Instructor: James Tompkin
TAs: Aaron Gokaslan (HTA), Spencer Boyum, Harsh Chandra, Joshua Chipman, Qikun (Tim) Guo, Yue Guo, Yunshu Mao, Luke Murray, Eleanor Tursman, Vivek Ramanujan.
Waitlist | Schedule | General Course Policy
This course provides an introduction to computer vision, including fundamentals of image formation, camera imaging geometry, feature detection and matching, stereo, motion estimation and tracking, image classification, scene understanding, and deep learning with neural networks. We will develop basic methods for applications that include finding known models in images, depth recovery from stereo, camera calibration, image stabilization, automated alignment, tracking, boundary detection, and recognition. We will develop the intuitions and mathematics of the methods in class, and then learn about the difference between theory and practice in projects.
This course is based upon James Hays' computer vision course, previously taught at Brown as CS143, and currently taught at Georgia Tech as CS 4476. Significant thanks to him and his staff, across the years, for all their hard work.
No prior experience with computer vision is assumed, although previous knowledge of visual computing or signal processing will be helpful (e.g., CSCI 1230). The following skills are necessary for this class:
This class can be taken as a capstone. You will need to complete 10 points of extra credit in each of the projects.
There is no requirement to buy a textbook. The goal of the course is to be self contained, but sections from two textbooks will be suggested for more formalization and information. These two books are available free online. If you find a word or concept that you do not understand, then please also consider the computer vision dictionary listed third.
Projects are released every two weeks, with deliverables due each week at Friday at 9pm. Each project has two parts: written, and code. You have one week to complete the written part, and two weeks to complete the code part.
Hand-in for both parts is electronic via Gradescope. Instructions coming soon.
Projects 1, 2, 3 and 5 must be completed in MATLAB. Project 4 must be completed in TBD.
Project 6 will present a team challenge. More details to come.
|Projects||Instructions||Written Qs||Gradescope Hand in|
|0. MATLAB Primer||LaTeX||15th Sept. 9pm|
|1. Image Filtering and Hybrid Images||Webpage||LaTeX||Written: 15th Sept. 9pm; Code: 22nd Sept. 9pm|
|2. Local Feature Matching|
|3. Scene Recognition with Bag of Words|
|4. Convolutional Neural Nets|
|5. Camera Calibration and Fundamental Matrix Estimation|
|6. Group Project|
Your final grade will be 100% from 7 projects. All projects are graded. We leave ourselves a little flexibility to make minor adjustments. Say, if one project ends up being a little more difficult, then we can tweak that project to be less significant in your final grade.
You will lose 10% from each project for each day that it is late. However, you have three late days for the whole course: the first 24 hours after the due date and time counts as one late day, up to 48 hours counts as two, and 72 hours counts as three. This will not be reflected in the initial grade reports for your assignment, but they will be factored in and distributed at the end of the semester so that you get the most points possible. Late days cover unexpected clustering of due dates, travel commitments, interviews, hackathons, etc. Do not ask for extensions to due dates—we give you a pool of late days to manage yourself.
|Wed||06||Sep||Introduction to Computer Vision||PPTX | PDF||Szeliski 1||0 out|
|Image Formation and Filtering|
|Fri||08||Sep||Light and Color||PPTX | PDF||Szeliski 2.2, 2.3||1 out|
|Mon||11||Sep||Image Filtering||PPTX | PDF||Szeliski 3.2|
|Wed||13||Sep||Thinking in Frequency||PPTX | PDF||Szeliski 3.4|
|Fri||15||Sep||Thinking in Frequency, part 2||PPTX | PDF||Szeliski 3.5.2, 8.1.1||0 due; 1 written due|
|Feature Detection and Matching|
|Mon||18||Sep||Thinking in Frequency, part 3||PPTX | PDF||Szeliski 3.5.2, 8.1.1|
|Wed||20||Sep||Edge Detection||PPTX | PDF||Szeliski 4.2|
|Fri||22||Sep||Interest Points and Corners||Szeliski 4.1.2||1 code due, 2 out|
|Mon||25||Sep||Local Image Features and Feature Matching||Szeliski 4.1.3, 4.3.2|
|Machine Learning Crash Course|
|Wed||27||Sep||Machine Learning: Unsupervised Learning||Szeliski 5.3|
|Fri||29||Sep||Machine Learning: Supervised Learning||Szeliski 5.3||2 written due|
|Mon||02||Oct||Recognition Overview and Bag of Features||Szeliski 14|
|Wed||04||Oct||Large-scale Instance Recognition||Szeliski 14.3.2|
|Fri||06||Oct||Large-scale Category Recognition and Advanced Feature Encoding||2 code due; 3 out|
|Mon||09||Oct||No class—Indigenous Peoples' Day|
|Wed||11||Oct||Detection with Sliding Windows: Viola Jones||Szeliski 14.1 and 14.2|
|Fri||13||Oct||Detection with Sliding Windows: Dalal Triggs||Szeliski 14.1||3 written due|
|Mon||16||Oct||Pascal VOC and Big Data||Szeliski 14.5|
|Wed||18||Oct||Big Data 2|
|Fri||20||Oct||Project Explanation +
Time Warp Design Challenge
|3 code due|
|Mon||23||Oct||Neural Networks||Goodfellow 6|
|Wed||25||Oct||Neural Networks Part 2||Goodfellow 6|
|Fri||27||Oct||Convolutional Networks for Recognition||Goodfellow 9||4 out; form project teams|
|Mon||30||Oct||Neural Network Regularization||Goodfellow 7.1-7.5, 7.12|
|Wed||01||Nov||R-CNNs and FCNs|
