Syllabus
Instructor: Ben Ochoa
Email: bochoa at ucsd.edu
Office hours: M 8:00 PM-9:00 PM (primary) and W 8:00 PM-9:00 PM (secondary), EBU3B 3234, and at other times by appointment
TA: Chandrakant Viraktamath
Email: cviraktamath at ucsd.edu
Office hours: Tu 11:00 AM-12:00 noon and Th 11:00 AM-12:00 noon, EBU3B B275, and at other times by appointment with instructor approval
Note: when emailing the instructor or TA with questions about the class, please put "CSE 252B" in the subject line.
Class section ID: 29303
Lecture: MW 5:00 PM-6:20 PM, WLH 2204
This course covers topics in imaging geometry using techniques from computer vision, photogrammetry, and projective geometry. These topics include methods for projecting a 3D scene to a 2D image, reconstructing a 3D scene from 2D images, and camera parameter estimation. Upon completion of this course, students will have an understanding of single and multiple view geometry, and the algorithms used in practice.
Prerequisites: Linear algebra, calculus, and probability and statistics. Python or other programming experience.
Assignments will be completed using a Jupyter Notebook with Markdown cells for text and math (images of handwritten text or math will not be accepted), and Code cells in Python.
Collaboration Policy: It is expected that you complete your academic assignments on your own and in your own words and code. The assignments have been developed by the instructor to facilitate your learning and to provide a method for fairly evaluating your knowledge and abilities (not the knowledge and abilities of others). So, to facilitate learning, you are authorized to discuss assignments with others; however, to ensure fair evaluations, you are not authorized to use the answers developed by another, copy the work completed by others in the past or present, or write your academic assignments in collaboration with another person.
Academic Integrity Policy: Integrity of scholarship is essential for an academic community. The University expects that both faculty and students will honor this principle and in so doing protect the validity of University intellectual work. For students, this means that all academic work will be done by the individual to whom it is assigned, without unauthorized aid of any kind. No student shall allow any academic work or academic credit to be completed or obtained, in part or in whole, for themselves by another (human or machine/artificial intelligence).
If the work you submit is determined to be other than your own, you will be reported to the Academic Integrity Office for violating UC San Diego's Policy on Integrity of Scholarship. In accordance with the CSE department academic integrity guidelines, students found committing an academic integrity violation will receive an F in the course.
Student Conduct Policy: UC San Diego strives to maintain a climate of fairness, cooperation, and professionalism. It is expected that you practice basic principles, including, but not limited to, mutual respect, civility, and decency, towards maintaining an atmosphere free of abusive or demeaning treatment. Non-academic student misconduct will be reported to the Center for Student Accountability, Growth, and Education for violating UC San Diego's Principles of Community.
Grading: There will be 5 homework assignments weighted with the following tentative percentages:
Assignment 1: 8.05%
Assignment 2: 12.64%
Assignment 3: 18.39%
Assignment 4: 25.29%
Assignment 5: 35.63%
The percent of each assignment is the number of points it is worth divided by the total number of points for all assignments. Later assignments build on earlier assignments, allowing reuse of code from previous assignments.
This course uses the standard grading scale:
| 96% ≤ | A+ | (4.0) | |
| 93% ≤ | A | (4.0) | < 96% |
| 90% ≤ | A- | (3.7) | < 93% |
| 86% ≤ | B+ | (3.3) | < 90% |
| 83% ≤ | B | (3.0) | < 86% |
| 80% ≤ | B- | (2.7) | < 83% |
| 76% ≤ | C+ | (2.3) | < 80% |
| 73% ≤ | C | (2.0) | < 76% |
| 70% ≤ | C- | (1.7) | < 73% |
| 60% ≤ | D | (1.0) | < 70% |
| F | (0.0) | < 60% |
Late Policy: Assignments will have a submission procedure described with the assignment. Assignments submitted late will receive a 15% grade reduction for each 12 hours late (i.e., 30% per day). Assignments will not be accepted 72 hours after the due date. If you require an extension (for personal reasons only) to a due date, you must request one as far in advance as possible. Extensions requested close to or after the due date will only be granted for clear emergencies or clearly unforeseeable circumstances. You are advised to begin working on assignments as soon as they are assigned.
