This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
Detect is related to the size provided when creating the object. So you get the size of the box already: (64,128) for the default value. The returned point is the Left-top corner point of the detected objects, but I agree that the API could be more consistent: using bounding boxes instead of points. This is always confusing: is it the center? is it the top-left corner? … Feel free to update it and add a pull request.
