# ROS Intel Movidius NCS Release – V0.5.0

**URL:** <https://discourse.openrobotics.org/t/ros-intel-movidius-ncs-release-v0-5-0/3530>\
**Category:** Projects\
**Tags:** release, kinetic\
**Created:** [December 25, 2017, 3:49am UTC](https://discourse.openrobotics.org/t/ros-intel-movidius-ncs-release-v0-5-0/3530 "2017-12-25T03:49:33Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![xhuan28](https://sea2.discourse-cdn.com/flex022/user_avatar/discourse.openrobotics.org/xhuan28/32/1838_2.png) [@xhuan28](https://discourse.openrobotics.org/u/xhuan28)\
**Post date:** [December 25, 2017, 3:49am UTC](https://discourse.openrobotics.org/t/ros-intel-movidius-ncs-release-v0-5-0/3530/1 "2017-12-25T03:49:33Z")

</div>

Hi All,

We are happy to announce the v0.5.0 release of ROS Intel Movidius NCS package.  
The Movidius™ Neural Compute Stick (NCS) is a tiny fanless deep learning device that you can use to learn AI programming at the edge. NCS is powered by the same low power high performance Movidius™ Vision Processing Unit (VPU) that can be found in millions of smart security cameras, gesture controlled drones, industrial machine vision equipment, and more.  
This project is a ROS wrapper for NC API of NCSDK, providing the following features:  
• A ROS service for object classification and detection of a static image file  
• A ROS publisher for object classification and detection of a video stream from a RGB camera  
• Demo applications to show the capabilities of ROS service and publisher  
• Support multiple CNN models of Caffe and Tensorflow, including  
o CNN models for object classification  
 AlexNet  
 GoogleNet  
 SqueezeNet  
 Inception\_V1  
 Inception\_V2  
 Inception\_V3  
 Inception\_V4  
 MobileNet  
o CNN models for object detection  
 MobileNet\_SSD  
 TinyYolo\_V1  
This project has been open sourced in github: [GitHub - intel/ros\_intel\_movidius\_ncs](https://github.com/intel/ros_intel_movidius_ncs). Please refer to README file for more details about this project. We have tested it on RealSense D400 series camera and Microsoft HD-300 USB camera. Welcome feedback and participation.