Course teacher(s)
Gauthier LAFRUIT (Coordinator)ECTS credits
5
Language(s) of instruction
english
Course content
Typical image processing algorithms (box filtering, windowed filtering, integral images, matrix calculus, etc) will be revisited for parallel implementations in CUDA with thread processing patterns that properly exploit the Graphics Processing Unit’s (GPU) memory and system architecture.
Objectives (and/or specific learning outcomes)
By the end of the course, the student will have implemented 2D image processing algorithms in CUDA, targeting (near) real-time applications. Similarities with OpenCL will be presented.
Teaching methods and learning activities
The course follows a “learn by example” approach.
The exercises will prepare the students to the parallel implementation of a 2D image processing algorithm described in a scientific paper, e.g. depth estimation with stereo matching.
Contribution to the teaching profile
This teaching unit contributes to the following competences:
-
Mastering CUDA parallel programming
-
Parallel threading in 2D image processing
References, bibliography, and recommended reading
John Cheng, Max Grossman, Ty McKercher, "Professional CUDA C Programming", John Wiley & Sons, 2014.
Other information
Contacts
Office ULB-Solbosch L3.119, Tél. 02/650 30 89, Email: gauthier.lafruit@ulb.ac.be
Evaluation
Method(s) of evaluation
- Other
Evaluation: 30% mastering the scientific paper, 70% practical exercises+project.
The evaluation covers a report and an oral presentation.
Mark calculation method (including weighting of intermediary marks)
Evaluation: 30% mastering the scientific paper, 70% practical exercises+project.