Computer vision deals with extracting a high-level description of the world around us, by inferring its geometry and semantics taking as input a snapshot from an acquisition device. Traditionally, this acquisition device has been a digital camera, and this input has been a picture or a series of pictures. Recently, the field has expanded into more types of input, including 3D data. This course aims to build a fundamental understanding of classic computer vision, starting at extracting semantics from image/s, moving to extracting geometry, and ending with higher-level tasks, including, semantic segmentation, recognition, detection, and tracking. An overview of recent developments in deep learning for computer vision will also be made.
- Teacher: Melinos Averkiou
- Teacher assistant: Marios Loizou