پروژه‌های سنسور با رزبری پای: اینترنت اشیا و پردازش تصویر دیجیتال (سری نوآوری‌های سازنده)

Use Python to develop Rasperry Pi projects to solve common digital image processing and IoT problems. Using a free IoT server you’ll tackle fundamental topics and concepts behind theses two areas. This second edition includes new content on Artificial Intelligence and updated sensor guidance to help you better explore virtual animations, create a homemade spectrometer, and master object classification with Edge Impulse. Start by creating a system to detect movement with a PIR motion sensor and a Raspberry Pi board. Use the MQ2 gas sensor and a Raspberry Pi board as a gas leak alarm system to detect dangerous explosive and fire hazards. Then train your system to send the captured data to the remote server ThingSpeak. You’ll also develop a weather station with your Raspberry Pi. Using the DHT11 (humidity and temperature sensor) and BMP (barometric pressure and temperature sensor) in conjunction with ThingSpeak and X, you can receive real time weather alerts from your own meterological system! Spectral sensers used with the Raspberry Pi include the AS7262 (six colors), and AS7263 (near infrared) for the construction of a filter spectrometer, sensing colored solutions, and assessing plant foliage health. Finally, expand your skills into the popular machine learning world of digital image processing using OpenCV and a Pi. Make your own object classifiers and finally manipulate an object by means of an image in movement. This skillset has many applications, ranging from recognizing people or objects, to creating your own video surveillance system. With the skills gained from Sensor Projects with Raspberry Pi , you'll be well-equipped to explore other applications in mobile development and electrical engineering as well. What You'll Learn Work with ThingSpeak to receive X alerts from your systems. Cultivate skills in processing sensor inputs that are applicable to mobile and machine learning projects. Incorporate sensors into projects to make interactive devices. Experiment with virtual scenarios and objects. Create Python and Pygame games that contain virtual scenarios and animations. Detect colored solutions and assess the plant foliage health. Who This Book Is For Hobbyists and makers working with robotics and IoT. Electronic engineers and programmers who would like to expand their familiarity with basic sensor projects. Table of Contents About the Author Acknowledgments Introduction Chapter 1: Theoretical Fundamentals Programming with the Raspberry Pi Elements of the Language Variables and Constants Variables Constants Types of Data Arithmetic Operators Comments Complex Data Types Tuples Lists Dictionaries Flow Control Structures Indentation Encoding Multiple Assignments Conditional Flow Control Structures Iterative Control Structures while Loop for Loop Important Differences Between Python 2.7.x and Python 3.x print Function Python 3.x Output Division Operator Python 3.x Output Unicode Python 3.x xrange Output in Python 3.x __future__ module Output Internet of Things History Smart Home Applications Elder-Care Applications Medical and Healthcare Applications Transportation Applications Building and Home Automation Applications Manufacturing Applications Agriculture Applications Metropolitan-Scale Deployments Energy Management Applications Environmental Monitoring Applications Living Lab Application IoT Security What’s the Difference Between OT and the IoT? Digital Image Processing History Tasks Classification Feature Extraction Multiscale Signal Analysis Pattern Recognition Projection Techniques Image Editing Image Restoration Neural Networks Filtering Convolution Applications Digital Camera Images Film Artificial Intelligence Turing Test Dartmouth Conference Perceptron Birth of AI Deep Learning Revolution Computer Vision Machine Learning Computational Artificial Intelligence Edge Impulse Why TensorFlow and Edge Impulse? TensorFlow vs. TensorFlow Lite Summary Chapter 2: Alarm System Hardware Software Procedure Creating a Project in ThingSpeak Using Your Twitter/X Account in ThingSpeak Sending an Alert to Your Twitter/X Account Challenges Conclusion Chapter 3: Gas Leak Alarm Hardware Software To use the tools of the IoT service provider, you must follow the guidelines indicated. Installing the ADS1115 Sensor Library Enabling the 12C Interface Creating a Project in ThingSpeak Using Your Twitter/X Account in ThingSpeak Sending an Alert to Your Twitter/X Account Challenges Conclusion Chapter 4: Weather Station Hardware Software Library Installation Installing the DHT11 Sensor Library Installing the BMP085 Sensor Library Enabling the 12C Interface Creating a Project in ThingSpeak Using Your Twitter/X Account in ThingSpeak Sending an Alert to Your Twitter/X Account Challenges Conclusion Chapter 5: Digital Image Processing with Python and OpenCV Installing the Software Step 1: Installing Python 2.7 and 3 Step 2: Installing the Dependencies Step 3: Getting the Latest OpenCV Source Code Step 4: Installing pip and virtualenv Step 5: Creating a Virtual Environment Step 6: Installing Numpy and Scipy Step 7: Installing OpenCV Step 8: Testing the OpenCV Installation Classifiers Step 1: Collecting Images for a Database Step 2: Arranging the Negative Images Step 3: Cropping and Marking the Positive Images Step 4: Creating a Vector of Positive Images Step 5: Haar Training Step 6: Creating the XML File Testing with Images Testing with Videos Moving a Robot Arm Challenges Conclusion Chapter 6: Animations with Python and Pygame Animated UFO Animated Dog Animated Man Challenges Conclusion Chapter 7: Homemade Spectrometer Optic Basics Spectrophotometry Basics SparkFun Qwiic pHAT v2.0 AS7262 Six-Channel Visible Light Sensor Configuring the Raspberry Pi Building a Filter Spectrometer Schematic Library Installation Spectrum Bar Graph Data Captured Conclusion Sensing Colored Solutions Device Assembly Schematic Programming Challenges Conclusion Plant Foliage Health AS7263 NIR Sensor Schematic Diagram Code Test Conclusion Chapter 8: Object Classification Using Edge Impulse on Raspberry Pi Using Edge Impulse Creating the Dataset Training the Model Deploying the Trained Model to Raspberry Pi Conclusion Index