Chenliang Xu

pic

Spring 2020 - CSC 249/449: Machine Vision

(Updated in response to COVID-19 outbreak)

Basic Information

All zoom meetings are password protected. Please find the code on Blackboard.

Meet Time/Location: T/R 12:30-13:45 in Goergen 101 via Zoom

Instructor: Prof. Chenliang Xu
Instructor's Office Hours: T/R 2:15-3pm, via Zoom

Graduate TAs and Office Hours:

UG TAs: Yihang Xu, Sizhe Li, Xiaoning Guo, Tianyou Xiao, Weitao Tan

Dicussion: We will use Piazza for class discussion and communication. The system is highly catered to getting you help fast and efficiently from classmates, the TA, and myself. Rather than emailing questions to the teaching staff, I encourage you to post your questions on Piazza. Find our class page here.

Information Flow: We will use Blackboard to make announcements, posting lecture notes and assignments, and submitting student work. The course ID is CSC249.2020SPRING.51879. This course website contains an outline of the course schedule and also serves for the purpose of a syllabus.


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
Prerequisites

Basic knowledge of probability, linear algebra (MTH 165 Strongly Recommended); data structures, algorithms; programming experience. For assignments and projects, the most common programming language is Python.


Schedule

This is a tentative schedule of the course and will be modified over the term.
Course materials will be posted on Blackboard.

Dates Tuesday (T) Thursday (R) HW Due Project
1/16 No Class: Before Term Introduction
1/21,23 Linear Filtering and Image Transforms Edges Tue: 1 Out
1/28,30 Corners SIFT and Feature Matching
2/4,6 Neural Network and Backpropagation CNN and Feature Visualization Tue: 1 Due
Tue: 2 Out
2/11,13 Case Study: Implement CNN Backpropagation Fitting I
2/18,20 Fitting II Image Alignment Thu: 2 Due
Thu: 3 Out
2/25,27 Dense Motion Estimate Segmentation
(meet in B&L 109)
3/3,5 Case Study: Object Tracking Midterm Exam
3/10,12 No Class: Spring Break No Class: Spring Break
3/17,19 No Class: Spring Break Ext. No Class: Spring Break Ext.
3/24,26 RNN and its Applications Case Study: Image Captioning Thu: 3 Due
Thu: 4 Out
3/31,4/2 Advanced CNNs I Advanced CNNs II Train/Val Out
4/7,9 Object Recognition I Object Recognition II Thu: 4 Due
4/14,16 Face Recognition, Style Transfer GAN and Image Synthesizing Tue: Test Out
4/21,23 Camera Models, Light and Color Stereo Vision Thu: Submit Due
4/28 Project Presentation No Class: Term Finished

Course Work and Evaluation

Late Work Policy: Deduct 1% of total score per hour passing the deadline for each assignment. We will not accept your submission after 72 hours over the deadline. All assignments should be submitted on Blackboard.

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.

Policy on Incomplete: The student will receive an Incomplete if he/she missed either the mid-term exam or the final project or any three or more of the assignments.


Textbook

Machine/Computer Vision is under rapid development over the past few years. There is not a perfect textbook I know of that covers everything needed for an introductory computer vision course in today's context. Even though, we will use the following textbook by Szeliski, which is widely used in many other computer vision courses and is also freely available online.

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

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.

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: If you need an accommodation based on the impact of a disability, please contact me privately during the first two weeks to discuss your specific needs. Alternatively, contact Center for Excellence in Teaching and Learning at 585-275-9049 in room 1-154 Dewey Hall to coordinate reasonable accommodations.