ibrahimhroob/SPS
Generalizable Stable Points Segmentation for 3D LiDAR Scan-to-Map Long-Term Localization
This project helps autonomous systems, like robots or self-driving vehicles, maintain accurate localization over long periods in changing outdoor environments. It takes 3D LiDAR scans and existing environment maps as input to identify and separate stable points (like buildings or terrain) from unstable points (like growing plants or moving objects). This segmentation allows the system to build and use more reliable maps, enabling engineers to develop robust navigation systems for dynamic outdoor settings like vineyards or parking lots.
No commits in the last 6 months.
Use this if you need to improve the long-term localization accuracy of autonomous systems using 3D LiDAR in environments that change over time, such as due to seasonal plant growth or reconfigurations.
Not ideal if your application doesn't involve outdoor, changing environments, or if you are not working with 3D LiDAR scan-to-map localization.
Stars
17
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jun 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ibrahimhroob/SPS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
JonasSchult/Mask3D
Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet,...
nsavinov/semantic3dnet
Point cloud semantic segmentation via Deep 3D Convolutional Neural Network
PRBonn/LiDAR-MOS
(LMNet) Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting...
yanx27/2DPASS
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (ECCV 2022) :fire:
ctu-vras/traversability_estimation
Semantic Segmentation of Images and Point Clouds for Traversability Estimation