CMPE 264:   Image Analysis and Computer Vision Fall 2006

Description:

The topics covered by this course include digital image formation, image features and feature detection, structure from X, image segmentation, object recognition, motion analysis, and stereopsis. Students will also work in groups to solve some real world problems. Some potential project topics are automatic object recognition, human face detection, video surveillance, and content-based image retrieval.

Syllabus:

1.  Introduction

2.  Image and video acquisition

3.  Camera models

4.  Image features - edge, corners, lines, Hough Transform, deformable contours

5.  Camera calibration

6.  Camera motion estimation and 3D scene reconstruction

7.  Stereopsis

8.  2D motion analysis - optical flow estimation, differential techniques

9.  Shape from X - reflection model, shape from shading, shape from texture, shape from defocusing and focusing

10.  Tracking - Kalman filtering, correlation-based tracking, change-based tracking, 2D layer tracking, tracking of articulated objects

11.  Image segmentation

12.  Object recognition - Feature, invariants, subspace method, face detection and recognition

Reference:

Computer Vision -- A modern approach, by David Forsyth and Jean Ponce, Prentice Hall, 2002.

Time and Place:

TuTh   12:00 p.m. - 1:45 p.m., Soc Sci 1 rm 149

Instructor:

Hai Tao (http://www.soe.ucsc.edu/~tao/)
Email:   tao@soe.ucsc.edu
Office:  Engineering 2,  Room 333

Evaluation: Coursework will be weighted as follows:

 Homework   20%
 Mid-term   35%
 Project    45%

Homework: Homework will be collected every next week on Thursday at the end of the class.

Homework Assignments:

Lecture notes:

      Introduction,

     Image acquisition and camera model,

     An additional homework problem,

     Image noise and filtering,

     Image features: edges and corners,

     Hough transform: lines and curves,

     Model fitting and robust regression,

     Camera calibration,

     Epipolar geometry and the 8-point algorithm,

     Tomasi-Kanade factorization,

     Zhang's correspondence algorithm,

     Rectification and depth computation,

     Image motion analysis,

     Optical flow,

     Additional homework problems,

     Hidden Markov model (HMM),

     Object tracking and Kalman filtering,

     Object recognition - interpretation tree,

     Object recognition - appearance subspace,

     Image segmentation,

     Shape from shading (1),

     Shape from shading (2),

     Shape from texture,

     Deformable contours,

     Texture synthesis

Potential Project Topics:

·  3D reconstruction and camera motion analysis

·  Super resolution and image enhancement

·  Multiple view object tracking

·  Face detection and recognition

·  Facial motion analysis and event detection

·  Image and video search

·  Image-based rendering

·  Machine vision powered device and toys

·  Optical flow estimation

Computer vision links:

· CMU Computer Vision Home Page

· CVonline: Computer Vision Online Course Notes

· USC Annotated Computer Vision Bibliography

· PEIPA - the Pilot European Image Proecssing Archive

 

---

webmaster@cse.ucsc.edu

Back to the SOE Class Home Pages.
Back to the SOE Home Page.