Chenliang Xu

pic

Spring 2022 - CSC 249/449: Machine Vision

Basic Information

Meet Time/Location: Tue/Thu 09:40-10:55 on Zoom for Janurary then Gavett 202
(You can find the class Zoom link on Blackboard course main page.)

Instructor: Prof. Chenliang Xu
Instructor's Office Hours: Tue 11:00-noon on Zoom

TAs and Office Hours:

Information Flow: We will use Blackboard to make announcements, post course materials, and collect assignments. The course ID is CSC249.1.SPRING2020ASE. This course website contains an outline of the course schedule and serves as a syllabus.

Email and Discussion: We will use Blackboard Discussion Board as the primary communication method between students and the instruction team. Using it, you can get help fast from the instruction team, and other students having similar questions can all benefit from your post. You can also use it to find teammates and start a discussion among your fellow students. Therefore, if you have a course-related question, the Discussion Board should be your first go-to place. However, I understand that sometimes you have personal questions. In this case, feel free to email us (and it may take some time for me to get to your email).

Credit Hours: This is a four-credit-hour course. The credit hours are met by weekly lectures (150 minutes), office hours, homework assignments, and the final course project.


Course Description

Fundamentals of computer vision, including image formation, elements of human vision, low-level image processing, and pattern recognition techniques. Advanced topics include modern visual features, graphical models, model-based and data-driven approaches, and contextual inference, as well as illustrative examples of successes and challenges in applications. CSC 449, a graduate-level course, requires additional readings and assignments.

Rough Topic Outline:

Course Objective: An introduction to computer vision. The course is designed as an upper-level elective for Computer Science undergraduate students and an AI-area breath course for graduate students. The students will develop a strong understanding of formulating and solving problems using computer vision.

Prerequisites: MATH 161 and CSC 242; MATH 165 strongly recommended; in addition, you should be familiar with Python, which is used for all programming assignments.


Schedule

This is a tentative course schedule and is subject to changes over the term.
All classes (Zoom and in-person) will be recorded and _only_ made available based on individual circumstances, e.g., COVID, that you have a solid reason to miss the synchronous class. Please note that the instructor owns the copyright of all course materials including recordings, You should not post them on the Internet or share them with a friend/classmate.

Dates Tuesday (T) Thursday (R) PS/Project Read
1/11,13 No Class: Before Term Introduction
1/18,20 Camera Models Linear Filtering PS-0 Due 2.1, 3.2-3.3.1
1/25,27 Edges Corners 7.1, 7.2
2/1,3 SIFT and Feature Matching Fitting I PS-1 Due
Teaming Due
7.4, 8.1.4
2/8,10 Fitting II Image Alignment 8.1
2/15,17 Dense Motion Estimate Visual Odometry 9.1, 9.3, 11.1-.3
2/22,24 Segmentation Neural Network PS-2 Due 7.5, 5.3
3/1,3 CNN Basics CNN Architectures Proposal Due 5.4, 5.5
3/8,10 Spring Break Spring Break
3/15,17 Midterm Review Midterm Exam
3/22,24 Feature Visualization Object Recognition I PS-3 Due
3/29,31 Object Recognition II Face Recognition
4/5,7 GAN and Image Synthesis Styler Transfer
4/12,14 RNN and Applications Video Understanding
4/19,21 Vision and Language Project Presentation I Slides Due
4/26,28 Project Presentation II No Class: Term Finished Report Due

Course Work and Evaluation

Late Work Policy: No individual extensions, and the following policy applies for all late work. Deduct 1% total score of the late assignment per hour passing the deadline. E.g., you submit PS-1 12 hours passing the deadline, then the max score you will get is 88% of PS-1. We will not accept your submission after 72 hours over the deadline. All assignments should be submitted on Blackboard. No makeups for the midterm exam.

Regrading: Any questions about the grading of a piece of work must be raised within one week of the date that the work was returned. In other words, if you do not pick up your work in a timely fashion, you may forfeit your right to question the grading of your work.


Textbook and Other Resources

We will use the following textbook by Richard Szeliski. Please note that we will use the 2nd edition, which was recently updated with many new contents.

In addition, I recommend the following textbooks as supplementary reading.

Other Policies

Code of Conduct: Check here for classroom "etiquette" expectations.

Academic Honesty: All assignments and activities associated with this course must be performed in accordance with the University of Rochester's Academic Honesty Policy. More information is available here. You are expected to read, understand, and follow the policy. Additionally:

Posting homework and project solutions to public repositories on sites like GitHub is a violation of the College’s Academic Honesty Policy, Section V.B.2 “Giving Unauthorized Aid.”

Disabilities: Please see me about your required accommodations as early as possible in the term. The University of Rochester respects and welcomes students of all backgrounds and abilities. In the event you encounter any barrier(s) to full participation in this course due to the impact of a disability, please contact the Office of Disability Resources. The access coordinators in the Office of Disability Resources can meet with you to discuss the barriers you are experiencing and explain the eligibility process for establishing academic accommodations. You can reach the Office of Disability Resources at: disability@rochester.edu; (585) 276-5075; Taylor Hall; www.rochester.edu/college/disability.

Accommodations for COVID-Related Illness: Please let me know asap. At the same time, you may contact the College Center for Advising Services (CCAS) or the Graduate Education and Postdoctoral Affairs office. These offices will be able to assist you and refer you to the right resources.