Heads up! To view this whole video, sign in with your Courses account or enroll in your free 7-day trial. Sign In Enroll
Preview
Start a free Courses trial
to watch this video
In this video, you'll learn what Computer Vision is and how it originated.
This video doesn't have any notes.
Related Discussions
Have questions about this video? Start a discussion with the community and Treehouse staff.
Sign upRelated Discussions
Have questions about this video? Start a discussion with the community and Treehouse staff.
Sign up
[MUSIC]
0:00
Welcome to Introduction
to Computer Vision.
0:02
[MUSIC]
0:05
Join us as we explore this exciting
branch of AI, its applications, and
0:08
the fundamental concepts
that drive its development.
0:12
[MUSIC]
0:15
What is computer vision?
0:20
Computer vision, or CV,
0:23
is a subfield of artificial intelligence
that enables computers to understand and
0:24
interpret visual information, such as
those from digital images or videos.
0:29
Its goal is to replicate human vision
capabilities and to empower machines to
0:34
recognize objects, extract meaning, and
make decisions based on visual input.
0:39
In this course, you'll learn about
the origins of computer vision.
0:47
Look at how vision works in humans.
0:51
And in comparison learn
how it works in computers.
0:54
Then we'll deep dive
into some interesting and
0:58
perhaps surprising applications
of computer vision in use today.
1:01
Learning computer vision can open
up a world of opportunities for
1:05
computer programming professionals.
1:09
So, we'll wrap up this course with a look
at how you can start a learning path in
1:12
computer vision here at Treehouse.
1:16
We'll begin our journey with a look
at the origins of computer vision.
1:20
While many important scientists have
made significant contributions to our
1:27
understanding of computer vision.
1:31
One British neuroscientist,
1:33
David Marr, played a prominent role in
the early days of computer vision.
1:35
Marr was one of the most influential
figures in the field during the 1970s,
1:39
a visionary in his interdisciplinary
approach to understanding human vision.
1:44
Bridging the realms of cognitive science,
neuroscience, and computational theory,
1:48
David Marr's work focused on the detailed
mechanics of visual perception and
1:55
weaved together insights
from psychology and
2:00
neurophysiology along with
artificial intelligence.
2:02
The convergence of these insights
not only expanded the horizons of
2:07
each individual field, but also paved the
way for the emergence of computer vision,
2:10
setting the stage for the development
of algorithms that could imitate or
2:15
even improve human visual capabilities.
2:19
One of Marr's most influential
contributions was his multilevel theory of
2:24
vision.
2:28
He proposed that in order to fully
understand a complex system like
2:29
the visual system, it must be
analyzed at three distinct levels.
2:33
The computational level
describes what the system does.
2:37
In other words, the problems it solves.
2:41
The algorithmic level describes
how the system solves the problem.
2:44
For example, the algorithms it uses.
2:48
This level provides a detailed
blueprint of the operations and
2:51
data structures that a system
like the brain utilizes.
2:54
And the physical level refers to
the physical processes that carry out
2:58
the functions.
3:02
For the human brain, this means
the neurons, their connections, and
3:03
how they function.
3:07
Marr's framework emphasized understanding
both the underlying computations that
3:12
the brain performs and the algorithms and
3:16
representations it employs to
execute these computations.
3:19
This multi level approach has
been influential not just
3:23
in vision research but also in other areas
of cognitive science and neuroscience.
3:26
Since David Mars foundational
ideas provided a roadmap for
3:33
early researchers in the 70s, the field of
computer vision has evolved substantially.
3:36
The 1980s saw stereo vision developed as
a way to derive depth information from
3:42
stereo images.
3:47
In the 1990s,
scale invariant feature transform,
3:49
or SIFT, was a popular algorithm for
image matching and object recognition.
3:53
In 2001, the Viola-Jones face
detection algorithm emerged using
3:59
an algorithm that allowed rapid
computation of facial features.
4:04
Deep learning dominated the 2010s,
and Convolutional Neural Networks
4:08
designed to recognize patterns in images
became the backbone of most CV tasks.
4:13
In the 2020s, advancements in Edge AI
have focused on optimizing and
4:19
compressing advanced
computer vision models so
4:23
they can run directly on local
devices like smartphones.
4:26
[MUSIC]
4:29
The ongoing integration of AI and
4:31
CV has continued to shape
the trajectory of the field.
4:33
Today, computer vision
is a mature field that
4:37
enables computers to perform tasks nearly
unfathomable in David Marr's time.
4:40
[MUSIC]
4:45
As we'll learn in the next video, computer
vision has a wide range of practical
4:49
applications in healthcare, surveillance,
augmented reality, and more.
4:53
[MUSIC]
4:58
You need to sign up for Treehouse in order to download course files.
Sign upYou need to sign up for Treehouse in order to set up Workspace
Sign up