Automated reasoning about image motion using a rule-based deduction system

Abstract A rule-based production system for the identification and structural description of image motion is presented. The system employs a set of intermediate-level motion description rules of antecedent-consequent form and a set of low-level, incomplete and possibly incorrect local spatiotemporal motion features together with a forward-backward chaining paradigm to produce or verify high-level motion descriptions. The system has been implemented in LISP and provides a basis for more complex designs, perhaps employing motion-specific frames and iterative deduction and feature extraction. Sample results and future research directions are presented.