In the graph below, object detection is done through a point that points to the right place rather than a bounding box (e.g., using faster RCNN). What method enables to train such a point?
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
Ususally the x,y coordinates of the top-left corner of the bounding box and the width and height of the bounding box is returned by objection detection algorithms (eg: Haar Cascades)
You can always convert a bounding box to a point via the equation:
$BoundingBoxCenter_{x}= \frac{BoundingBoxCorner_{x} + BoundingBoxWidth}{2}$ $BoundingBoxCenter_{y}= \frac{BoundingBoxCorner_{y} + BoundingBoxHeight}{2}$
