IoT Reference Implementation: How to Build an Intruder Detector Solution

Intruder Detector

An application capable of detecting any number of objects from a video input.

What it Does

This application is one of a series of IoT reference implementations aimed at instructing users on how to develop a working solution for a particular problem. It demonstrates how to create a smart video IoT solution using Intel® hardware and software tools. This solution detects any number of objects in a designated area providing number of objects in the frame and total count.

How it Works

The counter uses the Inference Engine included in OpenVINO™. A trained neural network detects objects within a designated area by displaying a green bounding box over them, and registers them in a logging system.

Requirements

Hardware

  • 6th Generation Intel® Core™ processor with Intel® Iris® Pro graphics and Intel® HD Graphics

Software

  • Ubuntu* 16.04 LTS       Note: You must be running kernel version 4.7+ to use this software. We recommend using a 4.14+ kernel to use this software. Run the following command to determine your kernel version:
uname -a
  • OpenCL™ Runtime Package
  • OpenVINO™

 

Visit Project on GitHub

For more complete information about compiler optimizations, see our Optimization Notice.