Main Content

A system which detects intruders in dark with a low resolution thermal camera connected to a Raspberry Pi Pico using a TensorFlow Lite model

Suppose you are alone at home or out for shopping or on vacations and someone breaks into your house. First thing comes into your mind is: if there is some gadget or home security system which can alert you or your neighbors. The home security camera does a good job but they may not work in complete dark. Also, you do not want your gadget to turn on false alarm if it is a cat. In this project I built a proof of concept which merely turn on an LED when it detects a person in light or dark using just a Raspberry Pi Pico and a thermal camera.

Data collection for training
The first and the most important step in a machine learning project is to collect the training data in such a way that it should cover most of the representative cases for a given task. I have used Seeed Wio Terminal for the data collection. The 3 buttons on the Wio Terminal was used to label the 3 classes (Person, Object, and Background). The captured data is saved to the files on an inbuilt micro SD card on the Wio Terminal. Each thermal image data was captured as a separate file. The file contains no header line, only the comma-separated 768 (24x32) temperature readings. An example file contents looks like as follows.”

Link to article