Change-driven data flow image processing architecture for optical flow computation
- 178 Downloads
Optical flow computation has been extensively used for motion estimation of objects in image sequences. The results obtained by most optical flow techniques are computationally intensive due to the large amount of data involved. A new change-based data flow pipelined architecture has been developed implementing the Horn and Schunk smoothness constraint; pixels of the image sequence that significantly change, fire the execution of the operations related to the image processing algorithm. This strategy reduces the data and, combined with the custom hardware implemented, it achieves a significant optical flow computation speed-up with no loss of accuracy. This paper presents the bases of the change-driven data flow image processing strategy, as well as the implementation of custom hardware developed using an Altera Stratix PCI development board.
KeywordsMotion estimation Optical flow computation Data flow architectures
This work has been supported by the project TEC2006-08130/MIC of the Spanish Ministerio de Educación y Ciencia.
- 1.Altera Corporation: Stratix Device Handbook. Stratix architecture, Chap. 2, pp. 2.1–2.140 (2005)Google Scholar
- 2.Arribas, P.C., Monasterio, F.: FPGA implementation of the Horn & Schunck optical flow algorithm for motion detection in real time images. In: Proc. XIII Design of Circuits and Integrated Systems, pp. 616–621, (1998)Google Scholar
- 8.Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Proc. 8th European Conference on Computer Vision. Springer Lect. Notes Comput. Sci. 3024, 25–36 (2004)Google Scholar
- 15.Pardo, F., Boluda, J.A., Sosa, J.C.: Circle detection and tracking speed-up based on change-driven image processing. In Proc. ICGST International Conference on Graphics, Vision and Image Processing GVIP-05 (2005)Google Scholar
- 18.Sandini, G., Questa, P., Scheffer, D., Diericks, B., Mannucci, A.: A retina-like CMOS sensor and its applications. In: Sensor Array Multichannel Signal Process. Workshop, pp. 514–519 (2000)Google Scholar