Course

Unit I

Image Formation: Geometric image formation, Photometric image formation – Camera Models and Calibration: Camera Projection Models – Orthographic, Affine, Perspective, Projective models. Projective Geometry, Transformation of 2D and 3D, Internal Parameters, Feature Detection and Matching – points and patches, edges, lines, Feature-Based Alignment – 2D, 3D feature based alignment, pose estimation, Image Stitching, Dense motion estimation – Optical flow – layered motion, parametric motion, Structure from Motion.

Unit II

Local Feature Detectors and Descriptors: Hessian corner detector, Harris Corner Detector, LOG detector, DOG detector, SIFT, PCA-SIFT, GLOH, SURF, HOG, Pyramidal HOG, PHOW-Calibration Methods: Linear, Direct, Indirect and Multiplane methods – Pose Estimation.

Unit III

Stereo and Multi-view Geometry: Epi-polar Geometry, Rectification and Issues related to Stereo, General Stereo with E Matrix Estimation, Stratification for 2 Cameras, Extensions to Multiple Cameras, Self-Calibration with Multiple Cameras, 3D reconstruction of cameras and structures, Three View Geometry.

Learning Objectives

LO1: To understand the mathematical and physical principles of image formation and
projection geometry.

LO2: To apply feature detection, alignment, and motion estimation for image analysis.

LO3: To explore multi-view geometry and 3D reconstruction techniques from stereo vision.

LO4: To develop and evaluate algorithms for camera calibration, pose estimation, and visual
scene understanding.

Course Outcomes

CO1: Explain the principles of camera models, image formation, and projective geometry.

CO2: Implement and compare feature detection and matching algorithms for visual
correspondence.

CO3: Analyze motion in visual scenes using optical flow and structure-from-motion
techniques.

CO4: Apply stereo and multi-view geometry to perform 3D scene reconstruction.

CO5: Evaluate calibration methods and pose estimation algorithms for real-world computer
vision applications.

CO-PO Mapping

Textbook(s)

1. Forsyth and Ponce, ?Computer Vision – A Modern Approach?, Second Edition, Prentice Hall, 2011.
2. Richard Szeliski, ?Computer Vision: Algorithms and Applications?, Springer, 2011.

Reference(s)

1. Olivier Faugeras, Three-Dimensional Computer Vision, MIT Press, 1993.
2. Emanuele Trucco and Alessandro Verri, ?Introductory Techniques for 3-D Computer Vision?, Prentice Hall, 1998.