# hku-mars/livox_camera_calib

This repository is used for automatic calibration between high resolution LiDAR and camera in targetless scenes.

Repository: https://github.com/hku-mars/livox_camera_calib
Canonical: https://ross.abutalabs.com/products/livox_camera_calib
Language: C++
License: GPL-2.0
License Family: copyleft
Topics: calibration, point-cloud
Last push: 2024-08-21T00:53:17+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2013, "days_push": 743, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1289, forks 252 (observed 2026-08-28T04:04:15.296416+00:00)

## What it is
A C++/ROS tool from HKU MARS for automatic extrinsic calibration between high-resolution LiDAR (e.g., Livox) and cameras in targetless environments. It uses edge information from indoor or outdoor scenes to achieve pixel-level accuracy, supporting both single- and multi-scene calibration.

## Use cases
- calibrate livox lidar to camera extrinsics without a calibration target
- align point cloud with camera image pixel-level
- targetless lidar camera extrinsic calibration
- multi-scene lidar camera calibration for robustness
- colorize point cloud using camera image after calibration
- extrinsic self calibration of high resolution lidar and camera

## When to choose
- you use a Livox or other high-resolution LiDAR with a camera on Ubuntu/ROS
- you cannot use a chessboard or calibration target in the scene
- you need pixel-level extrinsic accuracy for sensor fusion or point cloud colorization
- you want multi-scene calibration for extra robustness

## When to avoid
- you are not on Ubuntu 16.04/18.04 with ROS Kinetic/Melodic
- you need a target-based calibration workflow or a different sensor pair (e.g., radar-camera)
- you need a maintained cross-platform tool with recent ROS2 support
- your scene lacks edge features for the algorithm to work with

## Facets
- artifact type: application
- maturity: stable
- function: computer-vision, image-processing, simulation
- domain: robotics, autonomous-vehicles, computer-vision
- platform: cpp
- tags: lidar-camera-calibration, extrinsic-calibration, targetless-calibration, point-cloud, livox, ros, sensor-fusion, ceres-solver, linux

## Member repositories
- hku-mars/livox_camera_calib (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:15.296416+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 2026-08-30T04:55:44.236003+00:00, confidence not recorded.
  - readme: https://github.com/hku-mars/livox_camera_calib (fetched 2026-08-28T04:04:15.296416+00:00, sha 2f0374651ca2)
- Data as of 2026-08-30T08:39:29.467469+00:00.