pyboreas
pyboreas copied to clipboard
utiasASRL
Devkit for the Boreas autonomous driving dataset.
The [RTR paper](https://arxiv.org/pdf/2203.10174.pdf) assumes access to the ground-truth relative transformation of the first frame for initialization. For a fair comparison, consider adding a note to the localization benchmark saying using...
https://github.com/utiasASRL/pyboreas/blob/7a133355302a35a3e2c328a9d3d7ae27df188d7f/pyboreas/utils/odometry.py#L737 Either pitch or roll should be pi instead of 0 - maybe just round line[8] and line[7] to the nearest k * pi?
Needed by the Radar Teach Repeat paper and already implemented in `localization_eval` branch. Need to clearn up and merge into master.
The localization evaluation script uses variables defined in `splits.py` to detemine which sequence is used as reference and which sequences are for testing. Need to remind user to change these...
Boreas-2021-09-09-15-28 is a St. George sequence, shouldn't be added to localization benchmark.
Two issues with the 2021/09/02 sequence: - seems to have incorrect radar_poses.csv on AWS - need to compare AWS version with the navlab backup - misses ground truth pose for...
Hi, I noticed that in the labels of boreas-objects-v1, there are several frames where the tracking uuid is inconsistent with the previous frame (in the same scene). This causes an...
Hi, thanks for releasing this awesome Boreas Dataset. I have recently attempted visualization using the code provided below. The attached video demonstrates the output result. I am puzzled by the...
We want to make it hard for people to overfit to the test set. One way to do this is to limit how many submissions each user can make per...
