CMSC
733
Computer Processing of Pictorial Information
Spring
2011
Instructor: Yiannis Aloimonos (yiannis@cs.umd.edu)
Lecture: M 4:00-6:30 - CSI
1121
Office Hours: M 2:00-4:00 (or by appointment) - AVW 4475
Teaching Assistant: Ching L Teo (cteo AT cs DOT umd DOT edu)
Office Hours: Thur 9:30-11:30 (or by appointment) - AVW 4470
Important Anouncements !
(Please, reload everytime
you check the announcements)
-
(Jan 24) Welcome to CMSC733
-
(Jan 25) Course Information updated
-
(Jan 26) Reading materials sent via email. If you did not receive it, contact TA or check your spam.
-
(Jan 30) Instructions on accessing MATLAB available at Additional Resources.
-
(Jan 31) Sample Matlab Code is now at Additional Resources.
-
(Jan 31) Use the discussion forum found at CMSC 733 Class Forums to post your questions concerning the class.
-
(Feb 1) Topic 1 lecture notes uploaded.
-
(Feb 7) HW 1 assigned. See Grading and Homework. Due Feb 14, 2011 4pm.
-
(Feb 11) HW grading policy updated. See Grading and Homework.
-
(Feb 19) Topic 2 lecture notes uploaded.
-
(Feb 22) HW 2 assigned. See Grading and Homework. Due March 1, 2011 4pm.
-
(Mar 14) Topic 3 lecture notes uploaded.
-
(Mar 21) HW 1 solutions available.
-
(Mar 28) Topic 4 lecture notes uploaded.
-
(Mar 28) HW 3 assigned. See Grading and Homework. Due April 4, 2011 4pm.
-
(Apr 2) Topic 5 lecture notes uploaded.
-
(Apr 27) Finals released. Sent via email. Due May 16, 2011 11:59pm.
-
(May 12) HW 2 solutions available.
-
(May 19) HW 3 solutions available.
Course Outline
In this class we will cover the following topics:
- 1. Multiple View Geometry:
- Image Formation, Geometric aspects, Radiometric Aspects, Digital Images, The Human Eye, Camera parameters, Camera Calibration, Intrinsic Parameters, Extrinsic Parameters, Stereo, The Correspondence Problem, Epipolar Geometry, 3D Reconstruction
-
- 2. Edge Detection:
- Gradient based edge Detectors, Laplacian, Parametric Models
-
- 3. Other Image Features:
- Hough Transform, Ellipse fitting, Deformable contours
-
- 4. Lightness and Color:
- Surface Reflectance, Recovering Lightness, The Physics of Color, Human Color Perception, Color Representations
-
- 5. Filters:
- Linear Filters and Convolution, Spatial Frequency and Fourier Transform, Sampling and Aliasing, Noise Reduction
-
- 6. Motion and video processing:
- The Image Motion Field, Estimation of 3D Motion and Structure, Segmentation on the basis of different Motion, Image Compression
-
- 7. Shape from Single Image Cues:
- Surface Descriptions, Shape from Contours, Shape from Shading, Shape from Texture.
-
- 8. Segmentation
-
Reading List
We will use a few resources. For the first part of the course, we will
use material that can be found in:
- Multiple View Geometry in Computer Vision, by Hartley and Zisserman
-
There will also be materials given in class or posted on the website.
Grading and Homework
Midterm: 20%, Final: 25%, Homework: 25%, Projects: 30%
Grades are maintained at CS Grades
Grading Policy for HW: Extra 10% credit for HW submitted by early deadline. Final deadline is 1 week after early deadline. 0% after final deadline.
- HW 01 [pdf]; Data for Question 2 [JPG]; Data for Question 3 [zip]; Supplementary reading material [pdf]
- HW 02 [pdf]; Calibration images [zip]; Early Deadline (March 1, 4pm).
Solution [pdf]
- HW 03 [pdf];Yosemite data for q9 [zip];Early Deadline (April 4, 4pm)
Solution part 1 [pdf]
Solution part 2 [pdf]
Lecture Notes
Lecture notes will appear as the semester goes on.
- Topic 1: Projective Geometry [ppt]
-
- Topic 2: Camera Calibration [pdf]; Some useful linear algebra [ppt]; Link to additional resources [link]
-
- Topic 3: Image Motion [ppt]; Additional notes [ppt]
-
- Topic 4: Texture & Shape from Shading [ppt] and [pdf]
-
- Topic 5: Filters [ppt]
-
Projects
TBA
Additional Resources
- MATLAB startup guide. [text]
-
- MATLAB sample code. [zip file]
-
Send questions and concerns to cteo AT cs DOT umd DOT edu
