Spring 2008
Instructor:
B.S. Manjunath, manj at ece. Rm 3157, Engineering I. Tel: 805.893.7112
Office hours: Wednesday 1-2pm, Thursday 11am-12NOON or by appointment (or drop by and see if I'm available)
Pradeep Koulgi (PK) (pskoulgi AT umail.ucsb.edu)
Vignesh Jagadeesh (NV) (vignesh AT umail.ucsb.edu)
Office hours: Monday 2-4pm,Tuesday 9:30:10:30am, Wednesday 2-4 pm at the ECI Lab (HFH 1140 - walk through CSIL Lab. HFH 1138), Thursday 9:30-10:30am. Note the ECI Lab office hours; other meetings scheduled in the TA office (Phelps 1435).
Lecture: Tues/Thurs 8:00am - 915am, Building 387 Rm 101
Discussion sessions: Fri 9:00-9:50pm, Phelps 1425 or Fri 10:00-10:50am, Phelps 1425 NOTE THE ROOM CHANGE!!
Text Book: There is no required text book for this class. I will be distributing reading material and slides as needed, but expect the students to take good notes in class. .
Recommended (but not required) books:
1. Multiview Geometry, R. Hartley and A. Zisserman, Second Edition, Cambridge University Press (2003). The first part of the course will follow some of the material from this book.
2. Computer Vision: A Modern Approach, D. Forsyth and J. Ponce, Prentice Hall (2003). A good reference book.
Grading: Will be based on Homeworks/quiz (40%), Midterm (20%) and Final exam (40%). (note the increased weight to H/Ws than what was listed in the original slides, this reflects the increased weight to the programming assignments.)
Tuesday, May 20: Midterm examination (closed book/notes & no calculator or computer devices allowed)
June 12: 8-11am, Final exam (as per Spring schedule)
An introduction to the field of Computer Vision (also known as Machine Vision or Image Understanding or Computational Vision). The aim of computer vision is to make computers "see" by processing images and/or video. By knowing such things as how images are formed, information about the sensors (cameras), and information about the physical world, it is possible (at least in some cases) to infer information about the world from an image or set of images. For example, one may wish to know the color of an apple, the width of a printed circuit trace, the size of an obstacle in front of a robot on Mars, the identity of a person's face in a surveillance system, the motion of an object, the vegetation type of the ground below, or the location of tumor in an MRI scan - automatically, from images. Computer vision studies how such tasks can be done, and how they can be done robustly and efficiently. Originally seen as a sub-area of artificial intelligence, computer vision has been an active area of research for almost 40 years.
People come to computer vision from of a variety of motivations. Some want to better understand biological vision - how people and animals see, how the eye and the brain work together to enable sight. Others want to build robots that can perceive and react to the environment around them. Others are interested in multimedia databases, image compression, human-computer interaction, security and surveillance, medical imaging, and other areas. Whatever the motivation or application, there are several topics that are fundamental to work in computer vision and are important to almost any application.
- Image formation - geometry, radiometry, camera calibration
- Stereo and multiple views
- Shape from shading
- Edge detection and filtering
- Optical Flow and Motion processing
- Application to image registration, content based retrieval and image databases, and face recognition
Seminars
06/03/08 -Professor Ken Nakayama from Harvard University will give a talk on "Normal and Abnormal Face Processing in Humans". WHERE: Psychology Department's Spring Colloquium on Tuesday, June 3 at 3:30 pm. in the McCune Conference Room.
Introduction to Computer Vision
Final versionPost date Slides HomeWorks and Reading Comments/additional materials yes04/01/08 Lecture 1: Introduction HW #1 DUE APRIL 08, 2008. Homeworks due in the HW boxes on the fifth floor of Engineering I. Introduction to Multiple View Geometry This is Chapter 1, from Hartley & Zisserman, second edition. yes04/13/08 Lecture 2: Image Formation yes04/04/08 Discussion 1: Matlab MATLAB lecture notes Lecture notes on MATLAB, etc.
To download the .pdf of "MATLAB Primer" - Third Edition, by Kermit Sigmon follow this link. yes04/13/08 Lecture 3: Projective Geometry HW #2 DUE APRIL 18, 2008 (SOLUTIONS).
HW #3 DUE APRIL 24, 2008 (additional material) (SOLUTIONS).
yes04/16/08 Lecture 4: Camera Models 04/22/08 HW #4 DUE MAY 6, 2008 (additional material). yes04/30/08 Lecture 5: Stereo Epipolar geometry and Fundamental matrix READING: a Chapter from Hartley & Zisserman yes04/30/08 Lecture 6: More Stereo (final set) yes05/01/08 Lecture 7: Convolution and Correlation yes05/08/08 Lecture 8: Edge detection yes05/13/08 Solutions for Practice Midterm
Practice problems with solutions (for the midterm) and sample questions. yes05/15/08 - Eigenvalues and Eigenvectors
Read the paper: Eigenfaces for Recognition
See also, a review paper from 2002. Additional reading (some good notes from Prof Bebis).
HW #5 DUE JUNE 3, 2008 (additional material) yes Lecture 10: SIFT link to IJCV DavidLowe's paper yes 06/08/08 Lecture 11: Optic flow 06/01/08 06/03/08
Seminar: "Normal and Abnormal Face Processing in Humans"
Professor Ken Nakayama from Harvard University, Tuesday, June 3 at 3:30 pm. Psychology Department's in the McCune Conference Room
yes 06/08/08 Lecture 12: Shape from Shading
yesSample Final NEW! Homeworks
HW #1 DUE APRIL 08, 2008.
HW #2 DUE APRIL 18, 2008 (SOLUTIONS).
HW #3 DUE APRIL 24, 2008 (additional material) (SOLUTIONS).
HW #4 DUE MAY 6, 2008 FINAL VERSION (additional material).
Sample questions on Projective Geometry. (SOLUTION).
HW #5 DUE JUNE 3, 2008 (additional material)
Sample Question on SIFT Solutions
Sample Final NEW!