Create a Store Aisle Monitor

Use a visual heat or motion map to count the number of people that enter and exit a store, factory, or warehouse aisle.

Target Operating System Ubuntu* 16.04 LTS
Time to Complete 30 minutes

GitHub* (C++) GitHub (Python*)

What You Will Learn

Using a video source (webcam or loaded video), generate a visual heat map or motion map, count the number of people present, and analyze the results. Create an output video and save a specific snapshot of it to send to the cloud.

Gain insight into the following solutions:

  • Computer vision applications for IoT
  • Inference to analyze datasets
  • Retail market IoT

Use the skills learned in this reference implementation to develop similar IoT solutions.

Learn to build and run an application with these capabilities:

Detect and register the number of people passing in and out of the camera frame.
Generate a heat or motion map.
Capture video and save snapshots.

How It Works

The application uses the captured video source and preprocesses the video frames through a heat map function, as well as a people-counting inference function. The results are then merged for the final output and stored both locally and in the cloud.

  1. Visualizing movement patterns over time starts with preprocessing the video frames using the HeatMap generation function and apply ColorMap to create a heat map.
  2. Using the inference engine in the Intel® Distribution of OpenVINO™ toolkit, it detects and counts the number of people within the video frame, and then draws a bounding box over each person detected.
  3. The video frames are merged to create the final output and are saved as snapshots locally. The snapshots can be uploaded to the cloud as a data blob using the Microsoft Azure* for Python* SDK.

Tools We Used

Intel® System Studio

An all-in-one, cross-platform tool suite, built to simplify system bring-up and improve system and IoT device application performance.