Abstract

Shape geometric invariant play an important role in model- based vision (MBV). However, in many MBV scenarios, shape information may not be sufficiently reliable and hence other types of invariant need to be considered. This paper addresses motion-based classification of objects based on unique motion or activity characteristics in long-sequence of images. To date, the techniques developed in motion-based recognition are inherently sensitive to (a) object's shape, (b) Euclidean group actions and (c) time scale, i.e., velocity and acceleration of motion. We propose the development of a set of motion-based invariant that capture geometric aspects of object's kinematic constraints during distinctive motions and activities. Algebraic and differential invariant of curves and surfaces in a projective space, the kinematic image space, are proposed for motion and activity classification. The proposed approach established parallelism between space and motion geometric invariance.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call