CAP4453 – Robot Vision
(3 Credit Hours)
[ Home | Schedule | Course Material | Grading Policy ]
Course goals: The study of mechanical vision is one of the few areas of science which blends one’s intuition with formal methods. Vision (whether in humans or machines) is fundamentally a computational process. Visual processes for machines must be able to deliver the kinds of capabilities that humans have: scene recognition, motion processing, navigational abilities, and so forth. This course will begin by examining some of the elementary concepts in machine vision. Subprocesses to be examined include: edge detection, methods for obtaining shape information from images, object detection, and motion analysis. The student will also be exposed to unsolved problems in these topics, the solutions to which have very high technological pay-offs. The workload consists of interesting reading, programming, and tests. This class is suitable for undergradaute students in Computer Science and Engineering disciplines, and anyone else who wishes an introduction to machine vision.
A tentative list of topics to be covered in this course,
- Basics of Linear Algebra
- Image Filtering
- Edge Detection
- Feature Extraction
- Optical Flow
- Basics of Neural Networks
- Deep Learning for Computer Vision
- Image Segmentation
- Image Classification
- Object Detection
NOTE: The classes is currently scheduled for face-to-face lectures in Blendflex mode.
- The office hours will be virtual using Zoom. The links to the meetings will be shared on Webcourses.
- The lectures will be recorded and shared with the class. In person attendance is not mandatory but we encourage the students to attend live lectures via zoom.
- A student will be able to attend only one lecture per week face-to-face (due to Blendflex mode). We will announce the groups on Webcourses.
- This course will also use Zoom for synchronous (“real time”) class meetings. The zoom link for the lecture and office hours will be provided via Webcourses. Meeting dates and times will be scheduled through Webcourses@UCF and should appear on your calendar.
Please take the time to familiarize yourself with Zoom by visiting the UCF Zoom Guides at <https://cdl.ucf.edu/support/webcourses/zoom/>. You may choose to use Zoom on your mobile device (phone or tablet).
Things to Know About Zoom:
- You must sign into my Zoom session using your UCF NID and password.
- The Zoom sessions are recorded.
- Improper classroom behavior is not tolerated within Zoom sessions and may result in a referral to the Office of Student Conduct.
- You can contact Webcourses@UCF Support at <https://cdl.ucf.edu/support/webcourses/> if you have any technical issues accessing Zoom.
Pre-requisites: COP 3503C and MAC 2312, or C.I, Basic Probability/Statistics, a good working knowledge of any programming language (Python, C/C++, or Java), Linear algebra, Vector calculus.
Python will be main programming environment for the assignments. Following book (Python programming samples for computer vision tasks) is freely available.
Python for Computer Vision. A tutorial will be given in the class on PyTorch for deep learning.
Students are free to discuss ideas and technical concepts. However, students must submit original work for all assignments, projects and exams, and abide by UCF Golden Rule.
University-Wide Face Covering Policy for Common Spaces and Face-to-Face Classes
To protect members of our community, everyone is required to wear a facial covering inside all common spaces including classrooms (https://policies.ucf.edu/documents/PolicyEmergencyCOVIDReturnPolicy.pdf. Students who choose not to wear facial coverings will be asked to leave the classroom by the instructor. If they refuse to leave the classroom or put on a facial covering, they may be considered disruptive (please see the Golden Rule for student behavior expectations). Faculty have the right to cancel class if the safety and well-being of class members are in jeopardy. Students will be responsible for the material that would have been covered in class as provided by the instructor.
Notifications in Case of Changes to Course Modality
Depending on the course of the pandemic during the semester, the university may make changes to the way classes are offered. If that happens, please look for announcements or messages in Webcourses@UCF or Knights email about changes specific to this course.
COVID-19 and Illness Notification
Students who believe they may have a COVID-19 diagnosis should contact UCF Student Health Services (407-823-2509) so proper contact tracing procedures can take place.
Students should not come to campus if they are ill, are experiencing any symptoms of COVID-19, have tested positive for COVID, or if anyone living in their residence has tested positive or is sick with COVID-19 symptoms. CDC guidance for COVID-19 symptoms is located here: (https://www.cdc.gov/coronavirus/2019-ncov/symptoms-testing/symptoms.html)
Students should contact their instructor(s) as soon as possible if they miss class for any illness reason to discuss reasonable adjustments that might need to be made. When possible, students should contact their instructor(s) before missing class.
In Case of Faculty Illness
If the instructor falls ill during the semester, there may be changes to this course, including having a backup instructor take over the course. Please look for announcements or mail in Webcourses@UCF or Knights email for any alterations to this course.
Course Accessibility and Disability COVID-19 Supplemental Statement
Accommodations may need to be added or adjusted should this course shift from an on-campus to a remote format. Students with disabilities should speak with their instructor and should contact firstname.lastname@example.org to discuss specific accommodations for this or other courses.