Course Summary
This course teaches visual perception techniques used in self-driving cars. You'll learn how to analyze camera images and lidar data to make driving decisions.Key Learning Points
- Understand the fundamentals of visual perception and how it's used in self-driving cars
- Learn how to analyze camera images and lidar data
- Gain practical experience working with real-world data
Related Topics for further study
Learning Outcomes
- Analyze camera images and lidar data for driving decisions
- Understand the fundamentals of visual perception in self-driving cars
- Gain practical experience working with real-world data
Prerequisites or good to have knowledge before taking this course
- Basic knowledge of Python
- Familiarity with machine learning concepts
Course Difficulty Level
IntermediateCourse Format
- Online
- Self-paced
Similar Courses
- Self-Driving Cars: Advanced Topics
- Computer Vision Basics
Related Education Paths
Notable People in This Field
- Elon Musk
- Andrew Ng
Related Books
Description
Welcome to Visual Perception for Self-Driving Cars, the third course in University of Toronto’s Self-Driving Cars Specialization.
Knowledge
- Work with the pinhole camera model, and perform intrinsic and extrinsic camera calibration
- Detect, describe and match image features and design your own convolutional neural networks
- Apply these methods to visual odometry, object detection and tracking
- Apply semantic segmentation for drivable surface estimation
Outline
- Welcome to Course 3: Visual Perception for Self-Driving Cars
- Welcome to the Self-Driving Cars Specialization!
- Welcome to the course
- Meet the Instructor, Steven Waslander
- Meet the Instructor, Jonathan Kelly
- Course Prerequisites
- How to Use Discussion Forums
- How to Use Supplementary Readings in This Course
- Recommended Textbooks
- Module 1: Basics of 3D Computer Vision
- Lesson 1 Part 1: The Camera Sensor
- Lesson 1 Part 2: Camera Projective Geometry
- Lesson 2: Camera Calibration
- Lesson 3 Part 1: Visual Depth Perception - Stereopsis
- Lesson 3 Part 2: Visual Depth Perception - Computing the Disparity
- Lesson 4: Image Filtering
- Supplementary Reading: The Camera Sensor
- Supplementary Reading: Camera Calibration
- Supplementary Reading: Visual Depth Perception
- Supplementary Reading: Image Filtering
- Module 1 Graded Quiz
- Module 2: Visual Features - Detection, Description and Matching
- Lesson 1: Introduction to Image features and Feature Detectors
- Lesson 2: Feature Descriptors
- Lesson 3 Part 1: Feature Matching
- Lesson 3 Part 2: Feature Matching: Handling Ambiguity in Matching
- Lesson 4: Outlier Rejection
- Lesson 5: Visual Odometry
- Supplementary Reading: Feature Detectors and Descriptors
- Supplementary Reading: Feature Matching
- Supplementary Reading: Feature Matching
- Supplementary Reading: Outlier Rejection
- Supplementary Reading: Visual Odometry
- Module 3: Feedforward Neural Networks
- Lesson 1: Feed Forward Neural Networks
- Lesson 2: Output Layers and Loss Functions
- Lesson 3: Neural Network Training with Gradient Descent
- Lesson 4: Data Splits and Neural Network Performance Evaluation
- Lesson 5: Neural Network Regularization
- Lesson 6: Convolutional Neural Networks
- Supplementary Reading: Feed-Forward Neural Networks
- Supplementary Reading: Output Layers and Loss Functions
- Supplementary Reading: Neural Network Training with Gradient Descent
- Supplementary Reading: Data Splits and Neural Network Performance Evaluation
- Supplementary Reading: Neural Network Regularization
- Supplementary Reading: Convolutional Neural Networks
- Feed-Forward Neural Networks
- Module 4: 2D Object Detection
- Lesson 1: The Object Detection Problem
- Lesson 2: 2D Object detection with Convolutional Neural Networks
- Lesson 3: Training vs. Inference
- Lesson 4: Using 2D Object Detectors for Self-Driving Cars
- Supplementary Reading: The Object Detection Problem
- Supplementary Reading: 2D Object detection with Convolutional Neural Networks
- Supplementary Reading: Training vs. Inference
- Supplementary Reading: Using 2D Object Detectors for Self-Driving Cars
- Object Detection For Self-Driving Cars
- Module 5: Semantic Segmentation
- Lesson 1: The Semantic Segmentation Problem
- Lesson 2: ConvNets for Semantic Segmentation
- Lesson 3: Semantic Segmentation for Road Scene Understanding
- Supplementary Reading: The Semantic Segmentation Problem
- Supplementary Reading: ConvNets for Semantic Segmentation
- Supplementary Reading: Semantic Segmentation for Road Scene Understanding
- Semantic Segmentation For Self-Driving Cars
- Module 6: Putting it together - Perception of dynamic objects in the drivable region
- Project Overview: Using CARLA for object detection and segmentation
- Final Project Hints
- Final Project Solution [LOCKED]
- Congratulations for completing the course!
Summary of User Reviews
Check out what users are saying about the Visual Perception for Self-Driving Cars course on Coursera. Many users found the course to be comprehensive and informative.Key Aspect Users Liked About This Course
Comprehensive and informativePros from User Reviews
- Course content is well-structured and easy to follow
- Instructors are knowledgeable and provide clear explanations
- Hands-on assignments and quizzes help to reinforce understanding
Cons from User Reviews
- Some users found the course too technical and difficult to understand
- Limited interaction with instructors and other students
- Course may not be suitable for beginners with no prior knowledge in computer vision or machine learning
Steven Waslander
4.7 Raiting
Simple image classification using KNN
- 4.1
-
![]()
![]()
![]()
![]()
![]()
Learn how to classify images using KNN algorithm Learn intuition behind image classification with machine learning Build a strong foundation in image classification with this tutorial....
R: Neural Nets and CNN Architecture in R - Masterclass!
- 3.6
-
![]()
![]()
![]()
![]()
![]()
One stop guide to implement cutting-edge CNN architectures and build Neural Network models to solve complex problems! You’ll also apply supervised and unsupervised learning to your daily projects....
Multi-Object Tracking for Automotive Systems
- 0.0
-
![]()
![]()
![]()
![]()
![]()
Learn how to localize and track dynamic objects with a range of applications including autonomous vehicles g. , biological cells, sports athletes or space debris....
Machine Learning
- 4.9
-
![]()
![]()
![]()
![]()
![]()
Machine learning is the science of getting computers to act without being explicitly programmed. Many researchers also think it is the best way to make progress towards human-level AI....
