Computer vision is the study of methods to extract content from digital images/video for applications such as recognizing people, navigating in an unfamiliar environment, image-based rendering, and retrieving images from a vast library. This class will examine all stages of computer vision from low-level to high-level. Low-level tasks include noise reduction and edge detection. In the middle, are estimating 3D properties of the scene, determining the camera motion from an image sequence, and segmentation of an image into coherent subsets. At the highest level, object recognition and scene interpretation are performed.