Discussion: ROS/ROS2 OpenVINO Toolkit new features in Y2021

Computer Vision / Perception
, , ,
1

Hi, ROSers,
I am now planning the new features and development plans for ROS/ROS2 OpenVINO Toolkit projects.
In order to better fit the feature requirements with the limited work load, I would like to gather requirements from the developers, real users or field experts as the first step, then filter them in a feasible development priorities and schedules.

Here are some thoughts about migration/development activities, wish anyone interested can share yours:

  • Support latest ROS/ROS 2 versions and OpenVINO versions
  • Support more popular models and inferences, to better fix robotics use scenarios
  • GUI-based AI Inference Pipeline Configuration tool, to ease the OpenVINO Toolkit’s use and deployment.
  • Docker image support

Please feel free to share your thoughts, what features do you want this project have?

You may comment here, or add your comments to ROS OpenVINO repo or ROS2 OpenVINO repo

Thanks.

2 Likes
2

This sounds great!
My biggest concern is compatibility. In the past I had a project with Realsense and the first movidius stick. We used Openvino, ROS, OpenCV and Tensorflow. We had quite some issues with different python and opencv versions that were required.

I’m not sure if this is still an issue with the most recent hardware and software though.

3

We used Openvino, ROS, OpenCV and Tensorflow. We had quite some issues with different python and opencv versions that were required.

Thank you very much for your attention, @lars. Did you use ROS OpenVINO project or you developed your own ROS node by leveraging OpenVINO’s features? One of the main goals of OpenVINO project is to try to provide good solution for heterogenous computing and compatibility between IA hardware, but they were not aligned well among different versions.
It’s really a good direction for ROS/ROS2 OpenVINO toolkit projects to provide more and better solutions for compatibility issues, for example, doing more validation and tests, simplifying compiling and building process, creating docker images, etc.