how to associating the detections corresponding to the same object over time

1 view (last 30 days)
hi everyone I have a project that I want to calculate speed and counting vehicle in a video. I have done the Background subtraction step, now I want to associating the detections corresponding to the same object over time. I read this tutorial http://www.mathworks.com/help/vision/examples/motion-based-multiple-object-tracking.html and the result of that code is what I want to but in the first step, I want to replace the foreground detection step that code by my background subtraction. may you help me?

Accepted Answer

Dima Lisin
Dima Lisin on 8 Sep 2014
Hi Hai,
you can put your own background subtraction code into the detectObjects replacing the code that computes the mask.
  3 Comments
Dima Lisin
Dima Lisin on 9 Sep 2014
Edited: Dima Lisin on 11 Sep 2014
Hard to say without seeing your entire code. The reason you do not see any variables, is because this example is a function, not a script. If you want to use VideoReader instead of vision.VideoFileReader, then you have to use the readFrame method to read a frame, and the hasFrame method to check if there are any frames left. Look at the documentation for VideoReader. By the way, is there any reason you don't want to use vision.VideoFileReader? Can you run the example as is?
hai tran
hai tran on 22 Sep 2014
Thanks Dima Lisin. I don't use vision.VideoFileReader just because I used VideoReader from I started with Image processing and I want to keep my background subtraction method. I am a amatuer so It will tale me along time to restart with computer vision toolbox ( It is a little bit complicated with me ).
I tried to replaced detectObjects by my background subtraction, but I can't. I attached my code, can you help me to replace my code by detectObjects of the code in the link.
if you can, may you help me to revise the code in the link become a script that can easier to learn from that.

Sign in to comment.

More Answers (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!