We start to use Webex for our class from 3/19/2020
Course Description
This course provides an introduction to computer vision, which includes fundamentals of image formation, camera imaging geometry, feature detection and matching, stereo, motion estimation and tracking, image/video classification, image/video segmentation and scene understanding. We'll develop basic methods for applications that include finding known models in images/videos, depth recovery from stereo, automated image alignment, boundary detection, and recognition. The course focus 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. Deep learning methods are introduced because of recent attentions from both industry and academy.
Learning Objectives:
Students should be able to:
Recognize and describe both the theoretical and practical aspects of computing with images.
Connect issues from Computer Vision to Human Vision.
Describe the foundation of image formation and image analysis. Understand the basics of 2D and 3D Computer Vision.
Become familiar with the major technical approaches involved in computer vision.
Describe various methods used for registration, alignment, and matching in images.
Get an exposure to advanced concepts leading to object and scene categorization from images.
Know deep learning methods for image classification and object detection, segmentation and recognition.
Build computer vision applications.
Prerequisites:
No prior experience with computer vision is assumed, although previous knowledge 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. All project starter code will be in Python. TA (if we will have one) 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:
40% from at least 2 programming projects
60% from 2 written exams (mid-term and final)
You will lose 5% each time for missing class. You will lose 5% for three times for your late comings.
Suggested Text Books (optional):
Richard Szeliski: "Computer Vision: Algorithms and Applications"
Classroom:
Woodward Hall 135
Class Time:
Thursday 4:00PM-6:45PM
Instructor Office Hours:
Thursday 11:00AM-13:30PM; 6:45PM-8:45PM or make appointment
Class TA:
Name: Changlin Li, Email: cli33@uncc.edu
Office Location: Woodward Hall TA's Office (second floor)
Office Hours: Thursday 10:00AM-15:30PM
Exam Schedules:
Mid-Term Test: March 12, 2020, 4:00PM-6:45PM, (one page note is allowed)
Final Test: May 7, 2020, 2:00PM-4:30PM, (one page note is allowed)
2/20/2020: Today's Class is canceled by UNCC because of bad weather; Students should exercise good judgment and monitor local weather forecasts when determining travel plans
Schedules for Project Demonstration and Assessment: 2/3/2020-5/6/2020
You can make appointment with TA for individual project demonstration and grading.
Final Test: 5/7/2020, 2:00PM-4:30PM
Acknowledgements
The materials from this class rely significantly on slides prepared by other instructors, especially James Hays, 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.
Do what you can, with what you have, where you are! ---Theodore Roosevelt---
