Ask Your Question

dtbaker's profile - activity

2018-11-24 16:01:35 -0500 received badge  Notable Question (source)
2018-03-26 04:00:02 -0500 received badge  Popular Question (source)
2016-04-11 06:20:00 -0500 asked a question Passing "hints" to Object Tracking algorithm?

Is it possible to pass "hints" to any of the object tracking algorithms to improve performance?

Having a robot with onboard object tracking, I know my robot is about to turn left so I wonder if I can tell the "object tracker" that it should expect the tracked object to appear at position x/y in the next video frame? And if this could improve any processing speed?

(I'm running on a low powered Raspberry Pi so trying to squeeze as much out of it as possible.)

Examples of movement are:

  • I am tracking an object straight ahead of me but I have to do a slight detour around this obstacle infront of me first. This sharp detour could see the tracked object move from the center of the camera all the way to the edge of the camera in the very next frame. I could tell it that we're turning left so try to find the object on the right of the next video frames.
  • There is also some raw vectors coming straight off the GPU which might be able to used as "hints" towards the more CPU intensive object tracker https://www.raspberrypi.org/blog/vect...

Any thoughts?

Thanks!

2016-04-07 07:51:48 -0500 received badge  Scholar (source)
2016-04-07 07:51:44 -0500 received badge  Supporter (source)
2016-04-06 23:05:02 -0500 commented answer How do you use OpenCV TLD from Python?

Hey @ILA did you manage to find any Python wrappers?

2016-04-06 23:05:01 -0500 asked a question List of all available object tracking algorithms?

Hello,

I have just implemented Python/OpenCV2/CMT on a Raspberry Pi with pretty good results for my first OpenCV project ( https://www.youtube.com/watch?v=hvzoh... )

Is there an opencv-newbie-friendly list of all available tracking algorithms ( both built in and 3rd party ) with some examples/description of each implementation?

( or is it more a case of there are a few popular available tracking options that can be combined together in an unlimited number of ways to get better results? )

I'm keen to create some test footage from the RaspberryPi camera and pass them through a number of available tracking algorithms to see which one performs best in various scenarios. I'll be mainly tracking a the back of a walking person (indoor / outdoor) and a bike rider outdoor.

Thank you for any pointers in the right direction!

Cheers, Dave