Spring 2018

Course Description

This course provides a comprehensive introduction to computer vision. Major topics include image processing, detection and recognition, geometry-based vision, physics-based vision and video analysis. Students will learn basic concepts of computer vision as well as hands on experience to solve real-life vision problems. This course requires familarity with linear algebra and basic probability. Python will be used for all the assignments.

Computer Vision: Algorithms and Applications, by Richard Szeliski, Springer.

Tentative Schedule

 Image Processing 
Tue Jan 09Introduction 
Thu Jan 11Filtering 
Tue Jan 16Programming Tutorial 
Thu Jan 18Fourier Analysis 
Tue Jan 23Edge DetectionAssignment 1 Out
Thu Jan 25Hough Transforms 
Tue Jan 30Generalized Hough Transform 
Thu Feb 01Harris Corners 
Tue Feb 06Multi-Scale Detectors 
Thu Feb 08Feature DescriptorsAssignment 1 Due
Tue Feb 13Object Recognition 
Thu Feb 15Bag-of-WordsAssignment 2 Out
Tue Feb 20Classification 
Thu Feb 22Classification 
 Midterm Exam 
Tue Feb 27ReviewAssignment 3 Out
Thu Mar 01Mid-Term Exam 
Tue Mar 06Spring Break; No Class 
Thu Mar 08Spring Break; No Class 
 Image Transformations (2D) 
Tue Mar 132D TransformsAssignment 2 Due
Thu Mar 152D Alignment; RANSAC 
 Multi-View Geometry (3D) 
Tue Mar 20Pose Estimation and TriangulationAssignment 4 Out
Thu Mar 22Epipolar Geometry 
Tue Mar 27Essential and Fundamental MatrixAssignment 3 Due
Thu Mar 29Reconstruction, Stereo Vision 
Tue Apr 03Applications of N-view geometry 
 Video Analysis 
Thu Apr 05Optical FlowAssignment 5 Out
Tue Apr 10Image RegistrationAssignment 4 Due
Thu Apr 12Image Registration 
Tue Apr 17Tracking 
Thu Apr 19Tracking 
Tue Apr 24Temporal Inference 
Thu Apr 26Kalman FilteringAssignment 5 Due