Ask Your Question
0

General People Cascade Classifier

asked 2016-08-04 15:09:20 -0500

marcosbontempo gravatar image

updated 2016-08-04 20:06:20 -0500

Hello,

I'm training a Haar Cascade Classfier to identify people based on a set of samples. It works with the people from the pictures, but how can I assure that the classifier will work with different people? And what if they use different types of clothes?

Is there a way to produce a general Cascade Classifier that can identify every kind of people?

Here is the image I'm using:

image description

Any tip will be very helpful,

Thanks

edit retag flag offensive close merge delete

Comments

sturkmen gravatar imagesturkmen ( 2016-08-04 15:55:00 -0500 )edit

Thanks for your answer @sturkmen! I tried using the OpenCV ready classifiers, but they didn't work. I think it's because the position of my camera.

Here is my image: http://i.imgur.com/aq1qWXL.png

Do you know if there is a classifier that could work?

Thanks

marcosbontempo gravatar imagemarcosbontempo ( 2016-08-04 17:13:10 -0500 )edit

i can't see your image

sturkmen gravatar imagesturkmen ( 2016-08-04 18:50:02 -0500 )edit

@sturkmen I added the image to the question :) I think I'm having problems because the camera is not capturing the head

marcosbontempo gravatar imagemarcosbontempo ( 2016-08-04 20:04:07 -0500 )edit
1

do you have to put your camera, where it is now ?

(simply put: from straight above, a human is just a blob. almost any trained classifiers assume frontal view, to exploit human shape.) (and yes, you'll need the head, too ;)

berak gravatar imageberak ( 2016-08-05 02:35:38 -0500 )edit

1 answer

Sort by ยป oldest newest most voted
0

answered 2016-08-08 13:06:13 -0500

marcosbontempo gravatar image

Thanks for your help @sturkmen and @berak. It would be easier to me to put the camera in that position (because of the coverage area) but I decided to change it so I can capture the head.

edit flag offensive delete link more
Login/Signup to Answer

Question Tools

1 follower

Stats

Asked: 2016-08-04 15:09:20 -0500

Seen: 109 times

Last updated: Aug 08 '16