Jetson Nano Starter to Pro - A Computer Vision Course

Jetson Nano Starter to Pro - A Computer Vision Course

by Ritesh Kanjee Augmented AI
Released May 2024
Publisher(s): Packt Publishing
ISBN: 9781836202455

Watch it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Video description

This course begins with a thorough introduction to Jetson, highlighting its advantages over traditional microcontrollers like the Raspberry Pi. You'll learn how to select the right SD card, flash it effectively, and perform initial configurations to set the stage for advanced developments.

As you progress, delve into installing key AI libraries like OpenCV and PyTorch. Understand their roles in crafting robust AI solutions and enhance their performance with CUDA support. The course offers guidance on fundamental computer vision techniques, enabling seamless image operations, color conversions, and edge detections.

Explore object detection with YOLO and its variants through practical examples. Learn to train custom models like number plate recognition and optimize AI models using NVIDIA's TensorRT for enhanced performance. Dive deep into the DeepStream SDK for real-time video analysis and multi-camera synchronization, vital for security and surveillance applications.

Explore advanced topics like pose estimation, vehicle tracking, and face recognition, all with hands-on projects to reinforce learning. By the end, you will have mastered how to use this powerful platform to push the boundaries of what's possible in AI applications, making you a valuable asset in the tech industry.

What you will learn

  • Configure and initialize NVIDIA Jetson platforms
  • Compare Jetson with Raspberry Pi for technological advantages
  • Install and utilize key libraries like OpenCV and PyTorch on Jetson
  • Execute basic to advanced computer vision operations using OpenCV
  • Implement YOLO object detection on custom datasets
  • Integrate multiple camera inputs using RTSP and ONVIF protocols

Audience

This course is ideal for AI researchers, robotics engineers, and software developers who have a basic understanding of AI principles and familiarity with programming concepts. Learners should be comfortable with Python and have an interest in deep learning and computer vision applications.

About the Author

Augmented AI: At Augmented AI, they are pioneers in AI education, providing state-of-the-art courses that integrate technologies such as Generative AI, LLMs (Large Language Models), robotics, drones, and edge AI. They aim to democratize access to these advanced technologies, empowering both individuals and organizations to succeed in the fast-paced AI landscape. They engage over 114K subscribers on YouTube and keep their 43K LinkedIn followers updated on the latest in AI.

Ritesh Kanjee: Ritesh Kanjee, an experienced AI entrepreneur and the Founder and Director of Augmented AI, is renowned for his insightful and engaging educational content, with over 114,000 subscribers on YouTube. His dedication to making AI education accessible, coupled with his expertise, led to his appointment as a board member of the South African AI Association (SAAIA). Ritesh's profound knowledge and commitment to innovation and community-building establish him as a prominent figure in AI education.

