ECE 4230, ECE 5470 Computer Vision: Course Syllabus 2024

Credit Hours: 3

Location

Lectures: Hollister Hall 110, TR  10:10am - 11:25am

Instructor

A. P. Reeves, 392 Rhodes Hall, (255-2342) reeves@cornell.edu

Teaching Assistants

 Shih-ming Lin <sl2874@cornell.edu> 

James Jun Hao Ong <jo445@cornell.edu>

Hunter Tan ht499@cornell.edu

Prerequisite

The prerequisite for ECE5470 is ECE/ENGRD 2720: Data Science for Engineers, or permission of the instructor.

Textbooks

There is no required textbook for this course. Several useful texts and references are listed on the course website.

Class schedule Tuesday Thursday

Exam Schedule

There will be 3 in class exams, and no Final exam

Prelim Schedule

Prelim 1

Thursday Oct. 3

10:10am - 11:25am [may be changed to 7:30 pm]

Prelim 2

Tuesday Nov. 5

10:10am - 11:25am [may be changed to 7:30 pm]

Prelim 3

Thursday Dec. 5

10:10am - 11:25am [may be changed to 7:30 pm]

Note: There will be a prelim on the last day of classes

Classes will be held at 10;10 am on the following days:

August 27 29, September 3 5 10 12 17 19 24 26,

October 1 3 8 10 17 22 24 29 31, Nov 5 7 12 14 19 21 26, and December 3 and 5

 

 

 

Information and Help

The primary information source for ECE5470 is Canvas. Notes, and labs are on the on-line web at the following URL:

http://www.via.cornell.edu/ece5470 Links to an external site.

This will provide current information on reference materials, lecture contents, labs and homework assignments. Any corrections or changes will be posted on Canvas. Questions about the course may be sent to the instructor or the TA preferably by Ed Discussions and also by direct email.

For help with the course material connect with the course TAs and instructor at posted office hours or by email.

If you wish to have a homework or exam regraded, then first connect with a TA to discuss the issue.

Course Requirements

The final grade for the course will be computed from the following weighted components. There are no absolute thresholds for grades; the grades for the course will be determined from the distribution of grades for the whole class. All work for this course is expected to be original.

Prelim 1

 20%

Prelim 2

 20%

Prelim 3

 20%

Quizzes

 10%

Labs

 30%

Exams:

There are three in-class exams for this course. Exams cover the material given in both lectures and labs. The second exam will focus on material that is not covered in the first exam.

Quizzes:

Quizzes may occasionally be given based on the course material to reinforce the understanding of various course topics.

Labs:

Computer labs assignments generally occur on a weekly basis, lab reports are due at the end of the lab period. The schedule for the labs is provided on the course website; this schedule may be revised during the semester. Lab assignments may be conducted on ECE computer facilities, some labs permit the optional use of external resources.

 

Students taking ECE 5470 will be required to do a small independent project on a topic that they select. This will count as one of their labs and will be of similar effort to a lab.

 

Missed Deadlines

Course assignments are due to be submitted to Canvas by 11:59 p.m. on the due date. Late assignments will receive a 10% grade penalty per day late. There are a total of three slip days allowed per semester for lab or homework assignments.

Class Handouts

In general, slides presented in class will be made available on the course website; in addition, a video recording of the class may be made available on canvas. These slides are not intended to be complete notes and students are responsible for taking notes on information presented in class that is not in the slides.

Class Attendance

Students are expected to attend class and to be there at the start of class. Pop-quizzes for credit may be given at any time.

Course Description:

Computer Vision is the construction of explicit meaningful descriptions of physical objects and other observable phenomena from images. Basic techniques for image processing and feature extraction are covered in lectures; topics include image formation, edge detection, region growing, shape description, machine learning for computer vision. Higher-level more experimental image analysis techniques, such as video image sequence analysis, and 3D images are covered by selected presentations.

