Guide ROS 2 computer vision pipelines with OpenCV, depth sensing, and YOLO.
npx skills add https://github.com/robotics-playground/skills --skill cv-detection
Please help me install this Agent Skill. Skill: cv-detection Source: https://github.com/robotics-playground/skills/tree/main/skills/cv-detection Command: npx skills add https://github.com/robotics-playground/skills --skill cv-detection
Solves the problem of building robust ROS 2 computer vision pipelines by providing end-to-end guidance for OpenCV integration, depth sensing, and object detection.
Create a ROS 2 computer vision workflow that subscribes to a camera image, runs OpenCV and YOLO detections, and publishes an annotated result stream.
High-intent search queries and answers about installing and using this skill.
To integrate OpenCV with ROS 2, you use cv_bridge and image_transport to convert ROS image messages into OpenCV matrices for real-time processing. This Skill provides end-to-end guidance for building robust ROS 2 computer vision pipelines and publishing annotated result streams.
You can run YOLO object detection in ROS 2 by subscribing to a camera image topic, processing the frames with YOLOv8 or YOLOv11, and publishing the detection results. This Skill details the model workflows for training, inference, and deployment within ROS 2 nodes.
Yes, you can use depth sensing and point clouds with ROS 2 for 3D object detection by utilizing depth data and TF frames. This Skill guides you through using depth cameras like OAK-D with depthai_ros to support navigation, inspection, and quality control tasks.
The best way to calibrate cameras and optimize image pipelines in ROS 2 is to follow structured calibration workflows and image encoding best practices. This Skill provides references for ROS 2 image pipeline optimization to ensure rapid prototyping and production deployment.
Yes, this ROS 2 computer vision guidance explicitly supports specialized hardware including OAK-D, Jetson, and standard cameras. It provides tailored workflows for depth sensing, YOLO-based detections, and real-time image processing across these specific hardware platforms.
wimbleroboticsDetect objects in ROS 2 camera streams with 2D detections and 3D localization.
wimbleroboticsOrchestrate depth camera data into point clouds and 2D laser scans for ROS 2 Nav2.
wimbleroboticsConfigures RViz2 displays, camera views, and QoS settings for ROS 2 robots.
wimbleroboticsEnable on-device spatial AI inference and depth sensing with DepthAI/OAK-D cameras.
