Optic Flow Integration at Multiple Spatial Frequencies – Neural Mechanism and Algorithm
In this work we present an iterative multi-scale algorithm for motion estimation that follows mechanisms of motion processing in the human brain. Keeping the properties of a previously presented neural model of cortical motion integration we created a computationally fast algorithmic implementation of the model. The novel contribution is the extension of the algorithm to operate on multiple scales without the disadvantages of typical coarse-to-fine approaches. Compared to the implementation with one scale our multi-scale approach generates faster dense flow fields and reduces wrong motion estimations. In contrast to other approaches, motion estimation on the fine scale is biased by the coarser scales without being corrupted if erroneous motion cues are generated on coarser scales, e.g., when small objects are overlooked. This multi-scale approach is also consistent with biological observations: The function of fast feedforward projections to higher cortical areas with large receptive fields and feedback connections to earlier areas as suggested by our approach might contribute to human motion estimation.
KeywordsInput Image Motion Estimation Neural Model Coarse Scale Feedback Connection
Unable to display preview. Download preview PDF.
- 4.Hupé, J.M., James, A.C., Girard, P., Lomber, S.G., Payne, B.R., Bullier, J.: Feedback Connections Act on the Early Part of the Responses in Monkey Visual Cortex. J. Neurophys. 85, 134–145 (2001)Google Scholar
- 5.Bayerl, P., Neumann, H.: Towards real-time: A neuromorphic algorithm for recurrent motion segmentation. In: Ninth International Conference on Cognitive and Neural Systems (ICCNS 2005), Boston, USA (2005)Google Scholar
- 7.Weiss, Y., Fleet, D.J.: Velocity likelihoods in biological and machine vision, Probabilistic models of the brain: Perception and neural function, pp. 81–100. MIT Press, Cambridge (2001)Google Scholar
- 10.Simoncelli, E.: Course-to-fine Estimation of Visual Motion. In: IEEE Eighth Workshop on Image and Multidimensional Signal Processing, Cannes France (September 1993)Google Scholar
- 11.Burt, P.J., Adelson, E.H.: The Laplacian Pyramid as a Compact Image Code. IEEE Transactions On Communications 31(4) (1983)Google Scholar
- 13.Stein, F.: Efficient Computation of Optical Flow Using the Census Transform. In: DAGM-Symposium 2004, pp. 79–86 (2004)Google Scholar
- 14.Albright, T.D.: Direction and orientation selectivity of neurons in visual area MT of the macaque. J. Neurophys. 52, 1106–1130 (1984)Google Scholar
- 15.Duffy, C.J., Wurtz, R.H.: Sensitivy of MST Neurons to Optic Flow Stimuli. I. A Continuum of Response Selectivity to Large-Field Stimuli. J. Neurophys. 65, 1329–1345 (1991)Google Scholar