A Pipelined Real-Time Optical Flow Algorithm
Optical flow algorithms generally demand for high computational power and huge storage capacities. This paper is a contribution for real-time implementation of an optical flow algorithm on a pipeline machine. This overall optical flow computation methodology is presented and evaluated on a set of synthetic and real image sequences. Results are compared to other implementations using as measures the average angular error, the optical flow density and the root mean square error. The proposed implementation achieves very low computation delays, allowing operation at standard video frame-rate and resolution. It compares favorably to recent implementations in standard microprocessors and in parallel hardware.
Keywordsoptical flow real-time motion analysis pipeline hardware
Unable to display preview. Download preview PDF.
- 1.Smith, A.T., Snowden, R.J.: Visual Detection of Motion. Academic Press, New York (1994)Google Scholar
- 4.Stofler, N., Burkert, T., Farber, G.: Real-time obstacle avoidance using MPE Gprocessor- based optic flow sensor. In: Proceedings of the 15th International Conference on Pattern Recognition, Barcelona, Spain, pp. 161–166 (2000)Google Scholar
- 6.Farnebäck, G.: Fast and accurate motion estimation using orientation tensors and parametric motion models. In: Proceedings 15th Int. Conf. on Pattern Recognition, Barcelona, Spain, pp. 135–139 (2000)Google Scholar
- 8.Correia, M.V., Campilho, A.C., Santos, J.A., Nunes, L.B.: Optical flow techniques applied to the calibration of visual perception experiments. In: Proceedings 13th Int. Conf. on Pattern Recognition, ICPR 1996, Vienna, Austria, pp. 498–502 (1996)Google Scholar
- 9.Correia, M.V., Campilho, A.C.: Real-time implementation of an optical flow algorithm. In: Proceedings 16th Int. Conf. on Pattern Recognition, Québec City, Canada, pp. 247–250 (2002)Google Scholar
- 11.Simoncelli, E.P.: Distributed representation and analysis of visual motion, Ph.D. thesis, Massachusetts Institute of Technology (January 1993)Google Scholar
- 12.Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of the 7th International Joint Conference on Artificial Intelligence, Vancouver, Canada, pp. 674–679 (1981)Google Scholar
- 15.Lin, T., Barron, J.L.: Image reconstruction error for optical flow. In: Proceedings of Vision Interface 1994, Banff National Park, Canada, pp. 73–80 (1994)Google Scholar