I work on bin picking system with Kinect vision and ABB robot. The objective is to click on an object in figure with Kinect RGB+depth image in order to get it's X Y and Z world coordinates and send them to my robot.
I don't really know how to solve this problem. First idea was to transform my RGB+depth image to point cloud, then indicate one point to get its world coordinates, but i don't know how to indicate one point from cloud by click. Is it possible to put a marker on RGB image and transfer it on depth image? Maybe you know other solutions that may help me?