CIS5800 is an introduction to the problems of computer vision and machine perception that can be solved using geometrical approaches rather than statistical methods, with emphasis on analytical and computational techniques. This course is designed to provide students with an exposure to fundamental mathematical and algorithmic techniques that are used to tackle challenging image-based modeling problems. The content of this course finds application in the fields of Artifical Intelligence and Robotics. Some of the topics that are covered are: Signal processing, projective geometry, camera calibration, image formation and transformations, computational stereopsis, and structure from motion. 

Prerequisites: No prior experience with computer vision is assumed, however the following skills are necessary for this class: Mathematics (Linear algebra, vector calculus, and probability), data structures (representing images as features and geometric constructions) and programming.

Discussion Forum

Ed Discussion

Textbook References:  

• Elements of Geometry for Computer Vision and Computer Grahics by Tomas Pajdla

• Multiple View Geometry in Computer Vision by Richard Hartley and Andrew Zisserman (optional)

Grading Policy (Tentative):

• Homework 1-4: 48% 

• Midterm (Mar 18): 20%

• Project 1-3: 32%

Late Policy: 5 total late HW days without penalty for the semester.

University of Pennsylvania's CIS department encourages collaboration among graduate students. However, it is important to recognize the distinction between collaboration and cheating, which is prohibited and carries serious consequences. Cheating may be defined as using or attempting to use unauthorized assistance, material, or study aids in academic work or examinations. Some examples of cheating are: collaborating on a take-home exam or homework unless explicitly allowed; copying homework; handing in someone else's work as your own; and plagiarism. Any student suspected of cheating will be reported to the Office of Student Conduct.