ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange
Ask Your Question
0

Bumblebee2 applicability for long-range object detection

asked 2012-03-19 08:27:08 -0500

Spym gravatar image

updated 2013-05-16 08:14:51 -0500

Hello.

Maybe this question is little offtopic here (sorry if so), I don't know where to ask it instead.

I need a method to detect the following kinds of objects using a stereo camera:

  • any large obstacle, like building or tree, on a distance about 15m (tolerance doesn't matter, it's just for long-term collision avoidance)
  • human body on distance about 7m
  • a human's hand on distance about 2m

(Assuming good lighting, clear view, and so on)

Question for the people who have practiced with Bumblebee2: is this camera a good choice for these tasks? (http://www.ptgrey.com/products/bumblebee2/bumblebee2_stereo_camera.asp)

The Point Grey folks gave me nice guidelines about the stereo accuracy: http://www.ptgrey.com/support/kb/index.asp?a=4&q=103, but this isn't enough to make decision.

Thanks in advance,
Pavel.

UPD: Are there any other stereo cameras that are supported by ROS? A TOF camera seems to be a poor choice because of long ranges.

edit retag flag offensive close merge delete

1 Answer

Sort by ยป oldest newest most voted
3

answered 2012-03-19 14:18:47 -0500

mjcarroll gravatar image

I think that the Bumbleebee will work for what you are looking at.

Generally, stereo vision is going to be a little less accurate than a structured light approach (like the Kinect), especially with fine grain details.

I know that in my experimentation with the Bumbleebee, hands and arms come through fairly well, but fingers tend to show up as a "mitten" with no fine detail.

As for Bumbleebee support in ROS, it's a bit fragmented. Unfortunately, Point Grey hasn't release an updated library that will work with the newer Ubuntu systems. Because of this, using their libraries natively with ROS is impossible.

It is still possible to capture images from the Bumbleebee and then run them through OpenCV's stereo block matcher (what is used in stereo_image_proc), but you lose the benefit of Point Grey's factory calibration for rectification.

edit flag offensive delete link more

Question Tools

2 followers

Stats

Asked: 2012-03-19 08:27:08 -0500

Seen: 1,300 times

Last updated: May 16 '13