|Period:||period 3 (week 6 through 15, i.e., 3-2-2020 through 9-4-2020; retake week 27)
|Participants:||up till now 63 subscriptions|
|Schedule:||Official schedule representation can be found in Osiris|
|Contents:||The goal of computer vision is to allow computers to recognize and understand the world through visual information such as images and videos.
In this course, you will learn how cameras capture the 3D world, how to combine different views to reconstruct the world in 3D, how images can be described and how we can train algorithms to recognize what's depicted in images and videos. The course is centered around two main themes:
- Multi-view reconstruction: construct a 3D object from multiple views
- Classification with CNNs: classify videos with human actions using CNNs
|Literature:||Richard Szeliski, "Computer Vision: Algorithms and Applications", 2010 (download here for free). You can also order a paper copy from SV Sticky.|
|Course form:||The course combines theory (lectures, tested during exam) and practice (assignments). The assignments are an important part of the course and final grade. Programming skills in C++ are required. For the second part, we will be using Python, but will provide sufficient materials and support.|
|Exam form:||The final grade is average of the following assessments:
The minimum final grade to pass the course is 5.5. Assignments and final exam should each be completed with a minimum of grade 4.
- Assignments [50%]
- Final exam [50%]
|Minimum effort to qualify for 2nd chance exam:||To take part in the re-take exam, your original grade should be at least grade 4. There is no re-take for the assignments.|
|Description:||Please contact Ronald Poppe for more information about the course.|