Visual Perception for Self-Driving Cars
Start a new career with Visual Perception for Self-Driving Cars course offered by the University of Toronto.
Expert
Online
7 Weeks
13,514 INR Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study | Video and Text Based |
Course Overview
The Visual Perception for Self-Driving Cars certification course will introduce candidates to the key perception tasks and survey popular computer vision methods for robotic perception in autonomous driving, and dynamic and static object detection. Candidates will acquire the skills to work with the pinhole camera model by the end of this course. Along with them they will detect, explain and fit image characteristics, conduct intrinsic and extrinsic calibration of the camera and build their own convolutional neural networks. For drivable surfaces, estimation candidates can apply these methods to object detection and tracking, visual odometry, and semantic segmentation.
Candidates will build algorithms for the final project in the Visual Perception for Self-Driving Cars training course that defines the limits of the drivable surface and recognise bounding boxes for objects in the scene. On a realistic dataset, students learn to work using synthetic as well as real image data.
The Visual Perception for Self-Driving Cars online course is part of a self-driving car specialisation programme. It is the third one of a total 4 courses. This specialisation gives a detailed understanding of state-of-the-art engineering approaches used in the self-driving automotive industry.
The Highlights
- Advanced level course
- 3rd course of self-driving car specialisation
- Learn with own schedule
- Flexible deadlines
- Approximately 31 hours to finish
- Certification by Coursera
- Offered by University of Toronto
Programme Offerings
- online
- Quiz
- Assignment
- Practice Exercises
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | University of Toronto, TorontoCoursera |
Visual Perception for Self-Driving Cars Fee Structure :
Description | Amount |
1 month, 20+ hours per week | Rs. 6,757 |
3 months, 11 hours a week | Rs. 13,514 |
6 months, 5 hours a week | Rs. 20,271 |
Eligibility Criteria
Education
Candidates should have basic knowledge of deep learning, computer vision, linear algebra, and Python 3.0
Certification Qualifying Details
Certification will be done only after the successful completion of the Visual Perception for Self-Driving Cars certification by Coursera. To get full access to the programme and to get a certificate of completion candidates should subscribe to it by paying the required fee.
What you will learn
After the completion of the Visual Perception for Self-Driving Cars certification syllabus, candidates will learn these:
- Candidates will be working with models of pinhole cameras and performing intrinsic as well as extrinsic camera calibration. Candidates will detect, explain and fit image characteristics, conduct intrinsic and extrinsic calibration of the camera and build their own convolutional neural networks. And they will learn the skills to apply these methods to object detection and tracking, visual odometry and semantic segmentation for drivable surface estimation.
- Using the open source simulator ‘CARLA’ candidates can get to communicate with actual data sets from an autonomous vehicle (AV)through hands-on projects.
- Candidates can hear from industry experts working at companies such as Oxbotica and Zoox during their courses as they share insights into autonomous technology and how it fuels job growth in the field.
- Candidates can benefit from a highly realistic driving experience that features 3D modelling and environmental conditions for pedestrians.
- They will be able to create their own self-driving software stack and apply for jobs in the autonomous vehicle industry.
Who it is for
Admission Details
Candidates applying for the Visual Perception for Self-Driving Cars classes, follow these steps:
Step 1: Visit the website.
https://www.coursera.org/learn/visual-perception-self-driving-cars
Step 2: Click on “Enrol For Free”.
Step 3: Candidates will be requested to sign up or log in. Do sign up or log in with your Google/ Facebook/ Apple account.
Step 4: Candidates can audit the course for free or subscribe to the whole specialisation for getting a certificate. Select the option accordingly.
Step 5: Candidates will get a 7-day free trial. Payment has to be done only after 7 days. You can cancel the free trial anytime you want. No penalties will be charged.
The Syllabus
Videos
- Welcome to the Self-Driving Cars Specialization!
- Welcome to the course
- Meet the Instructor, Steven Waslander
- Meet the Instructor, Jonathan Kelly
Readings
- Course Prerequisites
- How to Use Discussion Forums
- How to Use Supplementary Readings in This Course
- Recommended Textbooks
Discussion Prompt
- Get to Know Your Classmates
Videos
- 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
Readings
- Supplementary Reading: The Camera Sensor
- Supplementary Reading: Camera Calibration
- Supplementary Reading: Visual Depth Perception
- Supplementary Reading: Image Filtering
Assignment
Module 1 Graded Quiz
Programming Assignment
- (Submission) Applying Stereo Depth to a Driving Scenario
Ungraded Labs
- Practice Assignment: Applying Stereo Depth to a Driving Scenario
- (Solution) Applying Stereo Depth to a Driving Scenario
Videos
- 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
Readings
- Supplementary Reading: Feature Detectors and Descriptors
- Supplementary Reading: Feature Matching
- Supplementary Reading: Feature Matching
- Supplementary Reading: Outlier Rejection
- Supplementary Reading: Visual Odometry
Programming Assignment
- Visual Odometry for Localization in Autonomous Driving
Ungraded Lab
- Visual Odometry for Localization in Autonomous Driving
Videos
- 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 Regularizatio
- Lesson 6: Convolutional Neural Networks
Readings
- 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
Assignment
Feed-Forward Neural Networks
Videos
- Lesson 1: The Object Detection Problem
- Lesson 2: 2D Object detection with Convolutional Neural Networks
- Lesson 3: Training vs. InferenceLesson 4
- Lesson 4: Using 2D Object Detectors for Self-Driving Cars
Readings
- 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
Assignment
Object Detection For Self-Driving Cars
Videos
- Lesson 1: The Semantic Segmentation Problem
- Lesson 2: ConvNets for Semantic Segmentation
- Lesson 3: Semantic Segmentation for Road Scene Understanding
Readings
- Supplementary Reading: The Semantic Segmentation Problem
- Supplementary Reading: ConvNets for Semantic Segmentation
- Supplementary Reading: Semantic Segmentation for Road Scene Understanding
Assignment
Semantic Segmentation For Self-Driving Cars
Videos
- Project Overview: Using CARLA for object detection and segmentation5m
- Final Project Hints6m
- Final Project Solution [LOCKED]
- Congratulations for completing the course!
Programming Assignment
- Environment Perception For Self-Driving Cars
Discussion Prompt
- Your Learning Journey
Ungraded Lab
- Environment Perception For Self-Driving Cars
Instructors
University of Toronto, Toronto Frequently Asked Questions (FAQ's)
This course doesn’t come with university credit. Certification is done by Coursera itself.
Candidates opting for a subscription plan have unlimited access to the course. They will get access to all contents including assignments and will get a certificate after the completion.
A free audit option is available. Candidates will have access to all the course contents. Contents like assignments are not included in it. There will not be certification after completion also.
Access will be enabled after the enrolment and it will vary according to the way of enrolment. Only subscribed candidates will gamer access to all the contents.
Coursera provides financial aid. If candidates can’t afford the fee, do apply for availing financial aid. It will take 15 days at least to complete the review process.