Computer Vision

Davi Geiger

Graduate Division

Computer Science

Classes are schedule Thursdays 7:10 pm to 9:00 pm, at 719 Broadway, room 1221.

Mailing list link

Office Hours and Location: Monday 4:00 pm.

TA: Otavio Braga, e-mail: obraga at

Office Hours: Tuesdays at 4:00 pm. 719 Broadway, Room 1219

Books: None

Course Structure: theory and laboratory work. Groups of three students will work together in developing vision applications. We will use the microsoft Kinect as a plataform to acquire images, infrared depth maps, and skeletons.

See the following SDK
- Primesense SDK (windows, Linux, MacOs)
HowTo install on Linux:
- LibFreenect (no skeleton) for windows, Linux, MacOS

Projects will be developped in class and as homeworks. Evaluation is based on participation and project results.


1. Introduction to Computer Vision.
Lecture 1.pdf
A historical film about the beginning of computer vision MIT-1959

2. Format Images
There is a large library of computer vision algorithms including how to read and write image files at opencv

3. Camera Calibration.
Lecture 2.pdf

3. Image Measurements and Feature Detection
(Image pixels, oriented filters, derivatives)
Lecture 3.pdf

4. Image Segmentation and Graph Cut Method
(Lecture 4 is from Hiroshi Ishikawa, Ph.D. student at NYU and now professor in Japan, see his page
Lecture 4.pdf

This is a paper by Microsoft Cambridge Researchers with a more detailed development of Graph cut for Segmentation

5. The K-means and the Expectation Maximization methods.
Lecture 5.pdf

6. Symmetry and Skeletons
Lecture 6.pdf

A paper by Microsoft researchers on the kinect skeleton extraction

6. Tracking
Lecture 7.pdf

Condensation Algorithm home page


Homework 0: Due Thursday, September 29th

Homework 1: Due Thursday, October 13th

Homework 2: Due Tuesday, November 1st

Homework 3: Due Thursday, December 15th