YOLOv8 Pipe Output Reformatting

We should look into how teams would like us to send the output of this pipe. Perhaps we should use normalized x and y values instead of pixel values? Perhaps we should look into taking fov settings for this pipe and then calculating the angles?

The issue does not name any files, tests, or entry points; start by locating the YOLOv8 pipe and tracing its current output format. Before implementation, clarify whether normalized coordinates, pixel values, field-of-view settings, or calculated angles are required, then define a concrete output contract and tests that demonstrate it.

Written by the indexing model from the issue text.