ESTIMATION OF THE CROSS CORRELATION BASED OPTICAL FLOW FOR VIDEO SURVEILLANCE

Authors

  • Rauf Sadykhov
  • Denis Lamovsky

DOI:

https://doi.org/10.47839/ijc.5.3.415

Keywords:

Cross-correlation, fast algorithm, MMX/SSE extensions, optical flow, video surveillance system

Abstract

This paper describes a new algorithm to calculate cross-correlation function. We combined box filtering technique for calculation of cross correlation coefficients with parallel processing using MMX/SSE technology of modern general purpose processors. We have used this algorithm for real time optical flow estimation between frames of video sequence. Our algorithm was tested on real world video sequences obtained from the cameras of video surveillance system.

References

B. Zitova J. Flusser Image registration methods: a survey”, Image and Vision Computing, 21 (11) (2003). pp. 977-1000

W. K. Pratt Correlation techniques of image registration, IEEE Transactions on Aerospace and Electronic Systems, 10 (1974). pp. 353–358.

R. Zabih J. Woodfill Non-Parametric Local Transforms for Computing Visual Correspondence, Proceedings 3rd European Conf. Computer Vision, Stockholm, 1994, pp. 150-158.

J. L. Barron D. J. Fleet S. S. Beauchemin Performance of optical flow techniques, International Journal of Computer Vision, 12(1) (1994), pp. 43-77.

S. S. Beauchemin J. L. Barron Computation of optical flow, ACM Computing Surveys, 27 (3) (1995). pp. 433-467.

J. Weng. Image matching using the windowed Fourier phase International Journal of Computer Vision, 11 (3) (1993). pp. 211-236.

M. J. McDonnel Box-filtering techniques, Computer Graphics and Image Processing, 17 (3) (1981). pp. 65-70.

H. Hirschmuller P. R. Innocent J. Garibaldi Real-time correlation-based stereo vision with reduced border errors, International Journal of Computer Vision, 47 (1-3) (2002). pp. 229 – 246.

K. Muhlmann D. Maier J. Hesser R. Manner Calculating dense disparity maps from color stereo images, an efficient implementation, International Journal of Computer Vision, 47 (1-3) (2002). pp. 79 – 88.

C. Sun Fast algorithms for stereo matching and motion estimation, Proceedings of Australia-Japan Advanced Workshop on Computer Vision, Adelaide, Australia, September 2003, pp.38-48.

C. Sun Fast optical flow using 3d shortest path techniques, Image and vision computing, 20 (13/14) (2002). pp. 981-991.

J. Germano R. Baptista L. Sousa Configurable platform for real time video processing and vision systems, Proceedings of XX Conference on Design of Circuits and Integrated Systems (DCIS'05), Lisbonne, Portugal, 2005.

R.Andraka A dynamic hardware video processing platform, Proceedings of Conference on Reconfigurable Technology for Rapid Product Development and Computing, November 1996, pp. 90-99.

S. Persa P.P. Jonker Evaluation of two real time image processing architectures, Proceedings of 6th Annual Conf. of the Advanced School for Computing and Imaging (ASCI 2000), Lommel, Belgium, June 2000, pp. 387-392.

J. Skoglund M Felsberg Fast image processing using SSE2, Proceedings of the SSBA Symposium on Image Analysis, Malmo, March, 2005.

V. Kravtchenko Using MMX technology in digital image processing, Technical Report and Coding Examples TR-98-13, Department. of Computer Science. The University of British Columbia.

G. Conte S. Tommesani F. Zanichelli The long and winding road to high-performance image processing with MMX/SSE, Proceedings of the In Fifth IEEE International Workshop on Computer Architecture for Machine Perception, Padova, Italy, September 2000, p. 302.

Downloads

Published

2014-08-01

How to Cite

Sadykhov, R., & Lamovsky, D. (2014). ESTIMATION OF THE CROSS CORRELATION BASED OPTICAL FLOW FOR VIDEO SURVEILLANCE. International Journal of Computing, 5(3), 112-117. https://doi.org/10.47839/ijc.5.3.415

Issue

Section

Articles