CS 6476 Computer Vision
CS 6476 Computer Vision
Spring 2021, MW 12:30 to 1:45, Synchronous remote lecture on Bluejeans
Instructor: James Hays
TAs: Cusuh Ham (head TA), Anant Joshi. Arvind Krishnakumar, John Lambert, Vijay Upadhya, Jing Wu
Course Description
This course provides an introduction to computer vision including fundamentals of image formation, camera imaging geometry, feature detection and matching, stereo, motion estimation and tracking, image classification and scene understanding. We'll explore methods for depth recovery from stereo images, camera calibration, automated alignment, tracking boundary detection, and recognition. We'll use both classical machine learning and deep learning to approach these problems.The focus of the course is to develop the intuitions and mathematics of the methods in lecture, and then to learn about the difference between theory and practice in the projects.
Learning Objectives
Upon completion of this course, students should be able to:
• 1. Recognize and describe both the theoretical and practical aspects of computing with images. Connect issues from Computer Vision to Human Vision
• 2. Describe the foundation of image formation and image analysis. Understand the basics of 2D and 3D Computer Vision.
• 3. Become familiar with the maior technical approaches involved in computer vision. Describe various methods used for registration, alignment, and matching in images.
• 4. Get an exposure to advanced concepts leading to object categorization and segmentation in images.
• 5. Build computer vision applications.
Prerequisites
No prior experience with computer vision is assumed. although previous knowledee of visual computing or signal processing will be helpful. The following skills are necessary for this class:
• Data structures: You'll be writing code that builds representations of images, features, and geometric constructions.
• Programming: Projects are to be completed and graded in Python and PyTorch. All project starter code will be in Python. TA's will support questions about Python. If you've never used Python that is OK, as long as you have programming experience.
• Math: Linear algebra, vector calculus. and probability. Linear algebra is the most important and students who have not taken a linear algebra course have struggled in the past.
Grading
Your final grade will be made up from .
• 100% 6 programming projects
This course traditionally has in person quizzes, but we will instead place more emphasize on the projects this semester because of the difficulty in remotely administering exams.
You will lose 10% each day for late projects. However, you have six "late days" for the whole course. That is to say, the first 24 hours after the due date and time counts as 1 day, up to 48 hours is two and 72 for the third late dav. This will not be reflected in the initial grade reports for your assignment, but they will be factored in and distributed at the end of the semester so that you get the most points possible.
These late days are intended to cover unexpected clustering of due dates, travel commitments. interviews. hackathons etc. Don't ask for extensions to due dates because we are already giving you a pool of late days to manage yourself. In fact, we're doubling the pool of late days this semester because of the difficult circumstances.
Academic Integrity
Academic dishonesty will not be tolerated. This includes cheating, lying about course matters, plagiarism, or helping others commit a violation of the Honor Code. Plagiarism includes reproducing the words of others without both the use of quotation marks and citation. Students are reminded of the obligations and expectations associated with the Georgia Tech Academic Honor Code and Student Code of Conduct. available online at www.honor.gatech.edu. We will use tools to find code sharing in projects.
You are expected to implement the core components of each project on your own, but the extra credit opportunties often build on third party data sets or code. That's fine. Feel free to include results built on other software, as long as you are clear in vour handin that it is not your own work.
You should not view or edit anvone else's code. You should not post code to Canvas. except for starter code / helper code that isn't related to the core project.
Learning Accommodations
If needed, we will make classroom accommodations for students with documented disabilities. These accommodations must be arranged in advance and in accordance with the office of disability services. (disabilityservices.gatech.edu).
Important Links:
• Canvas. This should be your first stop for questions and announcements. It will also be used for project handin.
Contact Info and Office Hours:
If possible, please use Piazza to ask questions and seek clarifications before emailing the instructor or staff.
