Hello
First of all, thank you for sharing OrbSlam library.
Second, after checking it with TUM database it appears that the algorithm is not stable:
- Several initializations with the same database produce different results.
- Sometimes SLAM stuck in reset mode (Resetting database) for almost all datasets from freiburg1.
- Sometimes track is lost and SLAM exits with error.
I've noticed one smooth run on "rgbd_dataset_freiburg2_360_hemisphere" while also some initializations appear to stuck or loose track.
Also it seems to work rather slowly (5-10 fps) sometimes slower.
Hello
First of all, thank you for sharing OrbSlam library.
Second, after checking it with TUM database it appears that the algorithm is not stable:
I've noticed one smooth run on "rgbd_dataset_freiburg2_360_hemisphere" while also some initializations appear to stuck or loose track.
Also it seems to work rather slowly (5-10 fps) sometimes slower.