Chapter 2. Alarm System
Chapter 3. Gas Leak Alarm
Chapter 4. Weather Station
Chapter 5. Digital Image Processing
Chapter 6. Animations With Python And Pygame
Chapter 7. Homemade Spectrometer
Chapter 6. Object Classification Using Edge Impulse
Summary:
"This book is a collection of my best publications on projects made with the Raspberry Pi board, and which I describe below:Alarm System: Develop an alarm system to detect the movement of someone through the use of a PIR motion sensor and the Raspberry Pi Zero W board. When this happens, an alert notice will appear on the Twitter account.
Gas Leak Alarm: Develop a system for the detection of fires or gas leaks with the Raspberry Pi Zero W board and the MQ2 gas sensor. This system can send the captured data to the remote server of ThingSpeak. When a gas increase is detected beyond a limit, then a message is sent to the Twitter account.
Weather Station: Develop a Weather Station with a Raspberry Pi Zero W board, and monitor all the sensors with ThingSpeak and Twitter. The sensors used are DHT11 (humidity and temperature sensor) and BMP085 (barometric pressure and temperature sensor). Also, you can use new versions of this sensors without any problem.
Digital Image Processing: Make use of digital image processing with OpenCV on a Raspberry Pi 3. To achieve this goal, start from the software installation to make your own object classifiers and finally make an example to manipulate an object by means of an image in movement. This has many applications, ranging from recognizing people or objects, to creating your own video surveillance system.
Animations With Python And Pygame: The main goal of this project is to develop virtual animations of a human, animals and objects that are moved on a stage or image background. We will use Python and Pygame, these software tools are used to program games."
Homemade Spectrometer: Kit made with the AS7262 (six colors) and AS7263 (near infrared) spectral sensors and the Raspberry Pi board. I have divided this project into three parts. The first section was done with the AS7262 six-color spectral sensor and the experiments were the construction of a filter spectrometer, and sensing colored solutions. The second section was made with the AS7263 NIR (near infrared) spectral sensor to assess plant foliage health, so it explains how to use the sensor's channel readings and the standard Normalized Difference Vegetation Index (NDVI) equation to calculate an estimated NDVI value, which is used to determines as “HEALTHY” or “UNHEALTHY” leaf.
Object Classification Using Edge Impulse: Here we use Edge Impulse Studio, which is a machine learning platform that enables developers to generate Machine Learning trained models in the cloud and deploy them on single-board computer like the Raspberry Pi.
The links of this Ebook are: