SluitenHelpPrint
Switch to English
Cursus: INFOMCV
INFOMCV
Computer vision
Cursus informatie
CursuscodeINFOMCV
Studiepunten (EC)7,5
Cursusdoelen
After completing the course, the student:
  • understands the motivation and goal of computer vision, including the applications and the general challenges.
  • knows the mechanisms of image formation in terms of both geometry and radiometry.
  • understands and is able to construct 3D voxel data from images or videos based on silhouettes.
  • understands and is able to use the 3D voxel data for tracking two persons and segmenting their body through the intersections of the back-projected 2D vertical reference lines.
  • understands the mathematical concept of Markov random fields (MRFs), and knows graphcuts for optimizing MRFs.
  • can use MRFs and graphcuts particularly in binary (two-class) segmentation and multi-class segmentation.
  • understands the concepts of image features (specifically SIFT) and its importance in computer vision, particularly in image matching and object recognition.
  • understands the challenges of image object recognition in computer vision, and is able to implement at least one algorithm of object recognition, such as the bags-of-features; as well as is able to use a classification technique such as AdaBoost.
  • understands the concept of the gradient-based image editing and an algorithm of digital image inpainting, as well as, is able to implement the inpainting algorithm.
  • understands and is able to use particle filters in visual tracking, including the mathematical reasoning behind the technique.
  • understands the concept of stereo and the feature-based 3D reconstruction in computer vision.
  • knows the basic concepts of physics-based computer vision.
Inhoud
As "seeing" the world with your eyes is important and beneficial, so is computer vision. The goal of computer vision is to make computers work like human visual perception, namely, to recognize and understand the world through visual information, such as, images or videos. Human visual perception, after millions of years of evolution, is extremely good in understanding and recognizing objects or scenes. To have similar abilities to human visual perception (or beyond), computer scientists have been attempting to develop algorithms by relying on various visual information, and this course is about those algorithms, particularly the practical side of them.
SluitenHelpPrint
Switch to English