Computer Vision (SP25)

Overview

This course offers a comprehensive exploration of key concepts in computer vision, blending traditional image processing methods with cutting-edge AI techniques. Designed to provide students with a strong foundation in visual data analysis, the course will cover a broad spectrum of topics, from image formation to advanced AI-driven applications in computer vision.

The curriculum begins with Image Formation, where students will explore how visual data is captured and represented. The course then moves on to core image processing techniques, including Color Science, Image Filtering, and Restoration & Enhancement, essential for improving image quality and preparing data for analysis.

Students will gain expertise in Feature Detection and Image Matching, learning to identify distinctive image features and apply transformations. The course also covers Classification and Object Detection, empowering students to classify and locate objects within images. This is followed by in-depth discussions on Image Segmentation, enabling the separation of different regions in an image for more precise analysis.

In terms of geometry, the course explores Stereo Vision and Multiview Geometry for depth estimation and understanding 3D structures from 2D images. The study of Motion and Object Tracking techniques will also be introduced, addressing how objects move within scenes and how to track them across frames.

The course further dives into advanced topics such as Photometric Stereo, which helps recover 3D shapes from images, and Human Pose and Action Recognition, focusing on understanding human activities in video. Students will explore cutting-edge AI technologies like Vision-Language Models and Generative Models, which bridge computer vision with natural language understanding and image generation.

Throughout the course, students will gain hands-on experience through programming assignments, allowing them to apply theory to practical problems and gain proficiency in real-world computer vision challenges. By the end of the course, students will have a deep understanding of both classical image processing techniques and modern AI applications in computer vision, preparing them for solving complex visual perception problems in various domains.

Prerequisites

• Instructor's Permission

To succeed in this course, students should have a strong foundation in linear algebra and Python programming. A solid understanding of data structures and algorithms, along with basic knowledge of machine learning concepts, will also be beneficial for effectively engaging with the course material.

As this is a programming-intensive course, strong programming skills are crucial for success!

Class Meetings:

Location: Engineering & CS Center (ECSC) Room 005 ; 

Lecture: Tuesday/Thursday, 2:25 – 4:15 pm

X-hour: Wednesday, 5:30 – 6:20 pm

Format/Attendance

This course will be in-person with some online components.

I expect you to attend class in person unless you have made alternative arrangements due to illness, medical reasons, or the need to isolate due to COVID-19. For the health and safety of our class community, please: do not attend class when you are sick, nor when you have been instructed by Student Health Services to stay home.

Course staff

Instructor: Yu-Wing Tai <yu-wing.tai@dartmouth.edu>

Teaching Assistant: Yuyao Zhang <yuyao.zhang.gr@dartmouth.edu>

Office Hours

You can make an appointment with the course staff (but keep in mind it may take some time to schedule). 

• Yu-Wing Tai: Tuesday / Thursday 1:30-2:20pm ECSC 208, or Appointment via Email
• Yuyao Zhang: Tuesday / Thursday 6:00-8:00pm ECSC 206, or Appointment via Email

If you find you need additional, individualized help beyond office hours, you can reach out to Dartmouth's Tutor Clearinghouse.

Graduate

The undergraduate (83) and graduate (183) sections of this class will be graded separately and we will generally grade graduate students more strictly. For graduates enrolled in 183, I will convert an A/A- to High Pass (HP) and B- or above to Pass (P). Low Pass (LP) starts at C+, and anything D or below receives No Credit (NC).

Submission Deadlines

You will turn in the submission through Canvas, and each assignment will have a strict deadline. 

It’s up to you to check that assignments have been successfully submitted to Canvas. Don’t upload seconds before the deadline to avoid accidents. Double-check that you indeed uploaded the correct file.

Late policy

Late is as defined by Canvas.

For other coursework, there is a 4% per (any portion of an) hour deduction for late submissions. This means that if you submit 70 minutes late, the maximum score you can receive is 92%, and submissions more than 24 hours late get a zero.

