Ask Your Question

dconner's profile - activity

2014-06-03 15:08:30 -0600 asked a question Anyone have python interface for PointGrey bumblebee stereo camera

Can you point me to any python software for interfacing a Pointgrey Bumbleebee stereo camera using the FlyCapture SDK under Linux?

My understanding is that the PG FlyCapture library is required to synchronously capture images for stereo processing. I'd like to interface my camera for some live tests using OpenCV under python (cv2).

Currently using Ubuntu 12.04

Any help is appreciated.

2014-03-14 16:50:07 -0600 received badge  Critic (source)
2014-03-14 12:49:05 -0600 received badge  Editor (source)
2014-03-14 12:45:37 -0600 commented answer Ripples in stereo disparity image?

Edited above to clarify. I start the stereo process with two rectified images and then use Q matrix calculated by cv2.stereoRectify() with focal length and Baseline data, but 0 distortion to project disparity into 3D space using cv2.reprojectImageTo3D. It is the 3D points that show show warped surface and ripples (ripples are also apparent in disparity image)

2014-03-13 14:53:24 -0600 asked a question Ripples in stereo disparity image?

I have a stereo image captured on relatively flat ground with the camera mounted above ground and pointed down at angle relative to horizontal. The source images are already rectified and aligned using the camera API.

When I calculate the disparity image in OpenCV using either BM or SGBM, the resulting disparity image shows "ripples". When this data is re-projected into 3D space using cv2.reprojectImageTo3D() the 3D points show a curved ground surface (e.g. warped around view axis) with ripples along the view axis. The re-projection matrix Q is calculated by cv2.stereoRectify() using the focal lengths (fx,fy) and Baseline data from rectified images, but use 0 distortion since the source images were already rectified and aligned.

My best guess is that the warping is due to the camera "calibration" parameters I'm using (fx,fy,B) (based on 3rd party calibration values), and that the ripples are based on the limits of subpixel interpolation. (I do not see this effect using the Point Grey libraries, so it is not the images themselves.)

Any suggestions on how to improve?

(Unfortunately, I can't post the relevant images.)

2014-02-19 14:28:40 -0600 received badge  Supporter (source)
2014-02-19 14:13:28 -0600 commented question Stereo Matching/Calibration Help

I'm interested in this answer as well. I'm trying to compare OpenCV stereo processing to what I get using the Point Grey (PG) libraries. I am trying to use images rectified by the PG software, and then generate the Q matrix using stereoRectify and parameters that I get from the PG calibration data. The resulting point cloud is curved improperly, and fails to generate point clouds at a distance. Are there any guidelines for comparing OpenCV and PG results?