-
Notifications
You must be signed in to change notification settings - Fork 390
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
no segments, calibration fails #91
Comments
Hi - this dataset worked fine for me when I tested with camodocal but that was in 2016 (I believe?). I haven't tested with the new version - there might have been some modification in the code since then. Did you have a look at the source code of what have caused of error? Sorry if I'm not helpful. |
@stanathong OK, I will try to debug it. By the way, How did you get the event.dat? Do I need to record the GPS and camera data simultaneously by using rosbag? |
In my system, I have a multi-cam system temporally synchronised with GPS. As a result, I only have images and GPS (lat, lon). Hence, I was only be able to derive the bearing angle from the GPS data and other angles to be 0 or fixed hand-measured values. The even.dat is created with the assumption that the ground plane is flat and all the angles are saved into the file as quarternion. |
Hello, I meet the same problem in Ubuntu 18.04 with OpenCV 3.4.4. But it is OK in my Ubuntu 16.04 with OpenCV 3.3.0. Do you solve it? |
I encountered this problem when I have CUDA installed in my system.Managed to resolve this by building camodocal without CUDA. Just comment the following lines in
|
hi,where can i get this datasets for test ? |
+1 |
@stanathong I am trying to test the data. Unfortunately, after about twenty minutes, I got an error shown at the above pic, does anyone has met the same problem? highly appreciated if you could give some cues.
The text was updated successfully, but these errors were encountered: