Introduction to Computer Vision
    CS4670, Fall 2010

Time: MWF 10:10am - 11:00am
Place: Hollister 306 (map)

Instructor: Noah Snavely (snavely@cs.cornell.edu)
    office: Upson 4157, (617) 255-4820
    office hours: Wednesdays 1:30-3pm

TAs: Kevin Matzen (kmatzen@cs.cornell.edu)
            office hours: Tuesday 4-5pm, Thursday 2-3pm, Upson 317
        Yin Lou (yinlou@cs.cornell.edu)
            office hours: Friday 3-4pm, Upson 4144

Newsgroup: cornell.class.cs4670


  Lectures Projects and class resources  


The goal of computer vision is to compute properties of the three-dimensional world from digital images. Problems in this field include reconstructing the 3D shape of an environment, determining how things are moving, and recognizing people and objects and their activities, all through analysis of images and videos.


The Nokia N900, a Linux-based camera phone with a 5-megapixel camera, focusable lens, WiFi, and touchscreen.
This course will provide an introduction to computer vision, with topics including image formation, feature detection, motion estimation, image mosaics, 3D shape reconstruction, and object and face detection and recognition. Applications of these techniques include building 3D maps, creating virtual characters, organizing photo and video databases, human computer interaction, video surveillance, and automatic vehicle navigation -- as well as new applications for mobile devices. This is a project-based course, in which you will implement several computer vision algorithms and do a final project on topic of your choice. The projects will center around computer vision on mobile devices. Nokia has generously provided us with a number of state-of-the-art Nokia N900 camera phones, which we will be using for course projects (including the final project).

Prerequisites
This course will be self-contained; students do not need to have computer vision background. This course will assume some familiarity with linear algebra. The programming assignments will be given in C++, so a familiarity with this language (or time and willingness to pick it up quickly) is essential.
Please send me email or speak to me if you are unsure of whether you can take the course.

Textbook
This course will have readings from Computer Vision: Algorithms and Applications (online), by Richard Szeliski.

Newsgroup
We'll be using newsgroup for discussion and announcement. The group name is cornell.class.cs4670. You can find instructions for setting up a newsgroup at http://www2.cit.cornell.edu/bearaccess/netnews/thunderbird/.


Thanks to Nokia and Nokia Research Center Palo Alto for their generous hardware support for this course.