Projectile impact detection and performance evaluation using machine vision

The paper reports on the development of a machine vision system for assessing targeting accuracy of ballistic, projectile-firing weapon systems. Current techniques rely on either manual optical sighting or acoustic signature to locate the point of impact. Optical sighting, still the predominant method in many events, is manual and imprecise. Acoustic-based approaches automate the process but require multiple sensor placements. The machine vision system described is able to continuously monitor the target, report precise quantitative targeting information and simultaneously provide a color-coded display of impacts. Special provisions have been built-in to account for target plane motion and overlapping impacts phenomenon.<>