CS308: COMPUTER VISION

Wishlist

Course Prerequisite(s)

About Course

The intent of this course is to familiarize the students to explain the fundamental concepts/issues of Computer Vision and Image Processing, and major approaches that address them. This course provides an introduction to computer vision including image acquisition and image formation models, radiometric models of image formation, image formation in the camera, image processing concepts, concept of feature extraction and selection for pattern classification/recognition, and advanced concepts like motion estimation and tracking, image classification, scene understanding, object classification and tracking, image fusion, and image registration, etc.

What Will You Learn?

  • Upon successful completion of this course, each student will be able to:
  • 1 List Goals of Computer Vision,
  • 2 Understand Image Formation Concepts
  • 3Explain Radiometry, Geometric Transformations, Geometric Camera Models
  • 4 Transform, Enhance, Filter, Segment and Process colour Images;
  • 5 Describe texture, identify colour features, Edges(Boundaries)
  • 6 Identify corner point detectors, Histogram of oriented Gradients, Scale Invariant Feature
  • Transform, Speed up Robust Features, Saliency
  • 7 Apply Artificial Neural Network for Pattern Classification, Convolutional Neural Networks,
  • and Autoencoders, Gesture Recognition, Motion Estimation and Object Tracking

Course Content

Introduction to Computer Vision and Basic Concepts of Image Formation
Introduction and Goals of Computer Vision

Fundamental Concepts of Image Formation-I
Image Formation and Radiometry Shape From Shading and Photometric

Fundamental Concepts of Image Formation-II
Geometric Transformations Geometric Camera Models

Fundamental Concepts of Image Formation-III
Image formation in a stereo vision setup

Image Processing Concepts
Fundamentals of Image Processing Image Transforms Image Filtering Colour Image Processing, Mathematical Morphology Image Segmentation

Image Descriptors and Features
Image Features and Edge Detection, Hough Transform Image Texture Analysism Interest or Corner Point Detectors, Histogram of Oriented Gradients, Scale Invariant Feature Transform, Speed up Robust Features, Saliency

Applications of Computer Vision-
Artificial Neural Network for Pattern Classification, Convolutional Neural Networks, Autoencoders

Fundamentals of Machine Learning
Gesture Recognition, Motion Estimation and Object Tracking,