International Journal of Control, Automation, and Systems

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

Optical Flow Measurement Based on Boolean Edge Detection and Hough Transform

  • Chang, Min-Hyuk (Division of Electronics and Information and Communication Engineering, Chosun University) ;
  • Kim, Il-Jung (Division of Electronics and Information and Communication Engineering, Chosun University) ;
  • Park, Jong an (Division of Electronics and Information and Communication Engineering, Chosun University)
  • Published : 2003.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

The problem of tracking moving objects in a video stream is discussed in this pa-per. We discussed the popular technique of optical flow for moving object detection. Optical flow finds the velocity vectors at each pixel in the entire video scene. However, optical flow based methods require complex computations and are sensitive to noise. In this paper, we proposed a new method based on the Hough transform and on voting accumulation for improving the accuracy and reducing the computation time. Further, we applied the Boo-lean based edge detector for edge detection. Edge detection and segmentation are used to extract the moving objects in the image sequences and reduce the computation time of the CHT. The Boolean based edge detector provides accurate and very thin edges. The difference of the two edge maps with thin edges gives better localization of moving objects. The simulation results show that the proposed method improves the accuracy of finding the optical flow vectors and more accurately extracts moving objects' information. The process of edge detection and segmentation accurately find the location and areas of the real moving objects, and hence extracting moving information is very easy and accurate. The Combinatorial Hough Transform and voting accumulation based optical flow measures optical flow vectors accurately. The direction of moving objects is also accurately measured.

Keywords

References

  1. Computer Vision Graphics Image Processing v.23 On the information in optical flow K. Prazdny https://doi.org/10.1016/0734-189X(83)90025-7
  2. Proc. IEEE Workshop on Visual Motion Object tracking with a moving camera P. J. Burt (et al.)
  3. IEEE Trans. on Pattern Analysis Mach. Intell. v.11 no.10 Obstacle avoidance using field divergence R. C. Nelson;J. Aloimonos https://doi.org/10.1109/34.42840
  4. Computer Vision Graphics Image Processing v.50 Bounds on time-to-collision and rotation component from first-order derivatives of image flow M. Subbarao https://doi.org/10.1016/0734-189X(90)90151-K
  5. Artif. Intell. v.17 Determining optical flow B. K. P. Horn;B. G. Schunck https://doi.org/10.1016/0004-3702(81)90024-2
  6. Computer Vision Graphics Image Processing v.21 Displacement vectors derived from second-order intensity variations in image sequences H. H. Nagel https://doi.org/10.1016/S0734-189X(83)80030-9
  7. Proc. 7th IEEE Int. Conf. on Pattern Recognition Towards the estimation of displacement vector fields by 'oriented smoothness' constraints H. H. Nagel;W. Enkelmann
  8. Signal Processing v.1 Tracking moving objects in television images C. Cafforio;F. Rocca https://doi.org/10.1016/0165-1684(79)90015-X
  9. Proc. 3rd IEEE Int. Conf. on Computer Vision Computing optical flow from an overconstrained system of linear algebraic equations M. Campani;A. Verri
  10. Int. Workshop on Computer Architecture for Machine Perception Multiconstraints-based optical flow estimation and segmentation P. Nesi;A. Delbimbo;J. L. Sanz
  11. IEEE Trans. on Pattern Analysis Mach. Intell. v.2 no.6 Combining motion and contrast for segmentation W. B. Thompson
  12. IEEE Trans. on Pattern Analysis Mach. Intell. v.6 no.6 Stochastic relaxation, Gibbs distribution, and Bayesian restoration of images S. Gemen (et al.)
  13. Proc. ECCV Combining intensity and motion for incremental segmentation and tracking over long image sequence M. J. Black
  14. Proc. 4th Int. Conf. on Computer Vision Segmentation and 2D motion estimate by region fragments M. Etoh(et. al.)
  15. IEEE Trans. on Consumer Electronics v.45 no.3 Local threshold and Boolean function based edge detection M. B. Ahmad;T.-S. Choi https://doi.org/10.1109/30.793567
  16. The Korean Society of Mechanical Engineers v.15 no.3 Estimation of moving information for tracking of moving objects S.-K. Kang;J.-A. Park
  17. Pattern Recognition Letter v.11 A combinatorial Hough transform D. B.-T.;M. Sandler https://doi.org/10.1016/0167-8655(90)90002-J