2010/11/18 Prasad Dixit <abhimohpra@gmail.com>:
>
> Thanks Ivan and Steven
>
> For localization-as explained earlier i have limited sensing capabilities
> which somehow want to make it more effective by Visualization-camera sensor.
> Also,in visuals i am avoiding stereo vision and IMU sensors due to my
> limited hardware configuration.
>
> So, as per my understanding and from your reply... I can mount a single
> camera on the robot (with camera_info topic published) and place various
> patterns at different locations where i know (x,y,z) of all those earlier. I
> don't need ekf or probabilistic approach since i am taking single input from
> webcam (Logitech pro 9000 - upto 30 fps) and know all patterns placing
> positions. A particular pattern will get matched whenever robot comes across
> it and ar_pose will recognize Robot's current position and update it in
> stack.
> Please let me know if i am wrong in this approach.

That's correct.

>
> If it is right then,
> 1. How the robot will know the distance from the pattern?

You have to calibrate your camera and provide the width of the marker to ar_pose

> 2. Is "demo_single" right program to study?

The demo_single tracks a single marker. Multiple markers are tracking
with demo_multi I think.

> 3. I have static map and /amcl node running, how ar_pose input will get
> combined to know the exact position after recognizing the pattern and it's
> position?

I guess you can provide the ar_pose estimates to the amcl node to
update the robots position, but I'm not familiar with this however.

Steven

>
>
>
> - Prasad
>
> --
> View this message in context: http://ros-users.122217.n3.nabble.com/ar-pose-basics-tp1921421p1924148.html
> Sent from the ROS-Users mailing list archive at Nabble.com.
> _______________________________________________
> ros-users mailing list
> ros-users@code.ros.org
> https://code.ros.org/mailman/listinfo/ros-users
>