Cascade Classifier

asked 2018-02-10 00:56:13 -0500

ice gravatar image

I am using Cascade Classifier to detect objects in a video stream. I load the .xml classifier file that I have trained before. Then I use detectMultiCsale to perform the detection but the problem is when I use detectMultiScale to perform the detection it cause my detection delay and lag. May I know have any other method to use .xml file to detect the object using cascade classifier?

I am using opencv 3.3.0 and I using c++ in my coding. Anyone can help me?Thank you.

edit retag flag offensive close merge delete


What kind of lag you are facing will you clarify?is your output frames per second is slow or detection is not smoother or what else?

Shivanshu gravatar imageShivanshu ( 2018-02-11 11:54:08 -0500 )edit

thanks for your reply. I am facing output frame is slow. When output frames is lag it also cause the detection not smoother.

ice gravatar imageice ( 2018-02-11 17:36:08 -0500 )edit

well I must tell you precision and speed cant be increased simultaneously.If you increase precission it will cause lag..I depends upon your computing power.So i recommend you to decrease detection precession .put window size from(100,100) instead putting window size to(30,30) and if your input image is noisy then use de-noising digital filters..(like bilateral filters)because it will cause bounding box to flicker if you want to check an example you can check my repository


This example detects face smoother without flickering.But i will only detect one face with such precession. I am working for multipleface still..

Shivanshu gravatar imageShivanshu ( 2018-02-12 02:10:22 -0500 )edit

thank you very much. I will try.

ice gravatar imageice ( 2018-02-12 04:56:35 -0500 )edit