Revision history [back]

Hi,

I have a question regarding procedure for stereo correspondence ( for computing disparity ( and depth ) images )

Which of the following 2 procedures is supposed to be used ? And why would you prefer one over the other ?

1. Using SURSIFT based detectors/descriptors + DescriptoMAtcher library ( eg:- FLANN )
2. Or using StereoSGBM/ StereoBM classes provided by openCV ?

Thanks!

Hi,

I have a question regarding procedure for stereo correspondence ( for computing disparity ( and depth ) images )

Which of the following 2 procedures is supposed to be used ? And why would you prefer one over the other ?

1. Using SURSIFT based detectors/descriptors + DescriptoMAtcher library ( eg:- FLANN )
2. Or using StereoSGBM/ StereoBM classes provided by openCV ?

Thanks!

Hi,

I have a question regarding procedure for stereo correspondence ( for computing disparity ( and depth ) images )

Which of the following 2 procedures is supposed to be used ? And why would you prefer one over the other ?

I am aware 1) will lead to sparse point cloud and 2) will lead to dense. However I have tried 2) and haven't yet got great results ( even on using a trackbar and fine tuning the parameters )

Thanks!

Hi,

I have a question regarding procedure for stereo correspondence correspondence ( for computing disparity ( and depth ) images )

Which of the following 2 procedures is supposed to be used ? And why would you prefer one over the other ?

1. Using SURSIFT SURF/SIFT based detectors/descriptors + DescriptoMAtcher library DescriptorMatcher ( eg:- FLANN library )
2. Or using StereoSGBM/ StereoBM classes provided by openCV ?

I am aware 1) will lead to sparse point cloud and 2) will lead to dense. However I have tried 2) and haven't yet got great results ( even on using a trackbar and fine tuning the parameters )

Thanks!

Hi,

Update: Several people have suggested improving calibration ( reducing rms reprojection error ) for getting a better depth/disparity map but -

1) What should be the rms error range ( approx ) ?

2) I can't find a fixed way of improving calibration even after providing images at different orientations and z-depth. (I randomly get a few "okay" rms error every now and then ) what else can I do ?

//========================================

Question:

I have a question regarding procedure for stereo correspondence ( for computing disparity ( and depth ) images )

Which of the following 2 procedures is supposed to be used ? And why would you prefer one over the other ?

1. Using SURF/SIFT based detectors/descriptors + DescriptorMatcher ( eg:- FLANN library )
2. Or using StereoSGBM/ StereoBM classes provided by openCV ?

I am aware of the following -

However I have tried 2) 2) and haven't yet got great results ( even on using a trackbar and fine tuning the parameters )

Thanks!