Lecture 1 notes on Introduction to Computer Vision by Andreas Geiger

Introduction to Computer Vision

Computer Vision

  • The goal of computer vision is to convert light into meaning (geometric, semantic, …)

Computer Vision Applications

  • Robotics
  • Medical Applications
  • 3D Modeling
  • Driving
  • Mobile Devices
  • Accessibility

Computer Vision vs. Biological Vision

  • Over 50% of the processing in the human brain is dedicated to visual information.

  • Computer Vision is an ill-posed inverse problem

    • Many 3D scenes yield the same 2D image
    • Additional constraints required

Challenges in Computer Vision

  • Images are 2D projects of the 3D World
  • Viewpoint Variation
  • Deformation
  • Occulusion
  • Illumination
  • Motion
  • Perception vs Measurement
  • Local Ambiguities
  • Intra Class Variation
  • Number of Object Categories