Recent advances in algorithmic techniques, computation and memory technologies have reinvigorated interest in artificial intelligence (AI). Many of the successes in AI in last few years have come from its sub-area computer vision which deals with understanding, and extracting information from digital images and videos. This course provides an introduction to computer vision including fundamentals of image formation, camera imaging geometry, feature detection and matching, multiview geometry including stereo, motion estimation and tracking, and some machine learning problems such as image classification, object detection, and image segmentation. We focus less on the machine learning aspect of computer vision in this course, which will be really done in Advanced Computer Vision course (next semester). This course will be a pre-requisite for the advanced course.

The course will be conducted online during this semester. More details can be found at the following link: Microsoft Teams

• Digital Image Processing
  • Image Formation
  • Image Filtering
  • Edge Detection
  • Principal Component Analysis
  • Corner Detection
  • SIFT
  • Applications: Large Scale Image Search
• Geometric Techniques in Computer Vision
  • Image Tranformations
  • Camera Projections
  • Camera Calibration
  • Depth from Stereo
  • Two View Structure from Motion
  • Object Tracking
• Machine Learning for Computer Vision
  • Introduction to Machine Learning
  • Image Classification
  • Object Detection
  • Semantic Segmentation

Textbooks

• For the first part part we will mostly follow "Computer Vision: A Modern Approach", by Forsyth and Ponce
• For the second part we will mostly follow "Multiple View Geometry in Computer Vision", by Hartley and isserman
• There is no textbook for the third part and will be taught on the basis of recent research papers.

• As per courses of study
• Though we will cover a short introduction to machine learning, a student is expected to be familiar with machine learning techniques, through self-study as well.
• The course is expected to be assignment heavy, and a student may be required to install and work with multiple libraries, at times through public web services. Proficiency in programming and working with multiple external libraries would be desired.