Late days:

You have 2 free "late days" available throughout the term. A late day can be used to waive the late penalty for any portion of a day on written or programming assignments, but not for quizzes. Late days cannot be used after the last day of class.

To use a late day and avoid the late penalty, you must include a comment in Canvas with your submission stating: "I would like to use a late day for this."

Note: Late days are counted in terms of "hours."

Exceptions & extensions:

I understand that life and health can sometimes interfere with academic responsibilities. I am generally flexible and understanding if you reach out to me in advance. However, I cannot accommodate requests made after the fact. If you anticipate needing an extension, please contact me in writing well before the deadline (preferably more than a week in advance, not just a couple of days).

Extensions will only be granted after the deadline in the case of a medical emergency.

Note: Deadlines for midterms or projects from other courses cannot be excused.

Regrades

Grading is a noisy process, so there may sometimes be errors (in either direction).

If you believe there is an error in the grading, first make sure you understand everything in the assignment. You may then submit a regrade request by emailing the course staff explaining your concern. We will then regrade your entire assignment or quiz, not just the portion you believe is in error. If we find previously missing deductions, your score may actually go down.

I will only consider regrades that change your grade by at least a full letter grade.

We will not consider regrade requests submitted more than 1 week after the grade is posted, or after the last day of class. 

Honor Principle and permissible sources of information

If you are not already, you should familiarize yourself with Dartmouth's policies on the Academic Honor Principle, and Proper Citation of Sources.

In short: You are welcome and encouraged to chat about assignments with other students in general terms, but your solutions must be written and developed on your own.

 

Properly attributing outside sources (if any)

If you’re ever in doubt, just include a citation in your code and report indicating where some idea came from, whether it be a classmate, a website, another piece of software, or anything. Note that you may still receive a zero for that task if you simply copy the solution from some outside source, but citing it at least maintains your honesty and would not be considered a violation of the academic honor principle.

You should treat proper attribution in code just like you would if you were writing an essay or journal article.

In this class, proper citation format in your code should include two things:

1. At the top of the file include a comment block listing all instances of outside sources used within that file. Think of this like the Works Cite/Bibliography section of a journal article. Number the references so you can refer to them later in the source code. For each item, list the URL, copyright notice any license if applicable, as well as information about how the code/idea is used.
2. Include a comment at a point close to where you adopt some idea/code from somewhere else. Think of this like an in-text parenthetical citation in a journal article. This should include enough information so that it is clear which outside source from the top of your file is being referenced (e.g. the reference number, or the name of author or library). 

The same basic principle applies to your presentations. Any material you reuse from outside sources must be properly attributed both on the slide it is used, and in a Bibliography/References slide.

 

Attendance

You are expected to attend class in person unless you have made alternative arrangements due to illness or other medical reasons. For the health and safety of our class community, please: do not attend class when you are sick, nor when you have been instructed by Student Health Services to stay home.

Consent to recording

Dartmouth has asked that I include the following language describing some bounds on how recording should be used. You do not need to send me any sort of agreement on this – it just makes clear that you shouldn’t record or distribute any recordings without my consent.

The remainder is standard text provided by Dartmouth [here].

1. Consent to recording of course meetings and office hours that are open to multiple students. By enrolling in this course,

   1. I affirm my understanding that the instructor may record meetings of this course and any associated meetings open to multiple students and the instructor, including but not limited to scheduled and ad hoc office hours and other consultations, within any digital platform, including those used to offer remote instruction for this course.

   2. I further affirm that the instructor owns the copyright to their instructional materials, of which these recordings constitute a part, and my distribution of any of these recordings in whole or in part to any person or entity other than other members of the class without prior written consent of the instructor may be subject to discipline by Dartmouth up to and including separation from Dartmouth.

