About This Course

Computer vision is concerned with the image processing, geometry, and statistical inference tools necessary for extracting useful information about the world from two-dimensional images. After decades of research, machine vision systems have reached human-level performance in some areas, while other areas are still wide open. This course is an advanced survey of the state of the art in machine vision, focused primarily on applications to robot vision, intelligent video analytics, optical character recognition, and human-computer interfaces. The course is a mixture of lectures on fundamentals, student presentations of research from the primary academic literature, and group projects involving application of machine vision technology to real-world problems. The course prepares students to do thesis research in the field.

On completion of this course, you should be able to:

• Write computer programs to find point correspondences between different images of a 3D scene; Use noisy point correspondences between images to estimate projective transformations between planes, camera positions and orientations, and the 3D structure of a scene;
• Apply machine learning techniques for classification to problems involving segmentation, detection, and recognition of people and other objects in video sequences as well as optical character recognition;
• Apply sequential state estimation techniques to problems involving tracking of people and other objects in video sequences;
• Implement and evaluate state-of-the-art machine vision algorithms described in the primary academic literature;
• Integrate the necessary statistical estimation, image processing, and machine learning tools with a custom-designed algorithm to provide a complete solution to an image or video processing problem.