PRBonn/MapMOS
Building Volumetric Beliefs for Dynamic Environments Exploiting Map-Based Moving Object Segmentation (RAL 2023)
This tool helps autonomous navigation systems understand their surroundings by identifying and tracking moving objects. It takes raw 3D point cloud data, like that from LiDAR sensors, and produces a detailed, evolving map that distinguishes between stationary parts of the environment and dynamic elements like vehicles or pedestrians. Robotics engineers and researchers working on self-driving cars or mobile robots would use this to improve situational awareness and path planning.
187 stars. No commits in the last 6 months.
Use this if you need to reliably detect and segment moving objects within complex 3D LiDAR point cloud scans to create a dynamic occupancy map.
Not ideal if you are working with static environments or primarily with 2D sensor data like cameras, as it's optimized for 3D dynamic scene understanding.
Stars
187
Forks
11
Language
Python
License
MIT
Category
Last pushed
Sep 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/PRBonn/MapMOS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
drprojects/superpoint_transformer
Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D...
yuxumin/PoinTr
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
charlesq34/frustum-pointnets
Frustum PointNets for 3D Object Detection from RGB-D Data
drprojects/DeepViewAgg
[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in...
facebookresearch/votenet
Deep Hough Voting for 3D Object Detection in Point Clouds