16-385 Computer Vision, Spring 2019 |

Time: | Mondays, Wednesdays 1:30PM - 2:50PM | |

Location: | Hamerschlag Hall B103 | |

Instructor: | Ioannis (Yannis) Gkioulekas | |

Teaching Assistants: | Sharvani Chandu, Chengqian Che, Abhay Gupta, Anshuman Majumdar, Neeraj Sajjan |

Course Description

This course provides a comprehensive introduction to computer vision. Major topics include image processing, detection and recognition, geometry-based and physics-based vision and video analysis. Students will learn basic concepts of computer vision as well as hands on experience to solve real-life vision problems.

Prerequisites

This course requires familarity with linear algebra, calculus, basic probability, as well as programming. In particular, the following courses serve as prerequisite:

- "Mathematical Foundations of Electrical Engineering" (18-202) and "Principles of Imperative Computation" (15-122) (OR)
- "Matrix Algebra with Applications" (21-240) and "Matrices and Linear Transformations" (21-241) and "Calculus in Three Dimensions" (21-259) and "Principles of Imperative Computation" (15-122)

Matlab will be used for project assignments and will be covered as part of the introduction to the course.

Textbook

Readings will be assigned from the following textbook (available online for free):

- Computer Vision: Algorithms and Applications, by Richard Szeliski.

Additional readings will be assigned from relevant papers. Readings will be posted at the last slide of each lecture.

The following textbooks can also be useful references but are not required:

*Multiple View Geometry in Computer Vision,*by Richard Hartley and Andrew Zisserman.*Computer Vision: A Modern Approach,*by David Forsyth and Jean Ponce.*Digital Image Processing,*by Rafael Gonzalez and Richard Woods.

Evaluation

Your final grade will be made up from:

- Seven homework assignments (95%).
- Class participation (5%).
- Talk attendance (5%).

**Homework assignments:** All homework assignments will have a programming component, and some of them will also have a theory component involving pen-and-paper exercises. The programming component of all assignments be done in Matlab. There will be an ungraded zeroth assignment that will serve as a short Matlab tutorial. We have collected a few useful Matlab resources here.

**Late days:** For the homework assignments, students will be allowed a total of **five** free late days. Any additional late days will each incur a 10% penalty.

**Submitting homeworks:** We use Canvas for submitting and grading homeworks.

Discussion

We use Piazza for class discussion and announcements.

Email, Office Hours, and Discussion

**Email:** Please use [16385] in the title when emailing the teaching staff!

**Office hours:** Office hours for the rest of the semester are as follows:

**Monday 5-7 pm**, NSH 1109, Sharvani.**Tuesday 5-7 pm**, NSH 4119, Anshuman.**Wednesday 4-6 pm**, NSH 4119, Neeraj.**Thursday 4-6 pm**, NSH 4119, Abhay.**Friday 3-5 pm**, Smith Hall graphics lounge, Yannis.**Friday 5-7 pm**, Smith Hall graphics lounge, Bruce.

Feel free to email us about scheduling additional office hours.

Syllabus and Schedule

The following syllabus is **tentative** and will most likely change during the semester. Slides will be updated on this site after each lecture.

Date | Topics | Slides | Assignments |
---|---|---|---|

M, Jan 14 | Introduction | pdf, pptx | HW0 out |

W, Jan 16 | Image filtering | pdf, pptx | |

M, Jan 21 | No class (MLK day) | ||

W, Jan 23 | Image pyramids and Fourier transform | pdf, pptx | HW1 out |

M, Jan 28 | No class | ||

W, Jan 30 | No class | ||

M, Feb 4 | Hough transform | pdf, pptx | |

W, Feb 6 | Feature and corner detection | pdf, pptx | |

M, Feb 11 | Feature descriptors and matching | pdf, pptx | |

W, Feb 13 | 2D transformations | pdf, pptx | HW1 due, HW2 out |

M, Feb 18 | Image homographies | pdf, pptx | |

W, Feb 20 | Camera models | pdf, pptx | |

M, Feb 25 | Two-view geometry | pdf, pptx | |

W, Feb 27 | Stereo | pdf, pptx | HW2 due, HW3 out |

M, Mar 4 | Structure from motion | pdf, pptx | |

W, Mar 6 | Radiometry and reflectance | pdf, pptx | |

S, Mar 10 | HW3 due | ||

M, Mar 11 | No class (spring break) | ||

W, Mar 13 | No class (spring break) | ||

M, Mar 18 | Radiometry continued | pdf, pptx | HW4 out |

W, Mar 20 | Photometric stereo and shape from shading | pdf, pptx | |

M, Mar 25 | Image processing pipeline | pdf, pptx | |

W, Mar 27 | Introduction to recognition | pdf, pptx | HW4 due, HW5 out |

M, Apr 1 | Bag of words | pdf, pptx | |

W, Mar 3 | No class | ||

M, Apr 8 | Neural networks | pdf, pptx | |

W, Apr 10 | Convolutional neural networks | pdf, pptx | HW5 due, HW6 out |

M, Apr 15 | Optical flow | pdf, pptx | |

W, Apr 17 | Alignment and tracking | pdf, pptx | |

M, Apr 22 | Temporal models and SLAM | pdf, pptx | |

W, Apr 24 | Graph-based methods | pdf, pptx | HW6 due, HW7 out |

M, Apr 29 | Segmentation | pdf, pptx | |

W, May 1 | Wrap-up | pdf, pptx | |

S, May 5 | HW7 due |

Special Thanks

These lecture notes have been pieced together from many different people and places. Special thanks to colleagues for sharing their slides: Kris Kitani, Bob Collins, Srinivasa Narashiman, Martial Hebert, Alyosha Efros, Ali Faharadi, Deva Ramanan, Yaser Sheikh, and Todd Zickler. Many thanks also to the following people for making their lecture notes and materials available online: Steve Seitz, Richard Selinsky, Larry Zitnick, Noah Snavely, Lana Lazebnik, Kristen Grauman, Yung-Yu Chuang, Tinne Tuytelaars, Fei-Fei Li, Antonio Torralba, Rob Fergus, David Claus, and Dan Jurafsky.