2. Requirement of consent to one-on-one recordings

   By enrolling in this course, I hereby affirm that I will not make a recording in any medium of any one-on-one meeting with the instructor or another member of the class or group of members of the class without obtaining the prior written consent of all those participating, and I understand that if I violate this prohibition, I will be subject to discipline by Dartmouth up to and including separation from Dartmouth, as well as any other civil or criminal penalties under applicable law. I understand that an exception to this consent applies to accommodations approved by SAS for a student's disability, and that one or more students in a class may record class lectures, discussions, lab sessions, and review sessions and take pictures of essential information, and/or be provided class notes for personal study use only.

If you have questions, please contact the Office of the Dean of the Faculty of Arts and Sciences.

Accommodations

Students with disabilities who may need disability-related academic adjustments and services for this course should see me privately within the first week of class.

The remainder is standard text provided by Dartmouth [here].

Students requesting disability-related accommodations and services for this course are required to register with Student Accessibility Services (SAS; Getting Started with SAS webpage; student.accessibility.services@dartmouth.edu; 1-603-646-9900) and to request that an accommodation email be sent to me in advance of the need for an accommodation. Then, students should schedule a follow-up meeting with me to determine relevant details such as what role SAS or its Testing Center may play in accommodation implementation. This process works best for everyone when completed as early in the quarter as possible. If students have questions about whether they are eligible for accommodations or have concerns about the implementation of their accommodations, they should contact the SAS office. All inquiries and discussions will remain confidential.

Mental Health and Awareness

The following is standard text provided by Dartmouth [here].

The academic environment at Dartmouth is challenging, our terms are intensive, and classes are not the only demanding part of your life. There are a number of resources available to you on campus to support your wellness, including your undergraduate dean, Counseling and Human Development, and the Student Wellness Center. I encourage you to use these resources to take care of yourself throughout the term, and to come speak to me if you experience any difficulties.

Respect, Diversity, and Inclusion

I would like to create a learning environment for my students that supports a diversity of thoughts, perspectives and experiences, and honors your identities (including race, gender, class, sexuality, religion, ability, etc.). To help accomplish this:

If you have a name and/or set of pronouns that differ from those that appear in your official college records, please include them in DartHub or let me know privately.

If at any time you feel uncomfortable about the interactions in our classroom I encourage you to contact me privately so I can better understand how I can manage the course; indeed, I am eager for feedback about how I can maximize everyone’s experience. If you feel like your performance in the class is being impacted by your experiences outside of class, likewise, please don’t hesitate to contact me. I want to be a resource for you. If you prefer to speak with someone outside of the course, the contacts in the Mental Health and Wellness section above can be an excellent resource.

I (like many people) am constantly learning about diverse perspectives and identities. If something was said in class (by anyone) that made you feel uncomfortable, please talk to me about it.

As a participant in course discussions, you should also strive to honor and respect the diversity of your classmates.

Title IX

The following is standard text provided by Dartmouth [here].

At Dartmouth, we value integrity, responsibility, and respect for the rights and interests of others, all central to our Principles of Community. We are dedicated to establishing and maintaining a safe and inclusive campus where all have equal access to the educational and employment opportunities Dartmouth offers. We strive to promote an environment of sexual respect, safety, and well-being. In its policies and standards, Dartmouth demonstrates unequivocally that sexual assault, gender-based harassment, domestic violence, dating violence, and stalking are not tolerated in our community.

The Sexual Respect Website at Dartmouth provides a wealth of information on your rights with regard to sexual respect and resources that are available to all in our community.

Please note that, as a faculty member, I am obligated to share disclosures regarding conduct under Title IX with Dartmouth's Title IX Coordinator. Confidential resources are also available, and include licensed medical or counseling professionals (e.g., a licensed psychologist), staff members of organizations recognized as rape crisis centers under state law (such as WISE), and ordained clergy (see https://dartgo.org/titleix_resourcesLinks to an external site.).

Should you have any questions, please feel free to contact Dartmouth's Title IX Coordinator or the Deputy Title IX Coordinator for the Guarini School. Their contact information can be found on the sexual respect website.