A ROS2 wrapper for real-time object detection, 3D localization, and tracking using RGB-D camera inputs.
Object Analytics (OA) is a ROS2 wrapper module for real-time object detection, localization, and tracking. It processes RGB-D camera inputs to enable advanced robotics features like intelligent collision avoidance and people following by publishing object tracking in 2D images and localization in 3D camera coordinates.
ROS2 developers and robotics engineers building perception systems for robots that require real-time object analysis, such as those working on autonomous navigation, surveillance, or interactive robotics.
It provides a ready-to-use, integrated ROS2 solution that combines multiple state-of-the-art tracking algorithms and 3D localization, simplifying the development of complex robotics perception pipelines compared to building from scratch.
Object Analytics (OA) is a ROS2 module designed to provide real-time object analyses over RGB-D camera inputs. It enables robotics developers to create advanced features like intelligent collision avoidance, people following, and semantic SLAM by processing 2D images and 3D point cloud data. The module subscribes to object detection topics and publishes tracking and localization data.
Object Analytics aims to integrate state-of-the-art algorithms into a cohesive ROS2 wrapper, making advanced robotics perception accessible and performant for developers.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Supports real-time tracking with algorithms like KCF, TLD, and GOTURN, integrated via OpenCV3, as detailed in the tracker_regression tool.
Combines 2D image tracking with 3D point cloud data to locate objects in camera coordinates, enabling advanced robotics features.
Allows launching tracking, localization, or both via customizable launch files, providing flexibility for different use cases.
Includes tools like tracker_regression for precision and recall statistics, helping developers benchmark tracking algorithms.
Intel has ceased all development, maintenance, and updates, leaving no official support or bug fixes, as stated in the README.
Full features require building OpenCV3 from source, and the system is tied to Ubuntu 18.04 and specific hardware like Intel NUC.
Depends on ROS2 Dashing and older packages, which may not be compatible with newer systems or limit integration with modern tools.