polygon_to_rbox3 average height

[eugene123tw]

I am wondering why the average height is compute as h = (norm(np.cross(dt, tl-br)) + norm(np.cross(dt, tr-bl))) / (2*(norm(dt)+eps)) in polygon_to_rbox3 function? Why didn't just compute like this (norm(tr - br) + norm(tl - bl))/2?

Original code reference: https://github.com/mvoelk/ssd_detectors/blob/master/utils/bboxes.py#L60

[mvoelk]

If I remember correctly, it compensates better for distorted rectangles. As an example, you have an image with size 800x600 and oriented bounding boxes defined as polygons. After resizing the image to 512x512, the aspect ratio changes and you end up with distorted rectangles.