Ask Your Question

Roboust Human detection and tracking in a crowded area

asked 2016-12-28 06:40:15 -0500

updated 2016-12-28 06:46:37 -0500

Hello! I am working on an application where I need to detect and track people in a crowded indoor area(like a mall). Right now I am using the OpenCV Background Subtraction class(MOG2) to detect blobs and a Kalman filter and Hungarian Algorithm for tracking(based on this video

The issues I'm having are i) the blobs merging together when two people come close to each other ii) Parts of the person not getting detected which leads to false and multiple detections on a person iii) The background subtraction itself leading to too many false detections. I would like to know your suggestions to improve this and any solutions to fix the problems? Thanks in advance!

BTW, I'm using OpenCV 3.1,C++

edit retag flag offensive close merge delete


Did you resolve the issues?

hoang anh tuan gravatar imagehoang anh tuan ( 2017-01-09 00:53:57 -0500 )edit

@hoang anh tuan Well, after a lot of trying and testing, I dropped the background subtraction method for my case. I'm just tracking faces instead

abhijith gravatar imageabhijith ( 2017-01-09 04:37:55 -0500 )edit

Can you share about it? video or code?

hoang anh tuan gravatar imagehoang anh tuan ( 2017-01-09 19:53:47 -0500 )edit

1 answer

Sort by ยป oldest newest most voted

answered 2016-12-28 06:56:36 -0500

pi-null-mezon gravatar image

It is hard to guess what method will work best for the such particular task. But you can empirically determine this by means of opencv_contib\opencv_traking module.

edit flag offensive delete link more

Question Tools

1 follower


Asked: 2016-12-28 06:40:15 -0500

Seen: 344 times

Last updated: Dec 28 '16