This course focuses on studying methods that allow a machine to learn and analyze images and video using geometry and statistical learning. The growth of digital imaging technologies, hardware advances, and machine learning models has led to many exciting recent developments in image and video analytics. A variety of topics are covered in this course, including image enhancement, feature extraction, multi-view geometry, and deep learning methods for high-level visual problems such as image classification, segmentation, generation, and object detection. Applications of deep learning in computer vision for autonomous vehicles is also covered.
