CMSC 426
Image Processing
(Computer Vision)
Instructor : Cornelia Fermueller, fer@cfar.umd.edu
Location and Time : Tu, Thu : 12:30 - 1:45 at CSI 3118
Office hours : Tu, Thu : 1:45 - 2:45 (AVW 4459)
Text : Introductory Techniques for 3-D Computer Vision, E. Trucco and A. Verri, Prentice Hall
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.
Lecture Notes
Lecture 1: Intoduction pdf
Lecture 2: Image formation 1 pdf ppt
Lecture 3: Image formation 2: Radiometry pdf ppt
Lecture 4: Linear algebra review and Introduction to Matlab Linear algebra tutorial (from PennState) Matlab script 1 Matlab script 2 (some image operations)
Lectures 5 and 6: Camera Calibration ppt Some linear algebra for solving equations ppt
Lecture 7: Filtering filter.ppt filter2.ppt
Lectures 8 and 9 and some of 10: Edge detection ppt Canny edge detection m-file
Lecture 10: Resampling ppt (Slides from Univ. of Washington)
Lecture 11: Image motion ppt
Lecture 12: Statistics on image features: Review of statistical concepts ppt Web site on illusions
Lecture 13: Stereopsis ppt
Lecture 14: Projective Geometry ppt (10 MB )
Lectures 15 and 18: Epipolar Geometry ppt (8 MB )
Lectures 19 and 20: Interpretation of image motion fields ppt
Lecture 21: 3D motion estimation from image derivatives ppt
Lecture 23: Shape from Shading pdf (from Daniel DeMenthon)
Lecture 24: Texture ppt (5.5 MB)
Lecture 25: Tracking with Kalman Filters pdf (from Daniel DeMenthon)
Homework
Homework 1 pdf Images: 1 2 3 4 5 data file: data1.mat
Homework 2 pdf Images: office-scene.zip Optical flow comparison paper (Barron et. al. 1994)
If you have an older version of matlab here are routines for reading ppm files.
Homework 3 pdf Stereo paper (Scharstein Szelisky)
Grading:
Midtem ( pdf ) 30%, Final 30 %, Homework 40 %
Useful Links:
Online resource of computer
vision topics: (contains short descriptions and tutorials on basic
and advanced topics)
http://www.dai.ed.ac.uk/CVonline/
Image Processing Learning
resources:
http://www.dai.ed.ac.uk/HIPR2/index.htm