Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

Well, it's certainly possible to do what you want, but how easy it is depends on what you know or can assume about the problem.

No matter what, you need to know either the distance to part of the object, or the size of the object. Otherwise you're going to not have enough information to get the full 6DOF. From what you say, though, the camera is fixed. So you know where the conveyor is relative to the camera, and hence where the bottom of the box is.

From there it's just detecting rectangular objects travelling along the conveyor and some simple geometry. Not easy, but straightforward.

Your first step is likely to calibrate your camera and determine it's position relative to the conveyor. If you can figure out the 3D location of a single point travelling down the conveyor, you're most of the way there.