Ask Your Question
1

How to get bounding box from HOGdescriptor::detect()

asked 2015-06-09 07:12:11 -0600

erogol2 gravatar image

I far as I see detect() only returns a point whereas detectMultiScale() returns a detection bounding box. Is there any way to replicate this for detect() function as well?

edit retag flag offensive close merge delete

1 answer

Sort by » oldest newest most voted
3

answered 2015-06-09 07:18:00 -0600

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.

edit flag offensive delete link more

Question Tools

1 follower

Stats

Asked: 2015-06-09 07:12:11 -0600

Seen: 410 times

Last updated: Jun 09 '15