1. Introduction

Question 1

What is CV?

Answer 1

Developing computational models and algorithms to
- interpret digital images
- understand the visual world we live in

Question 2

What are some of the use cases of CV?

Answer 2

• Face Detection (in images to focus)
• Human pose estimation (games)
• Google street view
• Photo search
• Character/object recognition/detection
• Special effects in movies
• ## Sport analysis (VAR)

Question 3

What is the Problem of Ambiguity in image Data?

Answer 3

• Our image data is not only too little to fully recover and understand the “state of the visible world”.
• It may even be of poor quality:
  
  • Low resolution
  • (Sensor) noise Etc.
    -> even if we have noiseless images, context and macro knowledge is needed to understand state of the world
    -> Our image data is always ambiguous.

Question 4

Why is CV is an inverse problem?

Answer 4

Compared to computer graphics, CV is an inverse problem. Computer graphics try to represent the 3D world into a 2D canvas (computer screen) while CV gets a 2D image and tries to interpret the context of the image and understand the meaning extract objects etc.

Question 5

How does a Pinhole Camera work? (idea)

Answer 5

put pinhole in front of film to block rays -> reduces blurring (size of opening = aperture)

Without the pinhole, there is no image since all rays go everywhere. Problem is that the image is upside down so we usually consider a virtual image (imaginary image on the other side of the pinhole, at the focal length just negative)

Question 6

What are two characteristics of the resulting image from a pinhole camera?

Answer 6

• resulting image is inverted
• digital representation of image is spatially discrete -> unlike real world
• image sensor performs sampling of continuous intensity function -> turns it into array of discrete intensity values (pixels)

Question 7

What are some projection properties of a pinhole camera (3D -> 2D) and what have we lost?

Answer 7

• what have we lost
  
  • angles
  • distances
• Many-to-one
  
  • all points along the same ray map to the same point in image
• Points → points
  
  • But projection of points on focal plane is undefined
• Lines → lines (collinearity is preserved)
  
  • But line through focal point projects to a point
• Planes → planes (or half-planes)
  
  • But plane through focal point projects to line
• Parallel lines converge at a vanishing point
• Spheres project to circles if the object is orthogonal to the image plane. Otherwise, it projects to an elipse

Question 8

What is a vanishing point?

Answer 8

When we have a pinhole camera, and there are some parallel lines in the world, they will project into lines onto an image plane, but they will not be parallel, but they will converge into some point called the vanishing point. But parallels also parallel to the image plane remain parallel

Question 9

Why some objects on the edge of an image might seem bigger?

Answer 9

Because of the image distortions. For example, the spheres will project to elipses and this causes the false observation. The rays come with the angle.