Assignments:
- Assignment 1 and files (assigned Jan 7, due Jan 14)
- Assignment 2 and files (assigned Jan 21, due Feb 4)
- Assignment 3 and files (assigned Feb 4, due Feb 18)
- Assignment 4 and files (assigned Feb 18, due Mar 4)
- Assignment 5 and files (assigned Mar 4, due Mar 18)
Handouts/Readings:
- Good Features to Track (Shi and Tomasi) [pdf]
- A Fast Operator for Detection and Precise Location of Distinct Points, Corners and Centres of Circular Features (Förstner and Gülch) [pdf]
- EPnP: An Accurate O(n) Solution to the PnP Problem (Lepetit, Moreno-Noguer, and Fua) [pdf]
- Review and Analysis of Solutions of the Three Point Perspective Pose Estimation Problem (Haralick et al.) [pdf]
- Corrections to Finsterwalder's Solution [pdf]
- Polynomial Eigenvalue Solutions to the 5-pt and 6-pt Relative Pose Problems (Kukelova et al.) [pdf]
Lecture slides:
- Lecture 1 Introduction and overview (Jan 5)
- Lecture 2 Feature detection and matching (simple) (Jan 7)
- Lecture 3 Geometric primitives (Jan 12)
- Lecture 4 Geometric transformations, the projective camera, and projection and back-projection of geometric primitives (Jan 14)
- No lecture meeting (Jan 19)
- Lecture 5 Estimation of camera projection matrix, linear (Jan 21)
- Lecture 6 Estimation of camera projection matrix, nonlinear (Jan 26)
- Lecture 7 Estimation of camera pose, linear (Jan 28)
- Lecture 8 Estimation of camera pose, nonlinear (Feb 2)
- Lecture 9 Camera pose, minimum solution, and outlier rejection (Feb 4)
- Lecture 10 Two view geometry: camera rotation and imaging a plane (Feb 9)
- Lecture 11 Estimation of 2D projective transformation (Feb 11)
- No lecture meeting (Feb 16)
- Lecture 12 Estimation of fundamental matrix, linear (Feb 18)
- Lecture 13 Estimation of fundamental matrix, nonlinear (Feb 23)
- Lecture 14 Estimation of essential matrix, linear (Feb 25)
- Lecture 15 Estimation of essential matrix, nonlinear (Mar 2)
- Lecture 16 Three view geometry (Mar 4)
- Lecture 17 n view geometry (Mar 9)
- Lecture 18 Additional topics (Mar 11)
Lecture Topics (tentative):
- Background
- Feature detection and matching (simple)
- Geometric primitives (points, hyperplanes, hyperquadrics, and lines) (sections 2.2, 3.1, and 3.2)
- Geometric transformations (sections 2.3, 2.4, and 3.4)
- Single view geometry
- Projective camera (sections 6.1 and 6.2)
- Projection and back-projection of geometric primitives (sections 8.1, 8.2, and 8.3)
- Estimation of camera projection matrix (sections 7.1, 4.1, 4.4, 7.2, and 4.5)
- Estimation of camera pose (calibrated camera)
- Outlier rejection (section 4.7)
- Two view geometry
- Camera rotation, two views (section 8.4)
- Estimation of rotation matrix (calibrated camera)
- Imaging a plane (section 13.1)
- Estimation of 2D projective transformation (sections 4.1, 4.4, and 4.5)
- Camera rotation and translation, two views (sections 9.1 and 9.2)
- Estimation of fundamental matrix and two-view triangulation (sections 11.1, 12.4, 11.2, 11.3, 10.1, 9.5, 11.4, and 12.5)
- From projective to metric reconstruction (section 10.5)
- Estimation of essential matrix (calibrated camera) (section 9.6)
- Three view geometry (chapters 15 and 16)
- n view geometry
- Triangulation (sections 12.1, 12.2, and 12.3)
- Bundle adjustment and 2D block adjustment, sparse (section 18.1)
- Additional topics
- Configurations of geometric primitives
- Robust cost functions (section A6.8)
- Auto-calibration (sections 2.7, 8.5, 8.6, and 8.7, and chapter 19)
- Calibration, including lens distortion (sections 7.4 and 8.8)
Required textbook:
Multiple View Geometry in Computer Vision, 2nd edition
Richard Hartley and Andrew Zisserman
Cambridge University Press, 2004
[Cambridge University Press] [Amazon] [Google]
Diversity and Inclusion
We are committed to fostering a learning environment for this course that supports a diversity of thoughts, perspectives, and experiences while respecting your identities (including race, ethnicity, heritage, gender, sex, class, sexuality, religion, ability, age, educational background, etc.). Our goal is to create an inclusive learning environment where all students can feel comfortable and thrive. Accordingly, the instructional staff will make a concerted effort to be welcoming and inclusive to the wide range of students in this course. If there is some way we can help you feel more included, please let one of the course staff know (in person, via email/Piazza, or even using an anonymous note).
We also expect that you, as a student in this course, will honor and respect your classmates, abiding by the UC San Diego Principles of Community. Please understand that others' backgrounds, perspectives, and experiences may be different than your own, and help us build an environment where everyone is welcomed and respected.
If you experience any sort of harassment or discrimination, please contact an instructor as soon as possible. If you prefer to speak with someone outside of the course, please contact the Office for the Prevention of Harassment and Discrimination.
Students with Disabilities
We aim to create an environment in which all students can succeed. If you have a disability, please contact the Office for Students with Disabilities (OSD) and discuss appropriate accommodations as soon as possible. We will work to provide you with the accommodations you need, but you must first provide a current Authorization for Accommodation (AFA) letter issued by the OSD. You are required to present your AFA letters to the instructor and to the department's OSD Liaison so that accommodations may be arranged.
Basic Needs/Food Insecurities
If you are experiencing any insecurities related to basic needs (food, housing, financial resources), there are resources available on campus to help, including The Hub and the Triton Food Pantry. Please visit The Hub for more information.