2
votes

I'm trying to develop an algorithm for real time tracking moving objects with a single moving camera setup as a project, in OpenCV (C++).

My basic objectives are

  • Detect motion in an (initially) static frame
  • Track that moving object (camera to follow that object)

Here is what I have tried already

  • Salient motion detection using temporal differencing and Optical Flow. (does not compensate for a moving camera)
  • KLT based feature tracking, but I was not able to segment the moving object features (moving object features got mixed with other trackable features in the image)
  • Mean shift based tracking (required initialization and is a bit computationally expensive)

I'm now trying to look into the following methods

  • Histogram of Gradients.
  • Algorithms that implement camera motion parameters.

Any advice on which direction should I proceed forward to acheive my objective.

1
For tracking you could look at this: blogs.oregonstate.edu/hess/code/particles - Lt. Pigeon
How can KLT features of object and background get mixed? If you (initially) know where the moving object is, just ignore/delete other features?? I would try probabilistic tracking (e.g. particle filtering) and maybe add some camera movement to the object state. - Micka
What exactly do you mean by object state? I'm guessing it means the feature points that describe a moving object @Erik ... thank you. I didn't know of particle filters before this - user3079474
no no, in probabilistic tracking you try to track the "state" of the object. Often it is the position (2D or 3D) and the velocity (2D or 3D) of the object. Have a look at: ttic.uchicago.edu/~rurtasun/courses/CV/lecture10.pdf but beware that those probabilistic tracking techniques have some mathematical background you should understand if you want to implement that. This is a sample video of particle filtering in action: youtube.com/watch?v=O1FZyWz_yj4 - Micka
this is the work of the video in detail, maybe you can use some of this stuff: kth.diva-portal.org/smash/get/diva2:535572/FULLTEXT01.pdf - Micka

1 Answers

0
votes

Type: 'zdenek kalal predator' to google.com and watch the videos, read the papers that came up. I think it will give you a lot of insight.