We developed a ROS wrapper for NC API of latest NCSDK, providing the following features:
Support NCSDK v1.09.00 and above
Support RealSense D400 series camera
A ROS service for classifying objects in a static image file
A ROS publisher for classifying objects in a video stream from a RGB camera
Demo applications to show the capabilities of ROS service and publisher
Support multiple CNN models
Source project at https://github.com/intel/ros_intel_movidius_ncs with v0.4.0 tag. With this release, ROS developers are powered with deep learning technology which provides object inference information, thus be able to build more intelligent Robotics usages.
Current version(V0.4.0) only supports object classification, but we are working on enabling CNN models for object detection with bounding box. This feature will come in next release soon.
