hku-mars/livox_camera_calib

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1289 stars · 252 forks observed · 2026-08-28

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

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

application · maturity stable

computer-vision image-processing simulation robotics autonomous-vehicles computer-vision cpp lidar-camera-calibration extrinsic-calibration targetless-calibration point-cloud livox ros sensor-fusion ceres-solver linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hku-mars/livox_camera_calib")