Area target calibration in weapon scoring system using computer vision to support Unmanned Combat Aerial Vehicle

Research development of Unmanned Combat Aerial Vehicle (UCAV) or fixed wing Combat Drone requires an accurate weapon scoring system for shooting training assessments to determine the type and capability of the rocket weapon to be used. The current camera-based rocket fire assessment method is only to determine the position of the rocket's impact point on the target, resulting in the pattern of combat training being limited to one shooting heading. The orientation of the rocket shooting practice with only one heading will result in the dependence of the UCAV pilot in carrying out the attack, it will be difficult to carry out firing patterns from various directions. One of the reasons for this is that the camera calibration method for the target area of the shot used is not yet oriented to multi-heading shots. This study aims to produce a method of weapon scoring system for the purposes of UCAV which is focused on calibrating the camera with computer vision for the area of the shot where the attack source is multi-heading. This study proposes a method of Clockwise-elliptical calibration using computer vision for monitoring and evaluating air to ground shooting exercises using high speed weapons. The method generates five main steps, i.e Input Video, Determination of 5 Main Points, Selection of Target Areas in the Image, Object Shape Transformation, and Calculation. The result succeeded in informing the position of the rocket explosion point and its distance from the center point and the angle of the rocket, the accuracy of the shape of the rocket trajectory to the impact point according to geo coordinates, sourced from variations in shot headings. © 2024 Author(s).