AndreiBarsan/DynSLAM
Master's Thesis on Simultaneous Localization and Mapping in dynamic environments. Separately reconstructs both the static environment and the dynamic objects from it, such as cars.
This project helps self-driving car engineers and robotics researchers by accurately mapping dynamic outdoor environments. It takes in stereo camera feeds and processes them to generate a detailed 3D reconstruction of both the static surroundings (like roads and buildings) and moving objects (like other cars), helping to build robust perceptions of complex, real-world scenes. This is for professionals developing autonomous navigation systems.
573 stars. No commits in the last 6 months.
Use this if you need to create precise 3D maps in environments where objects are constantly moving, such as for autonomous vehicle navigation or mobile robotics.
Not ideal if your application primarily involves static indoor environments or if you require real-time processing on embedded systems with limited computational power.
Stars
573
Forks
177
Language
Jupyter Notebook
License
BSD-3-Clause
Category
Last pushed
Sep 30, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AndreiBarsan/DynSLAM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
gradslam/gradslam
gradslam is an open source differentiable dense SLAM library for PyTorch
jbwang1997/OPUS
OPUS: Occupancy Prediction Using a Sparse Set
ai4ce/DiscoNet
[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception
mchancan/deepseqslam
The Official Deep Learning Framework for Robot Place Learning
KwanWaiPang/Awesome-Transformer-based-SLAM
Paper Survey for Transformer-based SLAM