Studies of image motion typically address motion categories on a case-by-case basis. Examples include a moving point, a moving contour, or a 2D optical flow field. The typical assumption made in these studies is that there is a unique velocity at each moving point in the image. In this paper we relax this assumption. We introduce a broader set of motion categories in which the set of motions at a moving point can be 0-D, 1-D, or 2-D. We consider one new motion category in detail, which we call optical snow. This motion category occurs, for example, when an observer translates relative to a massively cluttered scene. Examples include the motion seen by an observer moving through bushes, or falling snow seen by a stationary observer. Optical snow is characterized by a 1-D set of velocities at each moving point and as such, it cannot be analyzed using a classical computational method such as optical flow. We introduce a technique for analyzing optical snow which is based on a bow tie signature of the motion in the frequency domain. We demonstrate the effectiveness of the technique using both synthetic and real image sequences.
Dimensional analysis of image motion
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 ; 1 ; 155-162 vol.1
2001-01-01
891955 byte
Conference paper
Electronic Resource
English
Dimensional Analysis of Image Motion
British Library Conference Proceedings | 2001
|Three dimensional automatic motion analysis
Automotive engineering | 1995
|Three Dimensional Automatic Motion Analysis
British Library Conference Proceedings | 1995
|Image Systems on motion analysis
Online Contents | 2008