Computer Vision: From 3D Reconstruction to Recognition

Description

An introduction to the concepts and applications in computer vision, which include cameras and projection models, shape reconstruction from stereo, low-level image processing methods such as filtering and edge detection, mid-level vision topics such as segmentation and clustering, shape reconstruction from stereo, and high-level vision tasks such as object recognition, scene recognition, face detection and human motion categorization. 

Limited enrollment! Due to the popularity of this course, interested students should enroll as soon as possible.

Prerequisites

Linear algebra, basic probability and statistics.

Topics include

• Camera models and camera calibration
• Single view metrology and epipolar geometry
• Stereo systems and structure from motion
• Active and volumetric stereo
• Detectors and descriptors
• Image classification
• 3D object detection and 3D scene understanding

Course Availability

The course schedule is displayed for planning purposes – courses can be modified, changed, or cancelled. Course availability will be considered finalized on the first day of open enrollment. For quarterly enrollment dates, please refer to our graduate education section.