CS780 - Computer Vision - Fall'2012

• This course introduces computational models of computer vision and their implementation on computers, and focuses on material that is fundamental and has a broad scope of application.  Topics include contemporary developments in all mainstream areas of computer vision e.g., Image Formation, Feature Detection/Representation, Classification and Recognition, Motion Analysis, Camera Calibration, 3D/Stereo Vision, Shape From X (motion, shading, texture, etc.), and typical applications such as Biometrics.
• Prerequisite: CS 610 – Data Structures and Algorithms

• D. Forsyth and J. Ponce, Computer Vision: A modern approach, 2nd edition, Prentice Hall, 2012.
• E. Trucco and A. Verri, Introductory Techniques for 3D Computer Vision, Prentice Hall, 1998.
• L.G. Shapiro and G.C. Stockman, Computer Vision, Prentice Hall, 2001.
• D. Marr, Vision: A Computational Investigation into the Human Representation and Processing of Visual Information, Freeman, San Francisco, 1982.
• Selected papers.

1. Introduction
• Computer Vision Fundamentals
• Related Fields: IP, PR, NN, ML, AI
• Image Fundamentals: Formats/Protocols
• Matlab and IP Toolbox
• OpenCV
  
2. Image Formation
• Basic Optics (Thin Lens)
  
• Basic Radiometry (Lambertian, Radiance vs. Irradiance)
  
• Camera Models (Perspective, Weak Perspective, Orthographic)
  
• Camera Parameters
  
3. Camera Calibration
• Intrinsic/Extrinsic Camera Parameters
• Explicit Parameter Calibration
• Projection Matrix-based Parameter Calibration
4. Geometric Image Features
   
• Linear Filters (Convolution, FFT, Noise Reduction)
  
• Edge Detection (Canny, Zero-crossing, LOG, Prewitt, etc.)
• Corner Detection
• Line & Curve Detection (Hough Transform),
• Ellipse Detection
5. Local and Color Image Features
• Local Binary Patterns (LBP)
• Scale Invariant Feature Transform (SIFT)
• Histograms of Oriented Gradient (HOG)
• Color models (RGB, HSV, YIQ, YCbCr, Lab, XYZ, etc)
6. Statistical Image Features
• Most Expressive Image Features (PCA)
• Sparse Image Features (Sparse Coding)
• Wavelet (Haar, Gabor) Features
  
7. Classification and Recognition Methods
• Bayes Classifier and the MAP Rule
• Linear Methods (LDA/FLD)
• Kernel Methods (SVM, kernel PCA, kernel FLD, etc.)
8. Motion Analysis - Structure From Motion
• Motion Field
• Optical Flow
• Tracking (Kalman Filtering, Particle Filtering)
• Structure From Motion
9. 3D Vision - Stereo Vision
• Correspondence
• Epipolar Geometry
  
• Essential and Fundamental matrices
• 3D Reconstruction
10. Shape From X and Computer Vision Applications
    
• Shape From Shading
• Shape From Texture
• Target Detection
  
• Object Recognition
  
• Image Search and Retrieval
  
11. Evolutionary Computation for Computer Vision
• Genetic Algorithms (GA)
• Evolutionary Strategy (ES)
• Evolutionary Programming (EP)
12. Neural Computation for Computer Vision
• Multilayer Perceptrons and BP Algorithm
• Radial-Basis Function Networks
13. Machine Learning  for Computer Vision
• Bayesian Learning
• Decision Tree
• Reinforcement Learning
14. Statistical Learning Theory (STL)
• Structural Risk Minimization (SRM)
• Support Vector Machines (SVM)

Project, presentation, and term paper (topics are related to our course Contents)

Class attendance

NJIT Honor Code will be upheld, and any violations will be brought to the immediate attention of the Dean of Students.

Students will be consulted with by the instructor and must agree to any modifications or deviations from the syllabus throughout the course of the semester.

• CVonline: The Evolving, Distributed, Non-Proprietary, On-Line Compendium of Computer Vision
• Vision Science: An Internet Resource for Research in Human and Animal Vision