Periods
(31-Aug-2015
– 18-Oct-2015)
(19-Oct-2015
– 20-Dec-2015)
(11-Jan-2016
– 6-Mar-2016)
(7-Mar-2016
– 29-May-2016)
Teaching schedule for Master's Degree Programme in Computational Big Data Analytics. Schedule for General studies is published here.
See the Curricula for requirements of General, Advanced and Other and Optional Studies. List of responsible teachers, see Degree Programmes page.
Correspondence between old and new courses, statistics curricula 2012-2015 compared to CBDA curricula 2015-2018, can be found in separate document (finnish only).
See the course information for instructions on course registration. If a student has registered for a course but will not be taking it, he/she must cancel his/her registration. If a student does not participate in the course and does not cancel his/her enrolment by the time set by the teacher, or if he/she discontinues the course, he/she will be assigned a fail grade for the course in question.
Please fill in the form before the first seminar session.
Enroll before the first lecture.
Modes of study
- Lectures
- Exercises (independent work)
- Exam
Please fill in the form before the first lecture. After this contact the lecturer.
Please fill in the form before the first seminar session.
Modes of study
- Lectures
- Exercises (independent work)
- Exam
Please fill in the form before the first lecture. After this contact the lecturer.
Enroll before the first lecture.
A short hands-on course about the basic results and methodology of 3D computer vision, focusing on geometric results and optimization, and their practical applications in, for example, augmented reality, motion capture, robotics, and vision-based interaction techniques.
Content:
Projective geometry: homogeneous coordinates, perspective projection, single view geometry, absolute pose problem (DLT & P3P), camera calibration, two view geometry, relative pose problem, triangulation. (4+4h)
Estimation: Feature detection & matching, random sample consensus, Levenberg-Marquardt optimization, automatic differentiation, large-scale sparse optimization (bundle adjustment), 3D reconstruction from multiple views or video. (4+4h)
Dense 3D: Dense stereo, depth cameras (e.g. Kinect), point clouds, iterative closest point algorithm. (2+2h)
Applications & open source libraries for computer vision (exercises & project)
This course can be included on the modules
- Advanced Courses in Methods of Computational Data-Analytics
- Tietojenkäsittelyopin syventävät opinnot
- Optional studies
Prerequisites:
The course focuses on solving practical problems rather than on theory. Basics of programming (C++, Python, or Octave/Matlab), linear algebra (working with small matrices e.g. in computer graphics), calculus (derivatives), and probability (counting combinations, normal distribution) suffice.
Language of Instruction:
Lectures in Finnish or English depending on enrolled students. The course material is in English.
Please fill in the form before the first seminar session.
Please fill in the form before the first seminar session.