18CSE390T

Computer Vision
U1 - S1 - SLO-1 - Introduction to Computer Vision
Introduction to Computer Vision (1/8)
• Computer vision is a field of artificial intelligence (AI)
• Enables computers and systems to derive meaningful information from
digital images, videos and other visual inputs
• Take actions or make recommendations based on that information
• Computer vision works much the same as human vision
• Advantages of Human vision over Computer Vision:
• lifetimes of context to train
• how to tell objects apart
• how far away they are
• whether they are moving and
• whether there is something wrong in an image.

2
Introduction to Computer Vision (2/8)
• Computer vision trains machines to perform the functions of a
Human Vision
• This has to be done it in much less time with cameras, data and
algorithms rather than retinas, optic nerves and a visual cortex.
• Because a system trained to inspect products or watch a production
asset can analyze thousands of products or processes a minute

3
Introduction to Computer Vision (3/8)
• Computer vision trains machines to perform the functions of a
Human Vision
• This has to be done it in much less time with cameras, data and
algorithms rather than retinas, optic nerves and a visual cortex
• Because a system trained to inspect products or watch a production
asset can analyze thousands of products or processes a minute
• Computer vision is used in industries ranging from energy and utilities
to manufacturing and automotive – and the market is continuing to
grow
• It is expected to reach USD 48.6 billion by 2022

4
Introduction to Computer Vision (4/8)
Why is vision so difficult?
• In part, it is because it is an inverse problem, in which we seek to
recover some unknowns given insufficient information to fully specify
the solution.
• We must therefore resort to physics-based and probabilistic models,
or machine learning from large sets of examples, to disambiguate
between potential solutions.
• However, modeling the visual world in all of its rich complexity is far
more difficult than, say, modeling the vocal tract that produces
spoken sounds.
5
Introduction to Computer Vision (5/8)
For Example:
a) The classic Müller-Lyer illusion,
where the lengths of the two
horizontal lines appear different
b) The “white” square B in the shadow
and the “black” square A in the light
actually have the same absolute
intensity value
c) A variation of the Hermann grid
illusion, gray spots appear at the
intersections
d) the operations of parallel
perception and integration
pathways in the brain
6
Introduction to Computer Vision (6/8)
Real-world industrial applications of Computer Vision
• Optical character recognition (OCR): reading handwritten postal codes on
letters and automatic number plate recognition (ANPR)
• Machine inspection: rapid parts inspection for quality assurance using
stereo vision with specialized illumination to measure tolerances on aircraft
wings or auto body parts
• Retail: object recognition for automated checkout lanes and fully
automated stores
• Warehouse logistics: autonomous package delivery and pallet-carrying
“drives” and parts picking by robotic manipulators
• Surveillance: monitoring for intruders, analyzing highway traffic and
monitoring pools for drowning victims
7
Introduction to Computer Vision (7/8)
Real-world industrial applications of Computer Vision
• Medical imaging: registering pre-operative and intra-operative imagery or
performing long-term studies of people’s brain morphology as they age
• Self-driving vehicles: capable of driving point-to-point between cities as
well as autonomous flight
• 3D model building (photogrammetry): fully automated construction of 3D
models from aerial and drone photographs
• Motion capture (mocap): using retro-reflective markers viewed from
multiple cameras or other vision-based techniques to capture actors for
computer animation
• Fingerprint recognition and biometrics: for automatic access
authentication as well as forensic applications.
8
Introduction to Computer Vision (8/8)
Real-world consumer applications of Computer Vision
• Stitching: turning overlapping photos into a single seamlessly stitched
panorama
• Exposure bracketing: merging multiple exposures taken under challenging
lighting conditions (strong sunlight and shadows) into a single perfectly
exposed image
• Morphing: turning a picture of one of your friends into another, using a
seamless morph transition
• 3D modeling: converting one or more snapshots into a 3D model of the
object or person you are photographing
• Face detection: for improved camera focusing as well as more relevant
image searching
• Visual authentication: automatically logging family members onto your
home computer as they sit down in front of the webcam 9
History of Computer Vision (1/6)

10
History of Computer Vision (2/6)

Techniques in 1970s:
a. line labeling
b. pictorial structures
c. articulated body model
d. Intrinsic images
e. stereo correspondence
f. optical flow

11
History of Computer Vision (3/6)

Techniques in 1980s:
a. pyramid blending
b. shape from shading
c. edge detection
d. physically based models
e. regularization-based
surface reconstruction
f. range data acquisition and
merging

12
History of Computer Vision (4/6)

Techniques in 1990s:
a. Factorization-based
structure from motion
b. dense stereo matching
c. multi-view reconstruction
d. face tracking
e. Image segmentation
f. face recognition

13
History of Computer Vision (5/6)

Techniques in 2000s:
a) image-based Rendering
b) image-based modeling
c) interactive tone mapping
d) texture synthesis
e) feature-based recognition
f) region-based recognition

14
History of Computer Vision (6/6)
Techniques in 2010s:
a) ‘SuperVision’ deep neural network
b) object instance segmentation
c) whole body, expression, and
gesture fitting from a single image
d) fusing multiple color depth images
using the ‘KinectFusion’ real-time
system
e) smartphone augmented reality
with real-time depth occlusion
effects
f) 3D map computed in real-time on a
fully autonomous Skydio R1 drone
15