I'm using Aruco to find the relative translation between the marker and the camera, I calibrated my camera and got its intrinsic parameters.
I then have found the relative pose using estimatePoseSingleMarkers function in OpenCV for python.
My camera is set at a fixed position & height, the only thing changing is the position of the object in the x and y (not in z), by that I mean the object is at a table and not being moved up or down.
I noticed, however, that when changing the position of the object, all the three values of the tvecs got changed, including the z one, which gets larger as the object move further from the camera.
I tried to look it up online (how OpenCV estimate the translation?) but with no luck. Could someone please point me out to the way on how the relative position/translation between two frames is done?
Also, what if I want the position of the object in the frame of the camera? is it the same as the translation vector?
Sorry if this sounds naive question, I'm a newbie to this thing.