We are happy to announce the initial release of “ros2_openvino_toolkit”. The OpenVINO™ toolkit quickly deploys applications and solutions that emulate human vision. Based on Convolutional Neural Networks (CNN), the Toolkit extends computer vision (CV) workloads across Intel® hardware, maximizing performance.
This project is a ROS2 wrapper for CV API of OpenVINO™, providing the following features:
- Support CPU and GPU. FPGA and Movidius will be supported in the future.
- Support standard USB camera and Intel® RealSense™ camera
- Support Video and Image file as detection source
- Support person-attributes-recognition, including face detection, emotion recognition, age gender recognition and head pose recognition.
- Demo application to show above detection and recognition.
This project has been open sourced in github: https://github.com/intel/ros2_openvino_toolkit. Please refer to README file for more details about this project. We have tested it on RealSense D400 series camera and Standard USB camera. More features, such as object detection, vehicle-attributes-recognition and license-plate-recognition are under development and will be included in future release. Stay tuned. Welcome feedback and participation.