Speaker
Description
This research described is focused on computer vision tools implemented for detection of a particular military object (or many objects) in a observed scene, given a reference image(s) of the object(s). An algorithm for detecting a specific object based on finding point correspondences between the reference and the target image is designed. It can detect objects despite a scale change or in-plane rotation. It is also robust to small amount of out-of-plane rotation and occlusion. Reference images and a dataset with images obtained from a ground camera or drone are used for the experiments. Detection of point features in images and extraction of feature points are designed for Localization of the recognized object(s) in a scene using matches of feature points (groups of points).