vol.4, (No. 1), pp. 21-40, Feb. 1998 https://doi.org/10.1006/rtim.1996.0061
  2. M. Black and Y. Yacoob, Recognizing facial expressions in image sequences using local parameterized models of image motion, International Journal of Computer Vision, Vol. 25, No. 1, pp. 23-48, 1997 https://doi.org/10.1023/A:1007977618277
  3. G. Donato, M. S. Bartlett, C. Hager, P. Ekman, and T. J. Sejnowski, Classifying facial actions, IEEE Tr. on PAMI, Vol. 21, No. 10, pp. 974-989, Oct. 1999 https://doi.org/10.1109/34.799905
  4. G. Adiv, Inherent ambiguities in recovering 3-D motion and structure form a noisy flow field, IEEE Tr. on PAMI, Vol. 11, No. 5, pp. 477-489, May 1989 https://doi.org/10.1109/34.24780
  5. W. Wang, and J. H. Duncan, Recovering the tree-dimensional motion and structure of multiple moving objects from binocular image flows, Computer Vision and Image Understanding, Vol. 63, No. 3, pp. 430-446, May 1996 https://doi.org/10.1006/cviu.1996.0033
  6. H. Nagel and M. Haag, Bias-corrected optical flow estimation for road vehicle tracking, Proceedings of IEEE 6th International Conference on Computer Vision, pp. 1006-1011, Bombay, India, Jan. 1998 https://doi.org/10.1109/ICCV.1998.710839
  7. W. Burger, B. Bhanu, Estimating 3-D egomotion from perspective image sequences, IEEE Tr. on PAMI, Vol. 12, No. 11, pp. 1040-1058, Nov. 1990 https://doi.org/10.1109/34.61704
  8. S. Wachter and H. H. Nagel, Tracking persons in monocular image sequences, Computer Vision and Image Understanding, Vol. 74, No. 3, pp. 174-192, June 1999 https://doi.org/10.1006/cviu.1999.0758
  9. J. Weber and J. Malik, Rigid body segmentation and shape description from dense optical flows under weak perspective, IEEE Tr. on PAMI, Vol. 19, No. 2, pp. 139-143, Feb. 1997 https://doi.org/10.1109/34.574794
  10. D. Kreseski, R. E. Mercer, J. L. Barron, P. Joe and H. Zhang, Storm tracking in doppler radar images, Proceedings of 1st International Conference on Image Processing, pp. 226-230 Vol. 3. Nov. 1994 https://doi.org/10.1109/ICIP.1994.413854
  11. R. A. Deutschmann and C. Koch, An analog VLSI velocity sensor using the gradient method, ISCAS 98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems, Vol. 6, pp. 649-652, June 1998 https://doi.org/10.1109/ISCAS.1998.705450
  12. C. M. Higgins and C. Koch, Analog CMOS velocity sensors, Proceedings of Electronic Imaging 97, pp. 103-114, San Jose, CA, Feb. 1997
  13. J. K. Kearney, W. B. Thompson, and D. L. Boley, Optical flow estimation: An error analysis of Gradient-based methods with local optimization, IEEE Tr. on PAMI, vol. PAMI-9, No. 2, pp. 229-244, March 1987
  14. E. H. Adelson and J. R. Bergen, Spatiotemporal energy models for the perception of motion, Journal of Optical Society of America. A, Vol. 2, No. 2, pp. 284-299, Feb. 1985
  15. A. B. Torralba and J. Herault, An effcient neuromorphic analog network for motion estimation, IEEE Tr. on Circuits and Systems-I: Fundamental Theory and Applications, Vol. 46, No. 2, pp. 269-279, Feb. 1999 https://doi.org/10.1109/81.747199
  16. D. J. Fleet and A. D. Jepson, Computation of component image velocity from local phase information, International Journal of Computer Vision, Vol. 5, No. 1, pp. 77-104, 1990 https://doi.org/10.1007/BF00056772
  17. J. J. Little and A. Verri, Analysis of differential and imtching methods for optical flow, Proceedings of IEEE Motion Workshop, pp. 173-180, Irvine, 1989 https://doi.org/10.1109/WVM.1989.47107
  18. S. Barnard and W. B. Thompson, Disparity analysis of images, IEEE Tr. on PAMI, Vol. PAMI-2, No. 4, July 1980
  19. L. O. Chua and L. Yang, 'Cellular neural networks: theory,' IEEE Tr. on Circuits Systems, Vol 35, pp. 1257-1272, 1988
  20. T. Roska and L. O. Chua, The CNN universal machine:an analogic array computer, IEEE Tr. on Circuits Systems II, CAS-40, pp. 163-173, 1988 https://doi.org/10.1109/82.222815
  21. G. Borgefors, 'Distance transformations in digital images,' Computer Vision, Graphics, and Image Processing, Vol. 34, No. 3, pp. 344-371, 1986 https://doi.org/10.1016/S0734-189X(86)80047-0
  22. T. Yang, L. Yang, Fuzzy cellular neural network: A new paradigm for image processing, International Journal of Circuit thoery and Application, Vol. 25, pp. 469-481, 1997 https://doi.org/10.1002/(SICI)1097-007X(199711/12)25:6<469::AID-CTA967>3.0.CO;2-1
  23. L. O. Chua, T. Yang, G-Q. Zhong and C. W. Wu, Synchronization of Chua s Circuits with Time-Varying Channels and Parameters, IEEE Transactions on Circuits and Systems, Part I, Vol. 43, No. 10, pp. 862-868, 1996 https://doi.org/10.1109/81.538995
  24. I. Baturone, J. L. Huertas, A. Barriga, S. Sanchez-Solano, Current-Mode Multiple-Input Max Circuit, Electronics Letters, Vol. 30, No. 9, pp. 678-679, April, 1994 https://doi.org/10.1049/el:19940510