Open software that robots run on, with the license read from each project's license file, whether it is still maintained, and the robots on Robotheca that use it. A reference, not a download site: every entry links to its source.
Page 1 of 2 · newest commit first
A ROS2 driver that streams raw event-camera data from Prophesee Metavision SDK cameras and publishes it as ROS event_camera_msgs. Not written or supported by Prophesee.
Kornia is a differentiable computer vision library built on PyTorch, offering image processing, augmentation, geometry and pretrained AI models that integrate into deep learning workflows.
MediaPipe is an open-source framework and set of libraries for building on-device machine learning features such as vision, text, and audio tasks across mobile, web, desktop, and edge devices.
COLMAP is a general-purpose Structure-from-Motion and Multi-View Stereo pipeline with graphical and command-line interfaces, for reconstructing 3D scenes from image collections.
OpenCV is an open source computer vision library. It provides tools for image and video processing and analysis, with documentation, a Q&A forum and an issue tracker for users and contributors.
Ultralytics YOLO is a family of computer vision models and a Python package for detection, segmentation, pose, classification, depth and tracking tasks. It offers CLI and Python interfaces.
A ROS 2 node that publishes images and camera parameters from a range of cameras via libcamera, including V4L2 and Raspberry Pi camera modules.
ViSP is a cross-platform C++ library for prototyping visual tracking and visual servoing applications, including control laws for robots and simulation tools.
A C++ library with Python bindings for interfacing with Luxonis DepthAI hardware, supporting pipelines that can span one or several devices.
Vosk is an offline open source speech recognition toolkit supporting more than 20 languages, with streaming recognition and bindings for many programming languages.
Nebula is a universal sensor driver platform for ROS 2, mainly targeting Ethernet-based LiDAR sensors, and is the recommended driver for the Autoware project.
A ROS 2 metapackage bundling image_transport plugins that compress image topics for transport between nodes.
ROS packages for OAK cameras from Luxonis, giving ROS access to their depth and vision camera hardware. Documentation is maintained separately on the Luxonis docs site.
Picamera2 is a Python library for controlling Raspberry Pi cameras through the libcamera stack, replacing the older Picamera library. It offers an easy-to-use Python API.
ROS 2 driver that connects Intel RealSense depth cameras to ROS 2, publishing their color, depth, infrared, IMU and point cloud streams as ROS topics.
A cross-platform SDK for Intel RealSense depth cameras, providing depth and colour streaming plus intrinsic and extrinsic calibration data.
A standalone open-source library for processing 2D and 3D images and point clouds, aimed at robotics and research work.
A ROS 2 node that detects AprilTag markers in images and publishes their poses, ids and detection metadata. It is built on the AprilTag library.
A ROS 2 image transport plugin that encodes and decodes camera frames with FFmpeg/libav, such as H.264 and HEVC packets, to stream images across a network.
A ROS 2 wrapper that connects Orbbec depth cameras and LiDAR sensors to the ROS 2 ecosystem, supporting several ROS 2 distributions.
A ROS package for detecting and locating known objects in camera images, usable as a standalone tool, on ROS 1, and on ROS 2. It matches images of objects against a live camera feed.
An open-source cross-platform C/C++ SDK for interfacing with Orbbec RGB-D cameras, with wrappers for other languages and frameworks. It is the successor to Orbbec SDK v1.
A ROS package wrapping the Aruco augmented-reality marker detector, for tracking markers and estimating their poses from camera images.
A ROS 2 package with two components that convert PointCloud2 messages to LaserScan messages and back. It is a port of the original ROS 1 package.
Projects 1–24 of 36