Link Search Menu Expand Document



This app does semantic segmentation using the semantic-segmentation-adas-0001, the Intel Movidius Neural Compute Stick 2, OpenVINO Toolkit 2020.1 and the Intel® RealSense™ depth camera. The app takes color and depth frames from a video stream from the Intel RealSense depth camera (tested with Intel RealSense D415) and performs semantic segmentation on the color frames. The semantic segmentation inference results will colorize pixels and overlay them onto the color frame. These colorized pixels represent different objects. Based on where the mouse pointer is at, the app will tell you what object and the distance to that object on a pixel by pixel basis.


This program requires:

Note: All development and testing has been done on Ubuntu 16.04 on an x86-64 machine.

Realsense SDK Note: You can install the Intel RealSense SDK 2.0 packages by running the command: ‘make install-reqs’. This will install the following packages:

  • librealsense2-dkms - Deploys the librealsense2 udev rules, build and activate kernel modules, runtime library.
  • librealsense2-dev - Includes the header files and symbolic links for developers.

Building the Example

To run the example code do the following :

  1. Open a terminal and change directory to the sample base directory
  2. Connect your Intel RealSense depth camera and NCS device.
  3. Type the following command in the terminal: make all

Note: Make sure your Intel RealSense libraries are installed beforehand.

Running the Example

After building the example you can run the example code by doing the following :

  1. Open a terminal and change directory to the sample base directory
  2. Type the following command in the terminal: make run

When the application runs normally, another window should pop up and show the feed from the Intel RealSense depth camera. The program should perform inferences on frames taken from the Intel RealSense depth camera.


  • q or Q - Quit the application


Provided Makefile has various targets that help with the above mentioned tasks.

make run or make run_cpp

Runs the sample application.

make help

Shows available targets.

make all

Builds and/or gathers all the required files needed to run the application.

make data

Gathers all of the required data need to run the sample.

make deps

Builds all of the dependencies needed to run the sample.

make install-reqs

Checks required packages that aren’t installed as part of the OpenVINO installation.

make uninstall-reqs

Uninstalls requirements that were installed by the sample program.

make clean

Removes all the temporary files that are created by the Makefile.

This repository is distributed under the MIT License. Individual applications and networks may retain individual copyrights. Other copyrights and trademarks may be property of others. All rights reserved.