During the first part of the semester a sequence of computer labs will provide experience in the software tools that are important for computer vision applications and will include the basics of image processing, feature extraction and machine learning. In the last part of the semester, students will do additional labs on convolution neural networks and deep learning.

Essentially, ECE 4230, ECE5470 is a first course on learning about how computers can see; that is, interpret the multidimensional signals provided by imaging sensors. Computer vision has a very wide range of applications from medical diagnosis to seeing robots, from particle physics to geological surveying, and from face recognition to autonomous vehicle navigation. The objective of this course is to provide students with an understanding of the fundamental methods and an appreciation for the state of the art and the future potential of computer vision.

Course Objectives

Students will gain an understanding of the fundamental issues and techniques for extracting information from digital imagery. They will have a good knowledge of well-established methods for decomposing an image into basic elements: edges, regions, and other features. They will also be introduced to convolution neural networks and deep learning higher-level image understanding methods.

Introductory labs provide the student with experience in using computer systems and the associated specialized software tools for processing and extracting information from digital images.

Caveat

The schedule and procedures in this course are subject to change as always. The labs in final part of the course are new to this year.

Academic Integrity

Students expected to abide by the Cornell University Code of Academic Integrity with work submitted for credit representing the student’s own work. Discussion and collaboration on homework and laboratory assignments is permitted and encouraged, but final work should represent the student’s own understanding. Specific examples of this policy implementation will be discussed in class. Course materials posted on the computer vision website are for class use; students are not permitted to buy or sell any course materials without the express permission of the instructor. Such unauthorized behavior will constitute academic misconduct.

Inclusive Learning Environment

Cornell supports an inclusive learning environment where diversity and individual differences are understood, respected, appreciated, and recognized as a source of strength. It is expected that students in this class will respect differences and demonstrate diligence in understanding how other peoples' perspectives, behaviors, and worldviews may be different from their own.

Accommodations for Students with Disabilities

Cornell University is committed to full inclusion for all persons to its educational program and services. Services and reasonable accommodations are available to persons with temporary and permanent disabilities when conditions cause barriers to equal educational opportunity. Student Disability Services (SDS) determines the eligibility of students to receive accommodations and works collaboratively with the student and university faculty and staff to recommend appropriate accommodations.  Students are advised to contact SDS as early as possible in the semester to ensure appropriate accommodations: www.sds.cornell.edu, 607-254-4545.

Attestation

By registering for this class and accessing course materials through Canvas, students agree to abide by University, College, Department, and Course policies

COVID 19

Masks are not required in classrooms for Fall 23. However, the University strongly endorses compliance with requests to mask from students, staff, or faculty who are health compromised. If you are health compromised and would like me to request that the class be masked, please send me an email with any rationale that you are comfortable with me sharing. I do not need to identify you unless you would prefer that I do.

COVID 19 Symptoms

Zoom recordings of lecturers are not available for absences, including absences due to illness. For any illness, you are expected to keep up with course material by working with a peer in the course or accessing our shared notes page of CANVAS. We will allow time to find a peer buddy in the first week of the course.

If you have symptoms of COVID19, here is what you should do for my class:

  1. Do not come to class if you have symptoms
  2. Email me before class starts to let me know that you are not coming and are instead seeking out an antigen test. I expect that, according to university policy and free access to tests, you will be able to take a test immediately upon noticing symptoms and will have a result within minutes.
  3. If the test is negative, I expect you to be in the next class, having caught up on material from a classmate or the shared notes page.
  4. If your antigen test is positive, you must immediately upload the result to Daily Check. This will trigger instructions and a letter of temporary accommodation. You must forward this email to [me, TA] to receive accommodation, the system does not send it for you. Once you forward [me, TA] the letter, we will provide guidance on how you should keep up with material for the next 5 days (usually no more than one additional class will be missed).
  5. Please wear a mask in class through the 10th day after symptoms begin.