This Computer Vision course provides a strong theoretical and practical foundation in how machines understand and process visual information. The lectures begin with an introduction to the field of computer vision, including its history, major applications, and the evolution of visual AI systems.

Learners first study image formation concepts such as geometric transformations, camera models, and photometric image formation. The course explains how images are captured, processed, and represented digitally through the image sensing pipeline.

The course then explores the mathematical foundations behind visual perception and camera geometry. Topics include coordinate systems, transformations, and projection models used in computer vision systems.

A major section of the course focuses on Structure from Motion (SfM), which allows machines to reconstruct 3D scenes using multiple 2D images. Learners study two-frame structure from motion techniques, factorization methods, and 3D reconstruction principles used in robotics, augmented reality, autonomous vehicles, and 3D mapping systems.

Through detailed lectures and visual explanations, the course builds a deep understanding of modern computer vision algorithms and image processing techniques.

By the end of this course, learners will understand the core principles behind image formation, 3D scene understanding, and computer vision systems used in real-world AI applications.