ctu-vras/traversability_estimation
Semantic Segmentation of Images and Point Clouds for Traversability Estimation
This project helps roboticists and autonomous vehicle developers create safer navigation systems. It takes raw camera images or LiDAR point cloud data and processes it to identify areas that are safe or unsafe for a robot to traverse. The output is a segmented map, indicating obstacles or difficult terrain, which can be used by a robot's planning module to plot a safe course.
No commits in the last 6 months.
Use this if you need to equip an autonomous robot or vehicle with the ability to understand its environment and avoid obstacles in mostly static settings.
Not ideal if your robot operates in highly dynamic environments with rapidly changing obstacles, or if you only need basic obstacle detection without detailed terrain analysis.
Stars
81
Forks
13
Language
Python
License
BSD-3-Clause
Category
Last pushed
Oct 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ctu-vras/traversability_estimation"
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:
NazirNayal8/RbA
Official code for RbA: Segmenting Unknown Regions Rejected by All (ICCV 2023)