Skip to content
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

Recommendations for 3D Outdoor Mapping with RTAB-Map #1219

Open
csvicbot-7 opened this issue Oct 12, 2024 · 1 comment
Open

Recommendations for 3D Outdoor Mapping with RTAB-Map #1219

csvicbot-7 opened this issue Oct 12, 2024 · 1 comment

Comments

@csvicbot-7
Copy link

Hi @matlabbe

I usually use RTAB-Map with a 3D LiDAR and wheel odometry to build indoor maps. However, I am starting a new project to build an outdoor map, similar to the video published by RTAB-Map in 2022: "Car Mapping with RTAB-Map on CAT Vehicle Simulator (CitySim)" link

Here’s a summary of the project specifications:

  • Build a 3D map of a neighborhood.

  • The map must capture details such as poles, street lights, power and telecom cables, billboards, scaffolding, and ladders.

  • The required map accuracy is between 15 to 20 cm.

Which 3D LiDAR sensor and cameras would you recommend for optimal use with RTAB-Map?

@matlabbe
Copy link
Member

matlabbe commented Oct 13, 2024

Most 3D spinning LiDARs would work (with range > 50 meters). For stereo cameras, on a vehicle, a large baseline seems to be better as good features to track are generally >>> 15 meters away. If you use a LiDAR, an IMU for deskewing is required (that was not required in the simulator because the simulated LiDAR is not actually rotating and all points are taken at the same time for "one full rotation").

Not that if you rely only on LiDAR/IMU for motion estimation, you could have also only monocular cameras instead to color the laser scans and loop closures.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants