Computer Vision in 3D
Examiner
and lecturer:
Litterature:
[1] J. Bigun, "Vision with direction", Springer, (2006).
[2]
optical_flow_lk_dfd_lip_motion.ppt, [3] Laboratory exercises in
Matlab:
Optical Flow by DFD and Correlation, [4] A pdf file link to FAQ of the "report on research in Computer Vision in 3D"
(to be given). [5]
Extra (Optional): Example slides (link) on how different concepts of
the course contents are taught
elsewhere. Course Contents: Fundamentals of Computer Vision in 3D (4.5hp credits): This part consists in two
concepts, theory and labs (also called practice). Theory and practice
are examined in writing resulting in a grade for two concepts (comprising both). There is no split of the total 4.5hp credits
between theory and practice. Theory supports your learning in terms of understanding of tools necessary
to construct computational methods. Practice is meant to give skills illustrating the
theory. Evidently, not every detail of theory is possible to illustrate
via labs. Likewise, not every detail of practice is explained in
terms of theory, as some practice contents are expected to be supported by
your prior knowledge, e.g. basic programming skills and implementation
of basic math theory in programs. Below is the summary of theory and
how this relates to practice as well as sections of the course book.
Scientific report
Slides presenting Ch. 12 of ([1]). They comprise optical flow by:
3D Structure Tensor, Differentials, (Lucas & Kanade, using inverse
of 2D Structure Tensor) Ch. 12.9 (of [1]), Displaced Frames (using
Block-Matching, Correlation on gray images) Ch. 12.10, with
Application to biometric identification by lip motion (Faraj & Bigun, 2007 )
Optical Flow LK,
Calibration,
Depth by Stereo,
Epipolar Geometry.
https://web.stanford.edu/class/cs231m/lectures/lecture-7-optical-flow.pdf
Motion analysis (Ch. 12)
Brightness constancy, real motion,
perceived motion, Optical flow (Ch. 12.12, 12.4, 12.6
LAB 1 & LAB 2)
Correlation based methods (Ch.
12.10 LAB 1)
Gradient (2D) based methods (Ch.
12.9 LAB 2)
3-D reconstruction (Ch. 13)
Geometry, World basis, Camera basis,
Basis changes for reconstruction (Ch. 13.1, 13.2, 13.3 & LAB 3)
Geometry and Stereo cameras,
Reconstruction by stereo (Ch. 13.4, 13.8 &
LAB 4)
Epipolar Geometry:
Facilitation of searches for correspondence
(Ch. 13.5, 13.6, 13.8 &
LAB 5)
Laboratory exercises material (se Litterature above) contain normally a pdf document, images and matlab code which can be incomplete or complete. The pdf document will guide you through the lab duties and ask for explanations, or completitions of matlab codes when they are not. Questions in pdf documets ARE NOT THE SAME, as the questions in examination.