Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

KCL computer vision > w1 gemini > Flashcards

w1 gemini Flashcards

1
Q

What are the aims of studying Computer Vision?

A

[Implicit in later slides: Understanding the world from images

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Why is Computer Vision difficult? (Give two reasons)

A

One image → many interpretations
One object -> many images

(Exponential growth of complexity of problem with each variable)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are the two main approaches to tackling Computer Vision problems?

A

Computational approach
Biological approach

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Define Computer Vision according to Trucco and Verri.

A

Computing properties of the 3D world from one or more digital images

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Define Computer Vision according to Stockman and Shapiro.

A

“To make useful decisions about real physical objects and scenes based on sensed images”

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Define Computer Vision according to Forsyth and Ponce.

A

“Extracting descriptions of the world from pictures or sequences of pictures”

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Explain the relationship between Image Processing and Computer Vision.

A

Image processing manipulates images

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Explain the relationship between Computer Graphics and Computer Vision.

A

Computer graphics creates images from descriptions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is Pattern Recognition in the context of computer vision?

A

Recognising and classifying stimuli in images and other datasets.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is Photogrammetry?

A

Obtaining measurements from images.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is Biological Vision?

A

Understanding visual perception in humans and animals (studied in Neuroscience

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Why is vision a worthwhile subject to study?

A

Vision is the main way we experience the world.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Give examples of applications of smile detection.

A

Cameras can be set to automatically take photos when a chosen subject laughs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Give examples of applications of face detection/recognition.

A

Detecting faces in images to allow users to tag people.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Give examples of biometrics applications of computer vision.

A

Iris Recognition

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Give examples of applications of people tracking.

A

Visual surveillance and crime detection (e.g.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Give examples of applications of object tracking.

A

Instant replay and analysis in sports.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Give examples of applications of advertising in Computer Vision.

A

Detecting the ground plane in video to introduce pictures onto it.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Give examples of applications of content-based image retrieval.

A

Searching for images based on their content (query by image content).

20
Q

Give examples of applications of reverse image search.

A

Finding similar images.

21
Q

Give examples of applications of driver assistance systems.

A

Lane departure warning
FSD
Cruise control

22
Q

Give examples of applications of computer vision in space exploration.

A

Panorama stitching

23
Q

Give examples of applications of computer vision in medical imaging.

A

Automatic measurement and analysis of non-visual images created in MRI

24
Q

Give examples of applications of creating 3D models from images.

A

Generating a 3D virtual (CAD) model of an object or building from photos.

25
Q

Summarize why computer vision is challenging.

A

Vision is difficult because the problem is ill-posed (one image can have many interpretations) and exponentially large (one object can generate many images).

26
Q

Why is the “One image → many interpretations” problem considered ill-posed?

A

Because mapping from the 2D image back to the 3D world is not unique; many possible 3D scenes could have generated the same image.

27
Q

How do we solve the “One image → many interpretations” problem?

A

Using constraints or priors which make some interpretations more likely than others.

28
Q

Why is the “One object → many images” problem considered exponentially large?

A

Because a single object can appear with many variations in location, size, rotation etc where each extra variable multiples the number of possible interpretations

29
Q

Explain the concept of vision being an ill-posed problem.

A

There is no unique solution

30
Q

Why is vision easy for us but difficult for computers?

A

A significant portion of the cerebral cortex (~50%) is devoted to vision

31
Q

Why is it difficult to appreciate how difficult computer vision is?

A

Because our own visual processing is effortless and intuitive.

32
Q

What does it mean that all previous examples of vision systems are limited to operating in a specific (small) domain?

A

They are designed for a specific task in a specific environment and do not generalize well.

33
Q

Why are solutions to computer vision problems often not robust?

A

Because code that works well for one task might fail for different or similar tasks

34
Q

Example of non-rigid deformations affect the appearance of an object.

A

Facial expressions
Movement of hand
Clothing?

35
Q

Explain within-category variation in appearance.

A

Objects belonging to the same category can still have significant variations in their visual appearance.

36
Q

Explain the concept of “Discrimination despite variation” in vision.

A

The ability to recognize subtle differences between similar objects and recognize very different-looking objects as belonging to the same category.

37
Q

How do other objects in the scene affect appearance?

A

Background clutter and occlusion can make it difficult to recognize individual objects.

38
Q

What are constraints (or priors) in the context of computer vision?

A

Pre-existing knowledge or assumptions about the world that help to disambiguate interpretations of an image.

39
Q

Why are constraints/priors necessary in computer vision?

A

To solve the challenges of one image having many interpretations and one object having many images.

40
Q

Give an example of how prior knowledge can affect our perception.

A

Being able to see a camouflaged object once its content is known.

41
Q

Give an example of how prior exposure can affect our perception.

A

Change blindness

42
Q

Give an example of how context can affect our perception.

A

The ambiguous “THE CAT” example where the middle letter is interpreted correctly based on the surrounding letters.

43
Q

Explain the significance of illusions in understanding vision.

A

Illusions reveal the assumptions the visual system is making to solve the under-constrained problem of vision.

44
Q

Explain the “Forward Engineering Approach” to tackling the problem of vision.

A

Determine requirements
Design system
Implement
Test
Refine
(As opposed to reverse engineering)

45
Q

What does computational (machine) vision focus on?

A

Implementing algorithms for perception.

46
Q

What does biological (human) vision focus on?

A

Modelling biological perception.

KCL computer vision (12 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2025 Bold Learning Solutions. Terms and Conditions