Intro to Computer Vision

Course Description

Fundamental mathematical understanding of computer vision in various forms. Image processing fundamentals, including image filtering, image pyramids, hough transform, corner detection, and feature detection and descriptors. Geometry-based vision, including 2D transformations, homography, geometric camera models, two-view geometry, and stereo. Video-based vision, including optical flow, alignment and tracking, and structure-from-motion. Physics-based vision, including radiometry and reflectance, photometric stereo, and computational photography. Lectures provide a mixture of real-world motivation examples, problem setups and mathematical derivations, and discussions on today’s state-of-the-art approaches. Students complete Python-based programming assignments. To study complex algorithms, students use AI tools to promote code simplicity, readability, better OpenCV and NumPy functionalities, real-time applications, and vectorization techniques. Prerequisite: CS 375 or equivalent. Expected to be offered once every academic year. 3 credits.

Code

CS 556

Credits

3

Subject

CS

Programs That Include This Course

• Master's Master of Science in Computer Science
• Professional Certificate Micro-Credential in Artificial Intelligence