EECS 442: Computer Vision (Fall 2019)

This is the tentative schedule.

Date Topic Suggested Reading Slides Assignments/Things Out/Things Due
Wed Sep 4 Introduction & Projective Cameras I S2.1 or (for more) H&Z 2, 6 Intro PDF / Cameras PDF PPTXProjection and Dolly Zoom (Notebook)
Homogeneous coordinates (Notebook)
Mon Sep 9 Projective Cameras II S2.1 or (for more) H&Z 2, 6
Wed Sep 11 Light and Shading S2.2, S2.3 PDF PPTX
Mon Sep 16 Numerical Linear Algebra Part I Zico Kolter Review PDF PPTXHW1 Out
Things Don't Add Up (Notebook)
Distance 3 Ways (Notebook)
Using a Byte (Notebook)
Wed Sep 18 Numerical Linear Algebra Part II
Mon Sep 23 Linear and Nonlinear filtering S3.2 PDF PPTXConvolving Gracefully (Notebook)
Wed Sep 25 Detectors and Descriptors I S4.1 PDF PPTXHarris (Notebook)
Mon Sep 30 Detectors and Descriptors II S4.1 PDF PPTXHW1 Due, HW2 Out
Wed Oct 2 Transformations I S2.1, S6 PDF PPTXGrace in the Middle (Notebook)
Mon Oct 7 Transformations II S2.1, S6 PDF PPTX
Wed Oct 9 Linear Models S14 (skim) for context OR ESL 3.1, 3.2 (skim) and ESL 12.3.2 PDF PPTX
Mon Oct 14 Fall Study Break HW3 Out
Wed Oct 16 Continuous Optimization PDF PPTX HW2 Due Friday Oct 18
Mon Oct 21 Backpropagation and Neural Nets CS231n Backprop Examples
Wed Oct 23 Convnets Part I CS231n Convnets
Mon Oct 28 Convnets Part II CS231n Convnets HW3 Due, HW4 Out
Wed Oct 30 Labeling Pixels Deconvolution artifacts
Mon Nov 4 Detection
Wed Nov 6 Optical Flow S8.4
Mon Nov 11 Tracking and Video Problems S4.14 simple tracking with code HW4 Due, HW5 Out
Wed Nov 13 Calibration and Intro to 3D S6.3 calibration with opencv
Mon Nov 18 Single-View Geometry
Wed Nov 20 Epipolar Geometry S11.1
Mon Nov 25 Stereo S11 HW5 Due, HW6 Out
Wed Nov 27 Thanksgiving (by 30 minutes!)
Mon Dec 2 Structure from Motion S7
Wed Dec 4 Advanced applications: Learning and Geometry
Mon Dec 9 Advanced applications: embodiment HW6 Due
Wed Dec 11 Advanced applications: language

Congratulations and thanks to the following who found bugs/typos: Edric Guo, Kyle Marieb, Katie Lee

Re-use policy: I am extremely grateful to the many researchers who have made their slides and course materials available. Please feel to re-use any of my materials while crediting appropriately and making sure original attributions to these generous researchers is preserved.

S is Computer Vision: Algorithms and Applications by Richard Szeliski, which can be found here.

H&Z is Multiple View Geometry in Computer Vision by Richard Hartley and Andrew Zisserman, which can be obtained via the library in electronic form (scroll past the physical copies).

ESL is Elements of Statistical Learning by Hastie, Tibshirani, and Friedman, which can be found here