Chevron Left
Retour à Visual Perception for Self-Driving Cars

Avis et commentaires pour d'étudiants pour Visual Perception for Self-Driving Cars par Université de Toronto

4.7
étoiles
431 évaluations
58 avis

À propos du cours

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)....

Meilleurs avis

AQ
27 févr. 2020

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

BS
7 nov. 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!

Filtrer par :

51 - 57 sur 57 Avis pour Visual Perception for Self-Driving Cars

par Kosinski K

25 mai 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.

par Yogesh C

1 avr. 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.

par Marco

31 juil. 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.

par Sen Y

12 janv. 2020

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

par Levente K

25 mars 2019

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

par Omkar K

30 juin 2020

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

par Yan X

23 déc. 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.