Syllabus
This course is based on notes and articles from the literature. Additional materials will be posted below as appropriate.
This syllabus is a plan, not a commitment. Depending on class interest and the time needed to cover the various topics, it may be necessary to skip some of the topics below. The topic in color is the topic currently being covered. Topics and materials below the topic in color may change. Materials in parentheses are optional.
Paper references in the topics below are specified through their Digital Object Identifier, when available, or through a link that recognizes Duke affiliation. These links will get you to the full article if you or your institution have proper access privileges. For Duke students, this typically means that the link will work from a Duke computer, but not from elsewhere.
| 0 | Overview and Logistics |
| Date | Topic | Supplementary Materials |
|---|---|---|
| Aug 25 | Contents and logistics of the course | Fei-Fei Li's TED talk. Intro to LaTeX. |
| 1 | Image Processing |
| Date | Topic | Supplementary Materials |
|---|---|---|
| Aug 27 | Convolution and Filtering | — |
| Sep 1 | Image Differentiation | — |
| Sep 3 | Image Pyramids | Matlab image processing code |
| Sep 8 | Math Corner: Linear Transformations | — |
| 2 | Object Detection |
| Date | Topic | Supplementary Materials |
|---|---|---|
| Sep 10 | Histograms of Oriented Gradients | Dalal & Triggs |
| Sep 15 | Supervised Learning | Domingos |
| Sep 17 | [Supervised Learning, cont'd] | — |
| Sep 22 | Random Forest Classifiers | (Criminisi et al.) |
| Sep 24 | Pedestrian Detection | Hough Forests |
| Sep 29 | Math Corner: The Singular Value Decomposition | — |
| 3 | Convolutional Neural Nets |
| Date | Topic | Supplementary Materials |
|---|---|---|
| Oct 1 | Convolutional Neural Nets | (Vedaldi and Zisserman's CNN Practical) |
| Oct 6 | [Convolutional Neural Nets, cont'd] | — |
| Oct 8 | Training Convolutional Neural Nets | — |
| Oct 15 | Convolutional Neural Nets for Image Recognition | Krizhevsky et al. |
| 4 | Point Features |
| Date | Topic | Supplementary Materials |
|---|---|---|
| Oct 20 | Math Corner: Linear Systems | — |
| Oct 22 | Point Correspondences (sections 1-3 of the notes) | — |
| Oct 27 | Points of Interest (section 4 of the notes) | — |
| 5 | Image Formation |
| Date | Topic | Supplementary Materials |
|---|---|---|
| Oct 29 | Rigid Geometric Transformations | — |
| Nov 3 | A Camera Model | — |
| Nov 5 | [In-Class Midterm Exam] | — |
| 6 | 3D Reconstruction |
| Date | Topic | Supplementary Materials |
|---|---|---|
| Nov 10 | Epipolar Geometry (section 1 of the notes) | — |
| Nov 12 | The Essential Matrix (section 2 of the notes) | — |
| Nov 17 | Homogeneous Coordinates | — |
| Nov 19 | The Eight-Point Algorithm | (Longuet-Higgins) |
| Nov 24 | [The Eight-Point Algorithm cont'd] | — |
| [Dec 1] | [Camera Calibration] | (Zhang's Calibration Method) |
| [Dec 3] | [The Standard Reconstruction Pipeline] | (Building Rome in a Day) |
COMPSCI 527, Duke University, Site based on the fluid 960 grid system