Syllabus

There is some redundancy in the course material: The Videos below were recorded during the COVID pandemic, and correspond to topics and coverage only approximately.

In-person lectures are recorded on Panopto.

The notes below (n_01, ...) are the official reference material for the course.

The slides used in class are similar but not identical to those used in the topic videos. They are provided only for convenience below. They are not required reading. Slides should not be used as your main study materials as they are merely lecture props. They are not meant to convey concepts or material by themselves, and are not self-explanatory.

There will be approximately five homework assignments in addition to Homework 0, which is on prerequisites. Assignments will be posted on the homework page.

Topic Notes Slides Videos HW Due
0 Course Content and Logistics s_0 Jan 19
1 Correlation, Convolution, Filtering n_01 s_01 v_01
2 Image Differentiation and Pyramids n_02 s_02 v_02
3 Numerical Function Optimization n_03 s_03 v_03
4 Deep Learning Basics n_04 s_04 v_04
5 Backprop, Networks for Recognition n_05 s_05 v_05
6 Linear Algebra Refresher n_06 s_06 v_06
7 Image Motion and Window Tracking n_07 s_07 v_07
March 9: Midterm Exam on topics 1-5 (not 6 or 7)
8 Networks for Flow and Segmentation n_08 s_08 v_08
9 Rigid Transformations, Pinhole Camera n_09 s_09 v_09
10 Epipolar Geometry, 8-Point Algorithm n_10 s_10 v_10
11 Real Cameras and their Calibration n_11 s_11 v_11
12 Closing Thoughts s_12

COMPSCI 527, Duke University, Site based on the fluid 960 grid system