People Detecting and Counting System

In present days, people detecting and counting is an important aspect in the video investigation and subjective demand in computer vision systems. For many applications, it is necessary to identify people and then accurately count the number of people in real time or near real time. To perform people counting, a robust system for people detection is needed. The system is designed to be able to calculate the number of people entering and exiting a room. The system is implemented using a raspberry pi camera to capture images, laptop to train a model for specific dataset, and raspberry pi 3 model B to apply the model, count detected person and send the number of people going in and out of room to the web server. Information from people counting support the retail shops to analyze customer visit patterns. In addition, it can also give useful information in the implementation of internet of things for smart rooms or smart buildings such as automation of room lights.