JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD

Course Outcomes

At the end of this course, students will be able to

• 1. Study the image formation models and feature extraction for computer vision
• 2. Identify the segmentation and motion detection and estimation techniques
• 3. Develop small applications and detect the objects in various applications

UNIT - I

Image Formation Models Monocular imaging system • Orthographic & Perspective Projection • Camera model and Camera calibration • Binocular imaging systems, Perspective, Binocular Stereopsis: Camera and Epipolar Geometry; Homography, Rectification, DLT, RANSAC, 3-D reconstruction framework; Auto-calibration. Apparel, Binocular Stereopsis: Camera and Epipolar Geometry; Homography, Rectification, DLT, RANSAC, 3-D reconstruction framework; Auto- calibration. Apparel, Stereo vision

UNIT - II

Feature Extraction: Image representations (continuous and discrete) • Edge detection, Edge linking, corner detection, texture, binary shape analysis, boundary pattern analysis, circle and ellipse detection, Light at Surfaces; Phong Model; Reflectance Map; Albedo estimation; Photometric Stereo; Use of Surface Smoothness Constraint; Shape from Texture, color, motion and edges.

UNIT - III

Shape Representation and Segmentation: Deformable curves and surfaces • Snakes and active contours Level set representations • Fourier and wavelet descriptors • Medial representations • Multi- resolution analysis, Region Growing, Edge Based approaches to segmentation, Graph-Cut, Mean- Shift, MRFs, Texture Segmentation

UNIT - IV

Motion Detection and Estimation • Regularization theory • Optical computation • Stereo Vision Motion estimation, Background Subtraction and Modelling, Optical Flow, KLT, Spatio- Temporal Analysis, Dynamic Stereo; Motion parameter estimation • Structure from motion, Motion Tracking in Video

UNIT - V

Object recognition • Hough transforms and other simple object recognition methods • Shape correspondence and shape matching • Principal component analysis • Shape priors for recognition

REFERENCES:

• 1. D. Forsyth and J. Ponce, “Computer Vision - A modern approach”, 2nd Edition, Pearson Prentice Hall, 2012
• 2. Szeliski, Richard, “Computer Vision: Algorithms and Applications”, 1st Edition, Springer- Verlag London Limited, 2011.
• 3. Richard Hartley and Andrew Zisserman, “Multiple View Geometry in Computer Vision”, 2nd Edition, Cambridge University Press, 2004.
• 4. K. Fukunaga, “Introduction to Statistical Pattern Recognition”,2ndEdition, Morgan Kaufmann, 1990. R19 M.Tech. Embedded Systems
• 5. Rafael C. Gonzalez and Richard E. Woods,” Digital Image Processing”, 3rd Edition, Prentice Hall, 2008.
• 6. B. K. P. Horn, “Robot Vision”, 1st Edition, McGraw-Hill, 1986.
• 7. E. R. Davies “Computer and Machine Vision: Theory, Algorithms, Practicalities”, 4th Edition, Elsevier Inc,2012. R19 M.Tech. Embedded Systems M.TECH.- I YEAR- I SEMESTER EMBEDDED SYSTEMS