Optical System For Evaluation of Virtual Firearms Shooting Training Simulators, Based On Computer Vision

The proposed system is an innovative solution that allows the implementation of training spaces for shooting techniques using virtual reality and computer vision concepts. The scenarios are emulated using development software called Unity. The silhouettes are virtualized images of typical targets and useful for training that allows to improve the precision and dexterity that a shooter requires. The evaluation and qualification of the accuracy of the shot has as its main element a camera, whose capabilities are only slightly better than a webcam, and under an environment of total darkness it is capable of evaluating the exact place where an infrared laser beam hits on a virtual silhouette mounted on the training stage. The laser is adapted to the trumpet of a firearm. The image is processed using color recognition, edge detection, center of mass, and spot detection; information that allows to discriminate the contour of the laser and its center, and then assign a numerical value to the shot made. This ability to evaluate homographic images is another of the important contributions of this research.