[ros-users] [Discourse.ros.org] [Computer Vision / Perception] Proposal - New Computer Vision Message Standards

[Rein Appeldoorn]

Nice effort! What about also define interfaces for annotations?

We also try to define "generic" interfaces:

https://github.com/tue-robotics/image_recognition/tree/master/image_recognition_msgs/msg

However, it's hard to capture things as:
- [Face Properties](https://github.com/tue-robotics/image_recognition/blob/master/image_recognition_msgs/msg/FaceProperties.msg ): as a result from [Skybiometry for example](https://github.com/tue-robotics/image_recognition/tree/master/skybiometry_ros)
- Poses e.g. [Openpose](https://github.com/CMU-Perceptual-Computing-Lab/openpose) 

I think you would also like to define something as detection or feature groups that belong together. Maybe take a look at how [GeoJson](http://geojson.org/geojson-spec.html) does it.






---
[Visit Topic](https://discourse.ros.org/t/proposal-new-computer-vision-message-standards/1819/2) or reply to this email to respond.