|Fri||03||Nov||We Have To Go Deeper||4 written due|
|Wed||08||Nov||Social Good and Dataset Bias|
|Cameras, Multiple Views, and Motion|
|Fri||10||Nov||Model Fitting and RANSAC||Szeliski 6.1, 2.1||4 code due; project brief due; 5 out|
|Mon||13||Nov||Cameras and Optics||Szeliski 2.1, esp. 2.1.5|
|Wed||15||Nov||Stereo Introduction||Szeliski 11|
|Fri||17||Nov||Camera Calibration||Szeliski 6.2.1||5 written due; project start|
|Mon||20||Nov||No class—project work|
|Cameras, Multiple Views, and Motion Continued|
|Mon||27||Nov||Epipolar Geometry and Structure from Motion||Szeliski 7|
|Wed||29||Nov||Epipolar Geometry and Structure from Motion Continued||Szeliski 8.1 and 8.4|
|Fri||01||Dec||Stereo Disparity and Optical Flow||5 code due|
|Mon||04||Dec||Research paper class|
|Wed||06||Dec||Research paper class|
|Fri||08||Dec||Research paper class|
|Mon||11||Dec||Projects fast forward!|
Our intent is that this course provide a welcoming environment for all students who satisfy the prerequisites. Our TAs have undergone training in diversity and inclusion, and all members of the CS community, including faculty and staff, are expected to treat one another in a professional manner. If you feel you have not been treated in a professional manner by any of the course staff, please contact any of James (the instructor), Ugur Cetintemel (Dept. Chair), Tom Doeppner (Vice Chair) or Laura Dobler (diversity and inclusion staff member). We will take all complaints about unprofessional behavior seriously. Your suggestions are encouraged and appreciated. Please let James know of ways to improve the effectiveness of the course for you personally, or for other students or student groups. To access student support services and resources, and to learn more about diversity and inclusion in CS, please visit http://cs.brown.edu/about/diversity/resources/.
Prof. Krishnamurthi has good notes on this area.
This class runs quiet hours from 9pm to 9am every day. Please do not expect a response from us via any channel. Likewise, we won't ask you to do anything between these times, either, like hand in projects.
Feel free to talk to your friends about the concepts in the projects, and work through the ideas behind problems together, but be sure to always write your own code and perform your own write up. You are expected to implement the core components of each project on your own, but the extra credit opportunties often build on third party data sets or code. Feel free to include results built on other software, as long as you credit correctly in your handin and clearly demark your own work. In general, if you use an idea, text, or code from elsewhere, then cite it.
Brown-wide, academic dishonesty is not tolerated. This includes cheating, lying about course matters, plagiarism, or helping others commit a violation. Plagiarism includes reproducing the words of others without both the use of quotation marks and citation. Students are reminded of the obligations and expectations associated with the Brown Academic and Student Conduct Codes.
Brown University is committed to full inclusion of all students. Please inform me if you have a disability or other condition that might require accommodations or modification of any of these course procedures. You may email me, come to office hours, or speak with me after class, and your confidentiality is respected. We will do whatever we can to support accommodations recommended by SEAS. For more information contact Student and Employee Accessibility Services (SEAS) at 401-863-9588 or . Students in need of short-term academic advice or support can contact one of the deans in the Dean of the College office.
Being a student can be very stressful. If you feel you are under too much pressure or there are psychological issues that are keeping you from performing well at Brown, we encourage you to contact Brown's Counseling and Psychological Services. They provide confidential counseling and can provide notes supporting extensions on assignments for health reasons.
We expect everyone to complete the course on time. However, we certainly understand that there may be factors beyond your control, such as health problems and family crises, that prevent you from finishing the course on time. If you feel you cannot complete the course on time, please discuss with James Tompkin the possibility of being given a grade of Incomplete for the course and setting a schedule for completing the course in the upcoming year.
Laptops are discouraged, please, except for class-relevant activities, e.g., to help answer questions and show items relevant to discussion. No social media, email, etc., because it distracts not just you but other students as well. Read Shirky on this issue ("Why I Just Asked My Students to Put Their Laptops Away"), or Rockmore ("The Case for Banning Laptops in the Classroom").
We will release course lecture material online. In considering laptop use for note taking, please be aware that research has shown note taking on paper to be more efficient than on a laptop keyboard (Mueller and Oppenheimer), as it pushes you to summarize the content instead of transcribe it.
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.
Thanks to Tom Doeppner and Laura Dobler for the text on accommodation, mental health, and incomplete policy.
Thank you to the previous TAs who helped to teach and improve this class.