How to install vision_visp on Ubuntu with ROS 2?

First, install ROS 2 core and ViSP separately using their official guides, then clone the vision_visp repository into your ROS 2 workspace and build with colcon, specifying VISP_DIR if ViSP is not automatically found, as per the README instructions.

What's the difference between visp_tracker and visp_auto_tracker?

visp_tracker requires manual user interaction for initialization, while visp_auto_tracker uses markers like AprilTag or QR codes for automated setup and includes recovery features to handle tracking failures, making it more robust for continuous operation.

vision_visp vs OpenCV for ROS 2 tracking?

vision_visp is specialized for visual servoing and model-based tracking with recovery, ideal for robotic control, whereas OpenCV offers broader computer vision functions but less integration for servoing. Choose vision_visp if you need ViSP's algorithms in ROS 2.

How to calibrate a camera using visp_camera_calibration?

Launch the visp_camera_calibration tool in ROS 2, use calibration patterns supported by ViSP, and follow on-screen prompts to compute intrinsic parameters, which are then available for other vision tasks in the stack.

Does vision_visp support deep learning models?

No, vision_visp primarily interfaces with ViSP's model-based algorithms; for deep learning, you'd need to integrate other ROS 2 packages or custom bridges, as this stack doesn't provide native support.

Can I use vision_visp with ROS 1?

No, vision_visp is specifically designed for ROS 2; for ROS 1, you would need to seek alternative integrations or older versions, as this stack targets the newer ROS 2 ecosystem exclusively.

Open-Awesome

vision_visp

GPL-2.0C++vision_visp-0.5.0

ROS 2 packages for visual servoing and tracking using the ViSP library.

Visit Website GitHub

224 stars101 forks0 contributors

What is vision_visp?

vision_visp is a ROS 2 stack that provides interfaces to the ViSP (Visual Servoing Platform) library for robotics vision applications. It enables visual servoing, model-based tracking, and camera calibration within the ROS 2 ecosystem, solving the problem of integrating advanced computer vision algorithms into robotic systems. The stack includes tools for tracking objects, calibrating cameras, and estimating hand-eye transformations.

Target Audience

Robotics engineers and researchers working on vision-based control systems, particularly those using ROS 2 and needing visual servoing, object tracking, or camera calibration capabilities.

Value Proposition

Developers choose vision_visp because it bridges the powerful, academic-grade ViSP library with ROS 2, offering reliable tracking, calibration, and servoing tools without requiring custom integration. Its automated recovery and marker-based initialization provide robustness for real-world robotics applications.

Overview

ViSP stack for ROS

Use Cases

Best For

Implementing visual servoing for robotic arm control
Tracking objects in real-time for robotics applications
Calibrating camera intrinsic parameters in ROS 2 systems
Estimating hand-eye transformations for robotic manipulation
Using AprilTag or QR code markers for automated tracking initialization
Building vision-based robotics systems with recovery from tracking failures

Not Ideal For

Robotics projects not using ROS 2 as their middleware framework
Applications requiring simple, plug-and-play computer vision without calibration or tracking complexities
Teams needing deep learning-based object detection or recognition out of the box
Projects with strict real-time latency constraints where bridge overhead is unacceptable

Pros & Cons

Pros

Seamless ROS 2 Integration

Provides direct bridges between ROS 2 image/geometry messages and ViSP representations, enabling easy deployment in ROS 2-based robotic systems without custom message handling.

Advanced Tracking with Recovery

Includes visp_auto_tracker with automated marker-based initialization (e.g., AprilTag) and recovery mechanisms for robust tracking in dynamic environments, as highlighted in the README.

Comprehensive Calibration Tools

Offers visp_camera_calibration and visp_handeye_calibration for accurate camera intrinsic and hand-eye transformation estimation, leveraging ViSP's proven algorithms.

Academic-Grade Algorithms

Leverages ViSP's well-tested visual servoing and tracking libraries, providing reliable, research-backed performance for production robotics.

Cons

Complex Dependency Setup

Requires separate installation of both ROS 2 and ViSP, with potential build issues like needing VISP_DIR, making setup non-trivial and error-prone for newcomers.

Limited to Model-Based Approaches

Focuses on traditional model-based tracking and servoing, lacking built-in support for modern data-driven or deep learning methods, which may limit flexibility in some applications.

Tight Coupling with ViSP

Creates vendor lock-in to ViSP's API and development cycle, making it difficult to switch to alternative vision libraries without significant rework.

Frequently Asked Questions

Related Projects

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Stars34,624

Forks7,947

Last commit1 month ago

EasyOCR

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Stars29,814

Forks3,583

Last commit7 months ago

imgaug

Image augmentation for machine learning experiments.

Stars14,739

Forks2,450

Last commit2 years ago

meshroom

Node-based Visual Programming Toolbox

Stars12,846

Forks1,219

Last commit8 hours ago

Community-curated · Updated weekly · 100% open source

Found a gem we're missing?

Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.

Submit a project Star on GitHub