Ask Your Question

Is there any mature open source human detection and tracking system/algorithm?

asked 2012-10-17 23:55:34 -0500

priya gravatar image

I need to count the the people in video. for this i have to use a human tracking algorithm in my research. Is there any code is available for detection and tracking of people.

edit retag flag offensive close merge delete

3 answers

Sort by ยป oldest newest most voted

answered 2012-10-18 04:17:17 -0500

Ben gravatar image

updated 2013-08-22 03:50:41 -0500

Have a look at the LatentSvmDetector. OpenCV already provides different classificators trained to detect people, cars, cats, airplanes...

I guess you have to implement the tracking yourself, but OpenCV also provides helpful functionality like e.g. Kalman filters for that.

UPDATE Here you can find latentsvm models not included in the OpenCV release version.

edit flag offensive delete link more


Where can I find the classifiers for people, cars, etc. I could only find for cats in the OpenCV folders.

TimeManx gravatar imageTimeManx ( 2013-08-22 00:42:53 -0500 )edit

I updated my answer.

Ben gravatar imageBen ( 2013-08-22 03:52:30 -0500 )edit

answered 2012-10-18 04:55:10 -0500

elmiguelao gravatar image

Another alternative is to use Haar classifier for pedestrian detection, assuming your "people" are either standing or moving, see this link that includes some discussion about it. I have tried the classifiers myself and movement + Haar-detection + Kalman tracking works relatively ok as long as:

  1. there are not too many pedestrians on the scene, and they don't oclude each other,
  2. the pedestrians don't look too small in the image (camera too far)
  3. the background is not too cluttered with objects looking like pedestrians :)
edit flag offensive delete link more


I think LatentSvmDetector is superior to Haar detection, the latter has difficulties with non-rigid objects.

Ben gravatar imageBen ( 2012-10-18 05:10:21 -0500 )edit

answered 2013-08-23 11:45:09 -0500

anatoliy314 gravatar image

Take a look at "Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors" by Wu and Nevatia, here: . This looks like the most practical, hands-on algorithm that I found. I do not know if it is ready to be used out of the box. The safest thing to do would be to take this algorithm as a goal, and make a roadmap of how you would evolve from the simplest detection and tracking algorithm towards that goal. Once you implement that simplest algorithm, take a look at the results, see where the failure modes are. Go on with your plan if it makes sense, or redo it given the new information you uncovered. I know it sounds risky, but the guys who wrote this are good, and with a bit of skill and luck you will get your algorithm soon enough.


edit flag offensive delete link more

Question Tools

1 follower


Asked: 2012-10-17 23:55:34 -0500

Seen: 6,206 times

Last updated: Aug 23 '13