Notes and key takeaways of the Self-Driving Cars Perception and Deep Learning Free Course from freeCodeCamp.org.

Learn some computer vision core tasks for self-driving cars perception stack using deep learning, including road segmentation, object detection and tracking, and 3D data visualization.

Prerequisites

• ~2 hours
• Free course (No certificate awarded)
• Intermediate level: Python and deep learning (required)

Instructor

• Sakshay Mahna from (Robotics with Sakshay)

Course Objectives

• Gain a comprehensive understanding of the key computer vision tasks involved in self-driving car perception
• Deepen knowledge of deep learning techniques, particularly Convolutional Neural Networks (CNNs), for addressing these tasks
• Learn how to implement and evaluate deep learning models for road segmentation, object detection, tracking, and camera to bird's eye view (BEV) mapping
• Acquire hands-on experience with real-world data and popular deep learning libraries

• 00 - Introduction
• 01 - Road Segmentation | Fully Convolutional Network (FCN)
• 02 - 2D Object Detection | YOLO
• 03 - Object Tracking | Deep SORT
• 04 - 3D Data Visualization | Homogenous Transformations | KITTI
• 05 - Multi Task Learning | Multi Task Attention Network (MTAN)
• 06 - 3D Object Detection | SFA 3D
• 07 - Camera to Bird's Eye View | UNetXST

Read the courses Online, you can visit Perception for Self-Driving Cars Applied Deep Learning.

Chapter	Exercises
1. Road Segmentation - Fully Convolutional Network (FCN)
2. 2D Object Detection - YOLO
3. Object Tracking - Deep SORT
4. 3D Data Visualization - Homogenous Transformations - KITTI
5. Multi Task Learning - Multi Task Attention Network (MTAN)
6. 3D Object Detection - SFA 3D
7. Camera to Bird's Eye View - UNetXST

Happy Learning!

• Feel free to open a PR or an issue if you encounter some problem running the projects.

Here's how you can contribute:

• Fork this repository and clone it to your local machine.
• Create a new branch with a descriptive name for your contribution.
• Add your code and files to the branch and commit your changes.
• Push your branch to your forked repository and create a pull request to the main repository.
• Wait for your pull request to be reviewed and merged.

Full course link:

• freeCodeCamp - Computer Vision and Perception for Self-Driving Cars (Deep Learning Course)
• Class central - (great to follow with split section)

Other related courses:

Zero (Beginner):

• Introduction to Computer Vision - Udacity (Beginner)
• Introduction to Computer Vision for Self-Driving Cars - thinkautonomous
• Computer Vision Kaggle Free Course

Apprentice (Intermediate):

• The Complete Self-Driving Cars course applied Deep Learning - Udemy
• Deep Learning for Autonomous Vehicles - Perception - NVIDIA

Hero (Advanced):

• Advanced Computer Vision with TensorFlow - DeepLearningAI & Class Central
• Visual Perception - Self-Driving Specialization - University of Toronto
• Introduction to Computer Vision (Advanced)
• Udacity Computer Vision Nano Degree Program
  • Udacity Enterprise Syllabus Computer Vision nd891
  • Blog Review: https://www.mltut.com/udacity-computer-vision-nanodegree-review/
• Advanced Computer Vision and Deep Learning - Udacity

"Vision is a picture of the future that produces passion." ~ Bill Hybels