Click here to Skip to main content
15,881,172 members
Please Sign up or sign in to vote.
1.00/5 (2 votes)
See more:
I wrote a program to track any moving object from a camera frame using Opencv and c++. The approach that i used is frame differencing and then applying some thresholding to track the moving object. Well, until this part everything works pretty well. Now, my goal is that say i have multiple objects moving around in my camera frame and i want to track single object out of them. So, obviously i tried it with my above approach but the results were not that satisfactory. The reason i wanted to do this is because i can use this for security reasons and any other reasons. I dont want to use color detection or any sort of algorithm which may be brightness/background dependent. I want to come up with a robust system which can help me to track the object i want out of multiple moving objects. So, what kind of approach should i use to accomplish this project? Thanks

** I want to separate a single object from multiple objects and track it. Something like this -https://www.youtube.com/watch?v=fCu4_mhcdJg[^]
Posted
Updated 30-Sep-14 1:49am
v3
Comments
nv3 30-Sep-14 3:40am    
From your question it is not clear what exactly you have problems with: To separate multiple objects in your start frame, to find the desired object in the set of detected objects, or to track that object over a sequence of frames. Please use the green "Improve question" button to elaborate.
Rebecca1995 30-Sep-14 7:49am    
@nv3:- Thanks for the recco. I have updated my question with the youtube link.
KarstenK 30-Sep-14 8:38am    
Maybe you should scale down the frames in colors to some gray values.

But if you search for something - you must look at the frames :-O

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)



CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900