Computer Vision
Computer Vision
2020 – 21
Course Objectives:
To introduce students the fundamentals of image formation; To introduce students the major ideas,
methods, and techniques of computer vision and pattern recognition; To develop an appreciation for
various issues in the design of computer vision and object recognition systems; and To provide the student
with programming experience from implementing computer vision and object recognition applications.
Course Outcomes: After completing the course Student will be able to:
1. Identify basic concepts, terminology, theories, models and methods in the field of computer vision,
2. Describe known principles of feature detection and matching,
3. Describe basic methods of computer vision related to image stitching, photography like high
dynamic range imaging and blur removal.
4. Suggest a design of a computer vision system for a 3D Reconstruction, Albedos, image based
rendering views and depths.
UNIT I: Introduction: Image Formation: Geometric Primitives and Transformation, Photometric Image
Formation, Digital Camera, Image Processing: Point Operators, Linear Filtering, More Neighborhood
Operators, Fourier Transforms, Pyramids and Wavelets, Geometric Transformations, Global
Optimization.
UNIT II: Feature Detection and Matching: Points and Patches, Edges, Lines, Segmentation: Active
Contours, Split and Merge, Mean Shift and Mode Finding, Normalized Cuts, Feature-Based Alignment:
2D and 3D Feature-based Alignment, Pose Estimation, Geometric Intrinsic Calibration.
UNIT III: Structure and Motion: Triangular, Two-frame Structure from Motion, Factorization, Bundle
Adjustment, Constrained Structure and Motion, Dense Motion Estimation: Translation Alignment,
Parametric Motion, Spline-based Motion, Optical Flow, Layered motion
UNIT IV: Image Stitching: Motion Models, Global Alignment, Composing, Computational
Photography: Photometric Calibration, High Dynamic Range Imaging, Super-Resolution and Blur
Removal, image Matting and Compositing, Texture Analysis and Synthesis.
UNIT V: 3D Reconstruction: Shape From X, Active Range Finding, Surface Representation, Point-
based Representation, Volumetric Representation, Model-based Reconstruction, Recovering Texture
Maps and Albedos, Image- based Rendering: View Interpolation, Layered Depth Images, Light Fields and
Lumigraphs, Environment Mattes, Video-based Rendering.
Text Books:
1. Richard Szeliski, Computer Vision: Algorithms and Applications, Springer-Verlag London Limited,
2011.
2. Simon J.D Prince, Computer Vision: Models, Learning and Inference, 1 st Edition, 2012.
Reference Books:
1. Computer Vision - A modern approach, by D. Forsyth and J. Ponce, Prentice Hall Robot Vision, by B.
K. P. Horn, McGraw-Hill.
2. Haralick& Shapiro, “Computer and Robot Vision”, Vol II
3. G_erardMedioni and Sing Bing Kang “Emerging topics in computer vision”166