Table of contents

  1. Chapter 1 : Introduction to Jetson and Course Overview
    1. Jetson Introduction
    2. Explanation On How To Use It
    3. Course Overview
  2. Chapter 2 : Comparison of Jetson and Its Variants Along with RPi+SD Card Flashing
    1. How Jetson Is Better Than Raspberry Pi
    2. Comparison Among Different Variants
    3. SD Card Flashing
    4. Which Card To Buy
    5. Running Jetson For The First Time
  3. Chapter 3 : Installing Libraries and Setting Up AI Computer - Explain Dependencies and Their Use
    1. Various Libraries and Their Usage e.g., OpenCV, PyTorch, etc.
    2. Installing Supportive Libraries
    3. Installing OpenCV From Scratch With CUDA Support
    4. Installing Other Supportive Libraries
    5. Installing PyTorch and TorchVision
  4. Chapter 4 : Computer Vision OpenCV Basics on Jetson + Pytorch
    1. Perform Some Basic Image Operations Using OpenCV
    2. Import Libraries, Image Read and Display
    3. Color Conversion
    4. Basic Filtration
    5. Transformation
    6. Edge Detection
    7. Morphological Operations
    8. Corner Detection
    9. Basics About PyTorch
    10. Basics About TorchVision
    11. Combining OpenCV and Torch To Perform Basic Image Operations
  5. Chapter 5 : What is Object Detection + Yolo Object Detection
    1. Introduction to Object Detection and How It Is Performed
    2. YOLO Variants
  6. Chapter 6 : YOLO Object Detection on Custom Dataset (Number Plate Dataset)
    1. About The Dataset and Its Annotation for Object Detection
    2. Train The Model On Some Existing Dataset
    3. Perform Object Detection Using Pre-trained Model
  7. Chapter 7 : What is TensorRT? Setting Up Jetson for TensorRT
    1. Brief about TensorRT and Its Benefits
    2. Installing Dependencies and Setting Up Environment for TensorRT
  8. Chapter 8 : Optimizing YOLOX Model for Object Detection Using TensorRT
    1. Converting the YOLOX model to TensorRT
    2. Testing TensorRT (TRT) model
    3. Comparing results
  9. Chapter 9 : What is DeepStream and Theory?
    1. Introduction to DeepStream and how it works?
    2. Use of DeepStream in Different Applications
    3. Setting up environment for DeepStream SDK
    4. Setting up environment for DeepStream SDK
    5. Setting up environment for DeepStream SDK
    6. DeepStream Deep Dive
    7. Testing the DeepStream SDK on Jetson – Part 1
    8. Testing the DeepStream SDK on Jetson – Part 2
    9. Testing the DeepStream SDK on Jetson – Part 3
  10. Chapter 10 : Running DeepStream SDK and Setting up Multiple Cameras
    1. Introduction to RTSP (Real Time Streaming Protocol) and ONVIF
    2. RTSP Structure
    3. Testing RTSP using VLC
    4. Performing Multiple Camera Synchronization Using DeepStream
    5. Performing object detection on Multiple Cameras: Running the Model on the Jetson
    6. Performing object detection on Multiple Cameras: Changes to Config File
    7. Performing object detection on Multiple Cameras: Camera Output
    8. Final Remarks
  11. Chapter 11 : App 1 Car detection + Tracking + Counting
    1. Vehicle Counting Tracking Introduction
    2. Setting up the Implementation: How to Download Files
    3. Implementation Video: Short Version
    4. Implementation Video: Extended Version
    5. Implementation Output
  12. Chapter 12 : Automatic Number Plate Recognition with Paddle OCR
    1. Brief about Roboflow and how to use it
    2. How to annotate data in yolo format on Roboflow?
    3. Brief about Google Colab and Setting Environment for Training Data
    4. How to Train YOLOR on a custom Dataset
    5. Training YOLOR on Google Colab
    6. Training YOLOv7 on Google Colab
    7. Vehicle Number Plate Detection
    8. Vehicle Number Plate Detection Demo: ANPR
  13. Chapter 13 : Pose Estimation Method 1: PoseNet
    1. Introduction to Pose Estimation
    2. Importing properties for PoseNet
    3. Performing PoseNet on Jetson
    4. Demonstration of the Final Result
    5. Darknet
    6. Running Mediapipe
  14. Chapter 14 : Pose Estimation Method 2: PoseNet
    1. Introduction to Pose Estimation
    2. Implementation of PoseNet
  15. Chapter 15 : DeepFake face classification
    1. What is DeepFake?
    2. Implementation of DeepFake Detection
  16. Chapter 16 : Face Recognition and Attendance: Clock in, clock out.
    1. Introduction to Face Recognition and Attendance
    2. Implementation of Face Recognition and Attendance

Product information

  • Title: Jetson Nano Starter to Pro - A Computer Vision Course
  • Author(s): Ritesh Kanjee Augmented AI
  • Release date: May 2024
  • Publisher(s): Packt Publishing
  • ISBN: 9781836202455