Computer Vision

1
Computer Vision
2
Intelligent agents need to acquire knowledge of
their world through a set of sensors.
Computer vision is concerned with the theory and
technology for building artificial
systems that obtain information from images.
3
(No Transcript)
4
Applications
5

• Medical imaging
• Industry
• Defense
• Robotics
• Accessibility/Usability

6
Common Tasks
7

• Recognition one or several pre-specified or
  learned objects or object classes can be
  recognized.
• Identification an individual instance of an
  object is recognized.

8

• Detection the image data is scanned for a
  specific condition.
• Tracking following the movements of objects
  (e.g. vehicles or humans).

9

• Scene reconstruction computing a 3D model of a
  scene when given two or more images of that
  scene.
• Image restoration removal of noise (sensor
  noise, motion blur, etc.) from images.

10
State of the Art
11

• The field of computer vision can be characterized
  as immature and diverse.
• There exists an abundance of methods for solving
  various well-defined computer vision tasks, where
  the methods often are very task specific and
  seldom can be generalized over a wide range of
  applications.
• Many of the methods and applications are still in
  the state of basic research.