Element Integrity Principle

The element integrity principle is a natural constraint used to solve a particular problem of visual underdeterimination, the motion correspondence problem.  According to this constraint, motion correspondence matches are assigned in such a way that elements only rarely split into two, or fuse together into one, as they are tracked from one view to the next (Ullman, 1979).  It is a natural constraint in the sense that the physical coherence of surfaces implies that the splits or fusions are unlikely.  Although it is a relatively weak constraint – alone it can be used to solve few motion correspondence problems – it is assumed to operate in important theories of motion correspondence processing (Dawson, 1991; Ullman, 1979).

References:

1. Dawson, M. R. W. (1991). The how and why of what went where in apparent motion: Modeling solutions to the motion correspondence process. Psychological Review, 98, 569-603.
2. Ullman, S. (1979). The Interpretation Of Visual Motion. Cambridge, MA: MIT Press.

(Added March 2011)