Chevron Left
返回到 Visual Perception for Self-Driving Cars

学生对 多伦多大学 提供的 Visual Perception for Self-Driving Cars 的评价和反馈

509 个评分
72 条评论


Welcome to Visual Perception for Self-Driving Cars, the third course in University of Toronto’s Self-Driving Cars Specialization. This course will introduce you to the main perception tasks in autonomous driving, static and dynamic object detection, and will survey common computer vision methods for robotic perception. By the end of this course, you will be able to work with the pinhole camera model, perform intrinsic and extrinsic camera calibration, detect, describe and match image features and design your own convolutional neural networks. You'll apply these methods to visual odometry, object detection and tracking, and semantic segmentation for drivable surface estimation. These techniques represent the main building blocks of the perception system for self-driving cars. For the final project in this course, you will develop algorithms that identify bounding boxes for objects in the scene, and define the boundaries of the drivable surface. You'll work with synthetic and real image data, and evaluate your performance on a realistic dataset. This is an advanced course, intended for learners with a background in computer vision and deep learning. To succeed in this course, you should have programming experience in Python 3.0, and familiarity with Linear Algebra (matrices, vectors, matrix multiplication, rank, Eigenvalues and vectors and inverses)....



Feb 27, 2020

The course has proved to another milestone in furthering my understanding of robotics, computer vision, machine learning and autonomous driving vehicles.


Nov 7, 2020

Really really great course. I would like to work with Prof.Waslander at any project. I will advise this course to anyone interested. Thanks Coursera!


51 - Visual Perception for Self-Driving Cars 的 72 个评论(共 72 个)

创建者 Matías F

Jan 18, 2021


创建者 Jeff D

Nov 28, 2020


创建者 Chongyu Z

Oct 18, 2020


创建者 Sruti B

Sep 2, 2019


创建者 Soumyajit M

Oct 7, 2020


创建者 Md. R Q S

Aug 21, 2020


创建者 Balasubramanyam P

May 9, 2020


创建者 Kosinski K

May 25, 2020

Thanks to this course I have gained a lot of knowledge related to visual perception. However, in contrary to 2 previous Self-Driving Cars courses, it has 2 main drawbacks which I cannot omit while writing the review:

1) Bad quality of PDFs - overlaping texts and graphics. Watching videos was sometimes the only way to quickly recall a content of presentation.

2) Poor preparation in the presentations for the project from week 2 combined with incomplete online documentation of OpemCV functions made this task pretty tedious and annoying. Moreover, a ridiculous limit of 3 submits per 8h for the mentioned task, which requires multiple parameters modifications.

创建者 Subramanya B

Dec 2, 2021

This course was the heaviest in terms of content taught. It was a fun experience nevertheless. Seeing colorful, correct outputs always cheers me up and so it did here as well:)

But a small glitch in the YAML output file format took up a little too much time at the end. Would really appreciate the course coordinators looking into this matter and making necessary amends as soon as possible.


创建者 Yogesh C

Apr 1, 2020

The overall course content, the video lectures and the quizzes are great but I feel that the programming assignment can have more clarifications. Finally, I also want to mention that I liked the instructors encouraging numerous other algorithms and approaches to solve the same problem. That way we can have a much clearer understanding of the pros and cons of them over one another.

创建者 Marco

Jul 31, 2020

Please make sure the syntax is consistent. One thing I remember was a c_u instead of u_c. I feel sometimes that the explanation in the assignments can be more specific as it is otherwise a lot of guessing or extra learning.

创建者 Eric J

Dec 14, 2021

Liked the overarching themes and overall content of the course. Tuning the various OpenCV algorithms was unintuitive and not discussed in the course. Discussion forums are your friend.

创建者 Sen Y

Jan 12, 2020

I feel disappointed. Programming assignments are neither for 2D object detection nor for semantic segmentation.

创建者 Levente K

Mar 25, 2019

Good intro for those with not much experience w/ image processing/computer vision w.r.t. autonomous driving.


Sep 23, 2021

The final assignment in this course is at least well designed compared to previous courses.

创建者 OMKAR K 1

Jun 30, 2020

The range of topics was good but it would have been better if they were explained more.

创建者 Yan X

Dec 23, 2020

The content is good, project can be more complicated. One thing I have to complain is the course is lacking support. Specially the common problems about course content and technical issues are long waiting for answers. This will make learners feel really frustrated.

创建者 Metehan S

Jun 20, 2021

If you are not already familiar with NN, ML areas and image processing , just by watching videos ,it will be hard to pass this course. For a person who doesn't have enough time to search and understand deeply , this course will be difficult !

创建者 Kiavash F

Aug 26, 2021

By all due respect to the lecturers and (if any) teaching assistants, this course really was awful for the following reasons:

First of all, this course is not at all an advanced course. This course is merely an introduction to vision for self-driving cars and does not discuss the related topics in depth.

Second, given the fact that I have had some experience with neural networks, I sometimes could not agree with the solutions provided for the quizzes throughout the course. Even though I sent messages and tried to discuss my viewpoints, I received no response from lecturers or any teaching assistance.

Thirds, there were in, my opinion, some errors in the lecture slides, and again even though I sent messages to ask if I am mistaking or if the slides contain typos and errors I received no response.

Lastly, it is quite disturbing that even though this course has been available for years, no one made an effort to update some parts of the script (for programming assignments) which are erroneous (this was the last straw that broke the camel's back).

I really am disappointed in this course, and if I knew this course was going to be like this, I would have never chosen it.

Thank you for reading my comment.

All the best

创建者 Kasra D

May 13, 2021

This course is good for you if you already know the concepts and just want to review it. It's a terrible course if you don't know the concepts and want to learn from it. This is true for all courses in this specialization.

创建者 Mathew S

Apr 25, 2022

T​he course was fine till the where for the final assignment, it kept returning a compile error when submitting the solution. There were several students struggling with the issue going back 6 months to a year.

创建者 Vishwaswaroop B

Dec 30, 2021

Just annoying theory bits, with no practical coding examples