We propose a spatio-temporal representation for complex optical flow events that generalizes traditional parameterized motion models (e.g. affine) yet differs in significant ways. First, the spatio- temporal models may be non-linear or stochastic. Second, these models are event-specific in that they characterize a particular type of object motion (e.g. sitting or walking). The computational problem involves choosing the appropriate model, phase, rate, spatial position, and scale to account for the image variation. The posterior distribution over this parameter space conditioned on image measurements is typically non-Gaussian. The distribution is represented using factored sampling and is predicted and updated over time using the Condensation algorithm. The resulting framework automatically detects, localizes, and recognizes motion events.
Black, M. J., Explaining optical flow events with parameterized spatio-temporal models, IEEE Proc. Computer Vision and Pattern Recognition, CVPR'99, Fort Collins, CO, 1999, pp. 326-332. (postscript, 3MB), (0.7MB).