RTK-SLAM Absolute Accuracy#

Handheld LiDAR, camera, IMU and GNSS sequences measured against surveyed checkpoints, as native .mcap episodes.

A handheld rig carrying a Livox MID360, a global shutter camera and a GNSS receiver is walked through a public park and a construction hall. Both block the sky in places, including a 30 m underpass and an indoor hall spanning more than 400 seconds of the route.

The reference is not the GNSS. A geodetic total station surveyed 87 checkpoints along the routes independently, so absolute error can be measured without first fitting the estimate onto the reference. Three published trajectories are carried alongside the sensors, together with each one’s distance to every checkpoint.

Four sequences and 64.6 minutes of walking, over 76,409 camera frames, 38,175 LiDAR sweeps, 763,673 IMU samples and 38,202 GNSS fixes.

Details

Example usage

 1import fiftyone as fo
 2import fiftyone.zoo as foz
 3
 4dataset = foz.load_zoo_dataset("rtk-slam-absolute-accuracy")
 5
 6# Where the sky was hardest to see
 7view = dataset.sort_by("gnss_fix_rate")
 8
 9# The routes that go indoors
10view = dataset.match({"site": "construction"})
11
12session = fo.launch_app(dataset)
rtk-slam-absolute-accuracy