# PRBonn/depth_clustering

:taxi: Fast and robust clustering of point clouds generated with a Velodyne sensor.

Repository: https://github.com/PRBonn/depth_clustering
Canonical: https://ross.abutalabs.com/products/depth_clustering
Language: C++
License: MIT
License Family: permissive
Topics: catkin, velodyne-sensor, segmentation, clustering, velodyne, real-time, fast, ros, point-cloud, depth-image, depth, range, range-image, pcl, depth-clustering, lidar, robotics
Last push: 2021-11-11T12:58:42+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3572, "days_push": 1756, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1312, forks 380 (observed 2026-08-28T04:04:20.278646+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, parser
- domain: robotics, computer-vision, autonomous-vehicles
- platform: cpp
- tags: lidar, point-cloud, velodyne, depth-clustering, ros, catkin, segmentation, real-time, linux

## Member repositories
- PRBonn/depth_clustering (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.278646+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:48:56.879405+00:00, confidence not recorded.
  - readme: https://github.com/PRBonn/depth_clustering (fetched 2026-08-28T04:04:20.278646+00:00, sha 0528490fcd31)
- Data as of 2026-08-30T08:39:29.467469+00:00.