People detection using motion ROI

asked 2013-09-25 14:27:19 -0500

Steven P. Goldsmith gravatar image

People ROI compares and contrasts using image resizing and motion detection to obtain a ROI (region of interest) versus processing frames and regions unchanged. People detection is used in this example, but any type of image analysis can benefit from the techniques presented. Performance gains are in the 10 to 100 times range. My goal is to make people detection real-time on low end hardware without using hardware/software specific hacks (i.e. UncannyCV). The code is in Python and OpenCV 2.4.6.1 was used.

The wiki has installation instructions and techniques used.

edit retag flag offensive close merge delete

Comments

This is a very pertinent CV capability need, thanks for identifying it. Is there a forum where people can discuss approaches and thoughts?

Will Stewart gravatar imageWill Stewart ( 2013-12-03 10:47:06 -0500 )edit

You can post questions on the GitHub site.

Steven P. Goldsmith gravatar imageSteven P. Goldsmith ( 2014-07-11 20:24:53 -0500 )edit

I suggest you create a tutorial using this package or even create a pull request to the contribution branch of OpenCV. Who knows your solution will get integrated in OpenCV! If you keep it just here in the q&a forum, I am afraid it will loose the attention it deserves.

StevenPuttemans gravatar imageStevenPuttemans ( 2014-07-14 04:30:58 -0500 )edit

@Steven P. Goldsmith you could post your github link here

sturkmen gravatar imagesturkmen ( 2015-12-29 16:18:56 -0500 )edit