« View All Resources

CS6670 Computer Vision (Cornell Spring 2011)

Computer Vision Central - Posted on January 5, 2012 at 9:36 pm.

  • Links: http://www.cs.cornell.edu/courses/cs6670/2011sp/
  • Details:
  • 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.

    This course will provide an introduction to computer vision, including such topics as image formation, feature detection, motion estimation, image mosaics, 3D shape reconstruction, and object 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. This is a project-based course, in which you will implement several computer vision algorithms and do a final project on a research topic of your choice. 

    Lecture Dates

    TopicsMaterials
    01/24MIntroduction and Overview
    pptpdf

    Readings: Szeliski, Ch. 1

    21/26WImage Filtering
    pptpdf

    Readings: Szeliski, Ch. 3.1, 3.2

    31/31MImage Resampling
    pptpdf

    Readings: Szeliski, Ch. 3.4, 3.5

    3a1/31MFeature Detection
    pptpdf

    Readings: Szeliski, Ch. 4.1

    42/2WFeature matching
    pptpdf

    Readings: Szeliski, Ch. 4.1

    52/7MCameras and Projection
    pptpdf

    Readings: Szeliski, Ch. 2

    62/9WImage Warps and Projection
    pptpdf

    Readings: Szeliski, Ch. 3.5, 9.1

    72/14MPanoramas
    pptpdf

    Readings: Szeliski, Ch.6.1, Ch. 9

    8W2/16Image alignment and RANSAC
    pptpdf

    Readings: Szeliski, Ch.6.1

    9M2/21Single-View Modeling
    pptpdf

    Readings: Mundy, J.L. and Zisserman, A., Geometric Invariance in Computer Vision, Appendix: Projective Geometry for Machine Vision, MIT Press, Cambridge, MA, 1992, (read 23.1 - 23.5, 23.10). Online here.

    10W2/23Stereo
    pptpdf

    Readings: Szeliski, Ch. 11

    112/28MTwo-view geometry 
      
    pptpdf

    Readings: Szeliski, Ch. 7.2

    123/2WStructure from Motion 
      
    pptpdf

    Readings: Szeliski, Ch. 7.2, 7.4, Noah Snavely's thesis, Chapter 3

    13Multiview Stereo 
    pptpdf

    Readings: Szeliski, Ch. 11.6

    14Intro to Recognition
    pptpdf
    15Face Detection
    pptpdf

    Readings: Szeliski, Ch. 14.1, 14.2

    16Bag-of-words Models
    pptpdf

    Readings: Szeliski, Ch. 14.4

    17Pictorial Structures and Context
    pptpdf

    Readings: Szeliski, Ch. 14.4, 14.5

    18

    Context and Segmentation
     

    pptpdf

    Readings:

    19

    Graph Cuts

    pptpdf

    Readings:

    20

    Light and Reflectance

    pptpdf

    Readings: Szeliski, 2.2, 2.3.2

    21

    Photometric stereo

    pptpdf

    Readings: Szeliski 12.1

    22

    Computational photography 1 (HDR)

    pptpdf

    Readings: Szeliski Chapter 10.2

    23

    Computational photography 2

    pptpdf

    Readings: Szeliski Chapter 10

    24

    Recent work in recognition
     

    pptpdf

    Readings: Szeliski Chapter 14.5
    Kumar, et al., Attribute and Simile Classifiers for Face Verification

    25

    Multi-view stereo 2

    pptpdf

    26

    Vision for the Internet
     

    pptpdf

    k();} ?>