You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, I have a pair of stereo cameras from a VR headset that point at different angles. I've been able to get HybVIO to track stereo features only with -useRectification, but even then it doesn't seem possible for HybVIO to track features on the non-overlapping areas of the images.
Is there a way to avoid having to prerectify the images in this case?
Is it possible to track non-overlapping features in HybVIO?
Below is a stereo frame example obtained by running this command:
Hello! Your findings are consistent with our understanding of the capabilities of the current HybVIO code
Sometimes rectification is needed in practice or the left-to-right LK tracking fails (even though it "should not"). The current rectification implementation is very slow, which could be worked around by rectifying manually with, e.g, OpenCV before feeding the data to HybVIO (this also needs to be reflected in the calibration in parameters.txt). There are currently no work-arounds for the need for rectification in this case, except fixing/modifying the stereo LK-tracking implementation
The current code does not have the capability of tracking non-overlapping features in the case of -useStereo. It should be possible to extend the algorithm to support them
Hello, I have a pair of stereo cameras from a VR headset that point at different angles. I've been able to get HybVIO to track stereo features only with
-useRectification
, but even then it doesn't seem possible for HybVIO to track features on the non-overlapping areas of the images.Below is a stereo frame example obtained by running this command:
./main -i=../data/benchmark/ody-easy -p -c -s -windowResolution=640 -useSlam -useStereo -displayStereoMatching -useRectification
Over this HybVIO-formatted dataset. The original EuRoC-formatted dataset can be found here.
The text was updated successfully, but these errors were encountered: