Instructor: Prof. Yiannis Aloimonos (yiannis [at] cs |dot| umd |dot| edu)
Lecture: TuTh 12:30pm - 1:45pm @ CSIC 1122
Office Hours: By appointment or before class @ AVW 4475
TA: Peratham Wiriyathammabhum (peratham [at] cs |dot| umd |dot| edu)
Office Hours: Tu 4:00pm-6:00pm @ AVW 4103 (or AVW 4470)
Piazza Link:
Acknowledgement: Special thanks to Dr. Cornelia Fermüller
for providing most of the lecture materials for this class!! (link)


Course Outline

In this class we will cover the following topics:
  1. Introduction:
    What is Computer Vision? Ongoing Research and Application Areas.
  2. Image Formation:
    Geometric aspects, Radiometric Aspects, Digital Images, The Human Eye, Camera parameters.
  3. Filters:
    Linar Filters and Convolution, Spatial Frequency and Fourier Transform, Sampling and Aliasing, Noise Reduction small.
  4. Edge Detection:
    Gradient based edge Detectors, Laplacian, Parametric Models.
  5. Other Image Features:
    Hough Transform, Ellipse fitting, Deformable contours.
  6. Lightness and Color:
    Surface Reflectance, Recovering Lightness, The Physics of Color, Human Color Perception, Color Representations.
  7. Camera Calibration :
    Intrinsic Parameters, Extrinsic Parameters.
  8. Multiple View Geometry:
    Stereo, The Correspondence Problem, Epipolar Geometry, 3D Reconstruction.
  9. Motion:
    The Image Motion Field, Estimation of 3D Motion and Structure, Segmentation on the basis of different Motion, Image Compression.
  10. Shape from Single Image Cues:
    Surface Descriptions, Shape from Contours, Shape from Shading, Shape from Texture.
There is no required text. We will distribute material from a variety of sources.
Grading Policy: There will be six assignments/projects in the class accounting for 60% of the grade. There will be a midterm and a final exam each accounting for 20% of the grade. Assignments handed in by the deadline will receive a 5% bonus.

Lecture Notes

Lecture 1 - Jan 28th: Correlation and Convolution [pdf]
Lecture 2 - Feb 2nd: Histogram Equalization [pdf]
Lecture 3 - Feb 4th: Image Formation 1 [pdf] [pdf] [ppt]
Lecture 4 - Feb 9th: Projective Geometry [ppt] (10 MB) 
Lecture 5 - Feb 11th: Linear Algebra Review [ppt]
Lecture 6 - Feb 16th: Camera Calibration [pdf]
Lecture 7 - Feb 18th: Filtering [ppt
Lecture 8 - Feb 23th: Edge detection [ppt
Lecture 9 - Feb 25th: Resampling [ppt] (Slides from Univ. of Washington) 
Lecture 10 - Mar 1st: Image motion [ppt
Lecture 11 - Mar 3rd: Statistics on image features: Review of statistical concepts [ppt] [Website on illusions
Lecture 12 - Mar 8th: Stereopsis [ppt
Lecture 13 - Mar 10th: Epipolar Geometry [ppt] (8 MB) 
Lecture 14 - Mar 15th: Spring Break   
Lecture 15 - Mar 17th: Spring Break   
Lecture 16 - Mar 22nd: Interpretation of image motion fields [ppt
Lecture 17 - Mar 24th: 3D motion estimation from image derivatives [ppt
Lecture 18 - Mar 29th: Midterm 
Lecture 19 - Mar 31st: Classification with SVMs and Deep Neural Networks  [piazza] (Many slides are from Univ. of Toronto) 
Lecture 20 - Apr 5th: Classification with SVMs and Deep Neural Networks (con't)   [MatConvNet Quick Demo
Lecture 21 - Apr 7th: Shape from Shading [pdf] (from Daniel DeMenthon)
Lecture 22 - Apr 12th: Texture [ppt] (5.5 MB)
Lecture 23 - Apr 14th: Tracking with Kalman Filters [pdf] (from Daniel DeMenthon)
Lecture 24 - Apr 19th: Homework Recitation 
Lecture 25 - Apr 21th: Perception for Robots 1 [pdf
Lecture 26 - Apr 26th: Vision & Language Integration with Cognitive Dialogue [pdf
Lecture 27 - Apr 28th: Active Perception [pdf
Lecture 28 - May 3rd: Finalize 
Lecture 29 - May 5th: Finalize 
Lecture 30 - May 10th: Final & Closing 


The midterm consists of two parts, "programming" and "pencil and paper" (as usual). Please find the skeleton code for the programming part here.


  • Homework 1 (Due Feb 25th): Projective Geometry and Histogram Equalization  [pdf
  • Homework 2 (Due Mar 22nd): Stereopsis and Epipolar Geometry  [pdf
  • Homework 3 (Due Apr 21nd): Background Subtraction  [pdf]  [data
  • Homework 4 (Due Apr 21nd): Texture Synthesis  [pdf
  • Homework 5 (Due May 10th): Bag of Visual Words  [pdf]   [skeleton code
  • Homework 6 (Due May 10th): Review for Final Exam  [pdf