PRBonn/depth_clustering

Health v2 · maintenance only

Adoption not part of the score

1312 stars · 380 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A fast and robust C++ library for segmenting point clouds from Velodyne LiDAR sensors (16, 32, and 64 beam) into objects using depth clustering. It integrates with ROS and PCL and runs in real time.

Use cases

• segment velodyne point clouds into objects
• cluster lidar point clouds in real time
• detect objects from depth images generated by lidar
• preprocess lidar scans for autonomous driving
• integrate point cloud segmentation into a ros pipeline

When to choose

• you use Velodyne LiDAR sensors and need fast, real-time object segmentation
• you work in a ROS/catkin robotics stack
• you need a lightweight alternative to full PCL segmentation pipelines

When to avoid

• you need segmentation for non-Velodyne or non-rotating lidar sensors without adaptation
• you need a maintained project with recent releases
• you need GPU-accelerated or deep-learning-based segmentation

Facets

library · maturity maintenance

computer-vision image-processing parser robotics computer-vision autonomous-vehicles cpp lidar point-cloud velodyne depth-clustering ros catkin segmentation real-time linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PRBonn/depth_clustering")