ESB-CAP 6415 Computer Vision (Spring 2008)

Prof. Sudeep Sarkar  (sarkar@csee.usf.edu)

Classes: Tues and Thurs, 9:30 am to 10:45 am, ENC 1002

Office Hours:  Tues and Thurs, 11 am to 12 noon or any other time with appointment.

Pre-Requisites for the course:  Digital Image Processing

Policies:

1.      Penalty for unethical activity is a FF and expulsion from the department

2.      You are expected to attend all classes

3.      There are no make ups for worksheets in any circumstances.

4.      If you miss an examination due to a valid, documented reason, considerations for a makeup or prorated grading might be considered. Please get in touch with Dr. Sarkar as soon as possible regarding this.

5.      Students who anticipate to be absent from class due to religious observance should inform Dr. Sarkar by email by second class meeting.

6.      You do not have the right to sell notes or tapes of lectures generated from this class. Click here for USF’s policy on Course Notes and Recording

Course Objectives:

 

*      You will develop awareness of key journals and conferences in the area.

*      Journals

*       IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)

*       Computer Vision and Image Understanding (CVIU)

*       IEEE Transactions on Image Processing

*       International Journal of Computer Vision (IJCV)

*       IEEE Transactions on Systems, Man, and Cybernetics – Part B (SMC)

*       Image and Vision Computing (IVC)

*       International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI)

*       Pattern Analysis and Applications (PAA)

*       Pattern Recognition (PR)

*      Conferences

*       International Conference on Computer Vision (ICCV)

*       International Conference on Computer Vision and Pattern Recognition (CVPR)

*       International Conference on Pattern Recognition (ICPR)

*       International Conference on Image Processing (ICIP)

*      You will learn to read, understand, critique, and present ideas presentation in published papers.

*      You will learn to communicate and hone your presentation skills.

 

Evaluation Criteria

*      Assignments, in-class work: 20%

*      Paper Report: 10%

*      Book Report: Presentation: 10%, Report 10%

*      Project: Presentations (Proposal: 10%, Final: 20%), Report 20%

*       

Books:

  1. Trucco and Verri: Introductory techniques for 3D computer vision
  2. Haralick and Shapiro, Computer and Robot Vision
  3. Marr: Vision
  4. Jain, Kasturi, and Schunck, Machine Vision
  5. Shapiro and Stockman, Computer Vision
  6. Nalwa, A guided tour of computer vision
  7. Horn: Robot vision
  8. Duda, Hart, and Stork: Pattern Classification
  9. Sonka, Hlavac, and Boyle: Image processing, analysis, and machine vision

Online Resources

*       

*      Computer Vision Fact and Fiction in Film (3D Vision)

*      Many links to application of vision and vision resources

*      Code to find straight line segments in images, based on edges

*      USC Annotated Bibliography

*      Computer Vision Online (Lecture Notes)

*      IEEE Explore

*      Google Scholar

*      Computer Vision World Page for Datasets, Code, etc…

*      Intel’s Open CV

*      Machine Vision Toolbox in Matlab (camera calibration, feature extraction, matching, segmentation)

*      Peter Kovesi’s Matlab fns for some vision problems

*      Code for  An Invitation to 3D Vision Y. Ma, S. Soatto, J. Kosecka, S. Sastry

*       Camera Calibration

*       Ramani’s Lecture Slides

*       List of Camera Calibration Codes

*       Tsai calibration software

*       MATLAB camera calibration code

*       2D-3D camera calibration (DLT method)

*       T. S. Huang and A. Netravali, “Motion and Structure from Feature Correspondences: A review,” Proceedings of the IEEE, vol. 82, no. 2, Feb, 1994.

*       Texture

*             Forsyth and Ponce Slides

*             Cornelia Fermueller (UMD) slides.

*       Segmentation and Grouping

*              Sarkar’s Perceptual Organization Talk.

*       Graph based methods

*       Minimal Spanning Trees, Connected Components, Cliques etc

·         Slides from Duda and Harts book

·         C. T. Zahn, “Graph Theoretical Methods for Detecting Gestalt Clusters,” July 1970

¨       Figure for the above paper are available HERE

·         S. Sarkar and K. Boyer, “A computational structure for preattentive perceptual organization: Graphical Enumeration and Voting Methods,” SMC, Feb, 1994.

*       Graph Spectral Methods:

·         Coherent clusters: S. Sarkar and K. Boyer, “Quantitative Measures of Change Based on Feature Organization: Eigenvalues and Eigenvectors,” CVIU, July 1998

·         Laplacian Cut: P. Soundararajan  and S. Sarkar, “ Supervised Learning of Large Perceptual Organization: Graph Spectral Partitioning and Learning Automata,” PAMI, May 2000

·         Normalized Laplacian Cut: J. Shi and J. Malik, “Normalized Cuts and Image Segmentation,” PAMI, Aug 2000

*       Histogram based methods

*       Expectation Maximization

*       The Berkeley Segmentation Dataset and Benchmark

*       Stereo

*       Java applets to visualize epipolar geometry

*       Stereo vision code of different approaches

*       Motion

*       T. S. Huang and A. Netravali, “Motion and Structure from Feature Correspondences: A review” Proceedings of the IEEE, vol. 82, no. 2, Feb, 1994.

*       Projective vision toolkit

*       Tracking

*       Introduction to Kalman filter

*      The Kalman Filter page

*      Gentle introduction to Kalman filter and tracking

 

 

Last revised: April 8, 2008