• James: haysfat]gatech.edu
• Cusuh Ham: cusuhfat gatech.edu
• Anant Joshi: anant.joshifat]gatech.edu
• Arvind Krishnakumar: akrishna[atlgatech.edu
• John Lambert: johnlambert[atlgatech.edu
• Vijay Upadhya: vupadhya6[atlgatech.edu
• Jing Wu: jingwufatlgatech.edu
Office Hours
• James, Tuesday, 2 to 3 on Bluejeans
• TA hours: TBD
Projects Highlighted projects All Results
Convolution and Hybrid images
SIFT Local Feature Matching
Camera Calibration and Fundamental
Matrix Estimation with RANSAC
Stereo
Recognition with deep learning
Semantic Segmentation
All starter code and projects will be in Python with the use of various third party libraries. We will make an effort to support MacOS, Windows, and Linux. The course does not teach python and assumed you have enough familiarity wit procedural programming languages to complete the projects.
Textbook
Readings will be assigned in "Computer Vision: Algorithms and Applications, 2nd edition" by Richard Szeliski.This semester is our first time using the 2nd edition of the book. The book is available for free online or available for purchase.
Syllabus
Class Date |
Topic |
Slides |
Reading |
Projects |
Mon, Jan 18 |
No classes, Institute holiday |
|
|
|
Wed. Jan 20 |
Introduction to computer vision |
|
Szeliski 1 |
Proiect 1 out |
Image Formation and Filtering (Szeliski chapters 2 and 3) |
||||
Mon. Jan 25 |
Cameras and Optics |
|
Szeliski 2.1, especially 2.1.4 |
|
Wed, Jan 27 |
Light and Color and Image Filtering |
|
Szeliski 2.2 and 2.3 |
|
Mon. Feb 1 |
Thinking in Frequency |
|
Szeliski 3.2 and 3.4 |
|
Feature Detection and Matching |
||||
Wed. Feb 3 |
Interest points and corners |
|
Szeliski 7.1. 1 and 7.1.2 |
|
Mon, Feb 8 |
Local image features |
|
Szeliski 7.1.3 |
|
Wed, Feb 10 |
Model fitting, Hough Transform |
|
Szeliski 7.4.2 and 2.1 |
|
Mon, Feb 15 |
RANSAC and transformations |
|
Szeliski 8.1 |
|
Multiple Views and Motion |
||||
Wed. Feb 17 |
Stereo intro and Camera Calibratior |
|
Szeliski 12 and 11.2.1 |
|
Mon. Feb 22 |
Epipolar Geometry and Structure from Motion |
|
Szeliski 11 |
|
Wed. Feb 24 |
Stereo Correspondence and Optical Flow |
|
Szeliski 12 and 9.4 |
|
Mon. Mar 1 |
TBD |
|
|
|
Recognition |
||||
Wed. Mar 3 |
Machine learning crash course |
|
Szeliski 5.1 and 5.2 |
|
Mon. Mar 8 |
Recognition and bag of words |
|
Szeliski 6.2.1 |
|
Wed, Mar 10 |
TBD |
|
|
|
Mon. Mar 15 |
Obiect Detection with a sliding window |
|
Szeliski 6.3 |
|
Wed, Mar 17 |
Big Data |
|
|
|
Mon, Mar 22 |
Crowdsourcing and Human Computation |
|
|
|
Wed, Mar 24 |
No classes. Institute holiday |
|
|
|
Deep Learning |
||||
Mon. Mar 29 |
Neural networks Basics and Convolutional Networks |
|
Szeliski 5.3 |
|
Wed. Mar 31 |
Object Detectors Emerge in Deep Scene CNNs and Deeper Deep Architectures. |
|
|
|
Mon, Apr 5 |
"Unsupervised" Learning and Colorization |
|
Szeliski 5.4.7 |
|
Wed, Apr 7 |
Structured Output from Deep Networks |
|
Szeliski 5.5 |
|
Mon. Apr 12 |
Semantic and Panoptic Segmentation |
|
|
|
Wed. Apr 14 |
3D CNNs and Lidar |
|
|
|
Mon, Apr 19 |
Transformer architectures |
|
|
|
Wed, Apr 21 |
TBD |
|
|
|
Mon, Apr 26 |
TBD, Final Instructional Class Days |
|
|
|
Wed, Apr 28 |
No classes, reading period |
|
|
|
Final Exam Period |
Not used. No class or final exam |
|
|
|
Acknowledgements
The materials from this class rely significantly on slides prepared by other instructors, especially Derek Hoiem and Svetlana Lazebnik. Each slide set and assignment contains acknowledgements. Feel free to use these slides for academic or research purposes, but please maintain all acknowledgements.
2021-02-04