CS 512
Computer Vision (Fall 2018)

Course outline

What to expect from this course

Computer vision can be covered at different levels. The focus of this course is the understanding of algorithms and techniques used in computer vision. Students in the course are expected to write computer programs implementing different techniques taught in the course. The course requires mathematical background and some programming experience. This course does not intend to teach how to use a specific application software.

Objectives

1. Introduce the fundamental problems of computer vision.
2. Provide understanding of techniques, mathematical concepts and algorithms used in computer vision to facilitate further study in this area.
3. Provide pointers into the literature and exercise a project based on a literature search and one or more research papers.
4. Practice software implementation of different concepts and techniques covered in the course.
5. Utilize programming and scientific tools for relevant software implementation.

Overview

1. Introduction: overview of computer vision, related areas, and applications; overview of software tools; overview of course objectives.; introduction to OpenCV.
2. Image formation and representation: imaging geometry, radiometry, digitization, cameras and projections, rigid and affine transformations.
3. Filtering: convolution, smoothing, differencing, and scale space.
4. Feature detection: edge detection, corner detection, line and curve detection, active contours, SIFT and HOG descriptors, shape context descriptors.
5. Model fitting: Hough transform, line fitting, ellipse and conic sections fitting, algebraic and Euclidean distance measures.
6. Camera calibration: camera models; intrinsic and extrinsic parameters; radial lens distortion; direct parameter calibration; camera parameters from projection matrices; orthographic, weak perspective, affine, and perspective camera models.
7. Epipolar geometry: introduction to projective geometry; epipolar constraints; the essential and fundamental matrices; estimation of the essential/fundamental matrix.
8. Model reconstruction: reconstruction by triangulation; Euclidean reconstruction; affine and projective reconstruction.
9. Motion analysis: the motion field of rigid objects; motion parallax; optical flow, the image brightness constancy equation, affine flow; differential techniques; feature-based techniques; regularization and robust estimation; motion segmentation through EM.
10. Motion tracking: statistical filtering; iterated estimation; observability and linear systems; the Kalman filter; the extended Kalman filter
11. Object recognition and shape representation: alignment, appearance-based methods, invariants, image eigenspaces, data-based techniques.
12. Final presentation: students present selected topics and develop software implementation of related techniques based on the review of relevant literature. The work should be summarized in a concluding report which should include simulation results. A list of possible topics will be advertised prior to the project selection due date.

Grading

1. There is an additional mandatory assignment (assignment 0) which does not carry any credit. There is a penalty of 5% for not submitting this assignment. The best 5 assignment grades will be used for the combined assignment score.
   
2. A certain percentage of the students may be invited to discuss their assignments.
3. Late days: there is a total of 6 "free late days" with no grade penalty for all the assignments to cover various reasons such as not feeling well, being busy, etc. Up to 2 free late days may be applied to each assignment. Being late beyond what is allowed by the free late days will result in a grade reduction of 25% per day. Late days are counted past midnight when an assignment is due and include weekends and holidays. The final project can not be late and no submissions will be accepted beyond the last day of class.
4. Each member of this course bears responsibility for maintaining the highest standards of academic integrity. All breaches of academic integrity must be reported immediately. Copying of programs from any source (e.g. other students or the web) is considered to be a serious breach of academic integrity.
5. The usual grade scale applies: A  > 90, B > 80, C > 70, etc.

Books

1. Computer Vision: Algorithms and Applications, R. Szeliski, Springer, 2011.
2. Computer Vision: A Modern Approach, D. Forsyth and J. Ponce, Prentice Hall, 2nd ed., 2011.
3. Introductory techniques for 3D computer vision, E. Trucco and A. Verri, Prentice Hall, 1998.

Tentative schedule