Head-Counting using Raspberry Pi

Introduction

  • The use of micro-processor is tremendously increasing in the era of smart and connected world.
  • With the increase in amount and velocity of data, it is required to process the data in a real time manner (or near to real time) to generate the actionable events from the data using the low-cost microprocessor.
  • Use case focused on cutting edge areas i.e. Internet of Things, Image processing, and Data Analytics etc.
  • Ability to deal with both structured (i.e. motion detection true/false) and unstructured (i.e. image) data.
  • It can also be applicable to scenario where limited internet connectivity is available (by implementing the local broker based MQTT implementation).

Architecture

Experiment Setup*

Hardware, Tools and Technology Used

Hardware used:

Technology (library) used:

  • Node.js- A Lightweight scripting language with small memory footprint
  • Opencv*- Computer Vision library
  • Node opencv module** to utilize the power of image processing on micro-controller
  • Node rasipcam^ module to enable the functionality of Raspberry Pi camera module

*Installation steps are available at http://www.pyimagesearch.com/2015/02/23/install-opencv-and-python-on-your-raspberry-pi-2-and-b/

**Node opencv module is available at https://www.npmjs.com/package/opencv

^Node raspicam module is available at https://www.npmjs.com/package/raspicam

 

Result (1/1)

 

Result (1/1)

 

Future Direction

  • In the current scenario, Node.js code captures the image periodically and count the head using image processing technique (limitation).
  • Notifying the camera module to capture the image if motion is detected by PIR Motion sensor (in-progress).
  • Detecting the common faces in the two corresponding images and ignore them for head count.
  • Developing HVAC application (ideal scenario of shopping mall and auditorium- How to manage the HVAC with dynamic visitors/participants) by re-using the architecture (sounds interesting ???).

 

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.