This course will cover basis principles of image formation, basic image processing algorithms and different algorithms for estimating various quantities from single or multiple images (video). Apllications to vision-based control, 3D reconstruction, video analysis, surveillance and object recognition will be discussed.
Syllabus:
1. Representation of 3-D scenes : rigid
body motion, euclidean, affine and projective transformations.
2. Image formation: geometric and photometric
aspects of image formation process, binary, grey level and color images
3. Image features and Correspondence:
geometric and photometric features, feature detection and matching, optical
flow
4. Stereo - Two view geometry : camera pose
and 3D structure recovery from two views, camera calibration, 3-D reconstruction
6. Image Matching and Tracking : matching of
multiple views, tracking and video analysis
8. Grouping and Segmentation : detection and
recovery of multiple motions
9. Detection and Recognition of 0bjects in Images:
object representations and classification methods
10. Selected topics: vision based control, image
based rendering pipeline, vision for human computer intraction, recognition
Grading: Homeworks (about every 2 weeks) 40% Midterm:
30% Final project: 30%
Prerequisites: linear algebra, calculus
Lecture Materials: Lecture slides, lecture notes
Recommended Textbooks:
Computer Vision: Stockman and Shapiro, Prentice Hall.
Invitation to 3D Vision: From Images to Geometric Models: Y.
Ma, S. Soatto, J. Kosecka and S. Sastry (for part I of the course)
Introductory Techniques for 3D computer Vision. E. Trucco and A. Verri,
Prentice-Hall, 1998
Computer Vision: A Modern Approach: D. Forsythe and J. Ponce, Prentice-Hall,
2003
Required Software:
Matlab - the majority
of homeworks will require using Matlab. You can buy a student version in
Johnson center.