An alternative to traditional spatiotemporal gradient and
feature-based approaches to measuring object velocity in images is introduced.
Here, the velocity is computed by treating each object as a
distinct intensity wave profile, with Fourier components, and by identifying
the Fourier components that exhibit the magnitude and phase
changes that are consistent with anticipated velocity wave motion. This
detection is accomplished using an appropriate Hough transform. The
two major advantages of this technique are that because the analysis
takes place in the Fourier domain, the spatial organization and the visual
appearance of the moving object are not significant and, second, the
formulation presented in this paper lends itself to direct extension for
more complex motion. Consequently, objects that are visually or spatially
complex and that would be difficult to analyze using either of the traditional
spatiotemporal differentiation or feature-based approaches can be
effectively treated. The proposed approach is demonstrated for scenes
of varying complexity.