Spatiotemporal Filters for Optical Flow
Filtering plays a significant role in many approaches to image sequence
analysis. In particular, spatiotemporal filtering can be particularly
time- and memory-consuming if done with inseparable 3d FIR filters.
My work in 1985, with Allan Jepson (University of Toronto), was one of
the early examples of spatiotemporal filtering with Gabor FIR filters.
We also show how one can build spatiotemporal filters with cascades
of very simple FIR filters.
More recently, with Keith Langley (University College London) I
concentrated some efforts on designing and implementing recursive (IIR)
filters for motion analysis. The goal was to save both the storage and
the computation requirements. These goals are relevant to gradient-based
methods and to phase-methods. In both cases one needs both a smoothed
version of the signal and its derivatives in space and time.
Langley and I addressed these issues with a class of filters
(band-pass and low-pass) that admit efficient ways of simultaneously
smoothing images and obtaining their partial derivatives.
For phase-based methods, which require even larger numbers of filters,
we have shown how one might adapt the frequency tuning of the filters
to both reduce the required number of filters and to improve signal-to-noise
ratios and hence the robustness of velocity estimates.
- Fleet, D.J. and Langley, K. (1995) Recursive filters for optical
flow. IEEE Transactions on Pattern Analysis and Machine
- Clifford, C., Langley, K. and Fleet, D.J. (1995) Centre-frequency
adaptive IIR temporal filters for phase-based image velocity estimation.
IEE International Conference on Image Processing and Applications,
Edinburgh, July, pp. 173-178
- Langley, K. and Fleet, D.J. (1992) Recursive filters for phase-based
optical flow. Isreali Conference on Vision and AI, Ramat Gan,
Isreal, December, pp. 255-264
- Fleet, D.J. and Jepson, A.D. (1989) Hierarchical construction of
orientation and velocity selective filters. IEEE Transactions on
Pattern Analysis and Machine Intelligence, 11(3): 315--325
- Fleet, D.J. and Jepson, A.D. (1985) Velocity extraction without
form interpretation. IEEE Workshop on Computer Vision,
Bellaire, pp. 179-185
Return to David Fleet's home page.