CS6320

This course is an introduction to the fundamental challenges in computer vision and the core concepts and techniques used to address them. Students begin by exploring image formation, gaining an understanding of how images are captured and processed. They will learn to transform images, extract visual features, and estimate camera pose, applying these concepts to tasks such as stereo matching and 3D reconstruction. Building on these foundations, the course delves into advanced algorithms and machine learning-based approaches, including an introduction to deep neural networks and their application to high-level vision tasks such as object detection, image segmentation, and activity recognition in videos.

Prerequisites: CS 3505 AND MATH 2270.

Fall and Spring