What is Computer Vision? | Introduction
First Principles of Computer Vision is a lecture series presented by Shree Nayar who is faculty in the Computer Science Department, School of Engineering and Applied Sciences, Columbia University. Computer Vision is the enterprise of building machines that “see.” This series focuses on the physical and mathematical underpinnings of vision and has been designed for students, practitioners, and enthusiasts who have no prior knowledge of computer vision.
What is Computer Vision? | Introduction
Introduction to Computer Vision
In this section, the speaker introduces computer vision and explains why it is important.
What is Computer Vision?
- Vision is our most powerful sense, and roughly 60% of the brain is involved in visual perception.
- Computer vision is the enterprise of building machines that can see.
- Reasons for building machines that emulate human vision include freeing up time from daily chores, making precise measurements, and surpassing human capability to extract information about the world.
Elements of a Computer Vision System
In this section, the speaker explains the basic elements of a computer vision system.
Basic Elements
- A three-dimensional scene lit by some form of lighting.
- The camera takes light from the three-dimensional scene to produce a two-dimensional image.
- The goal of vision software is to come up with a symbolic description of the scene.
- Sophisticated vision systems can tell you more detailed information about objects in the scene.
Definition of Computer Vision
In this section, different definitions for computer vision are discussed.
Different Definitions
- Vision is automating human visual processes or an information processing task.
- Vision can be thought of as inverting image formation or walking back into a three-dimensional world from a two-dimensional image.
- Vision can also be seen as the inverse of graphics.
Images and Pixels in Computer Vision
In this section, images and pixels are discussed in the context of computer vision.
Images and Pixels
- An image is an array of pixels, with each pixel recording information about a corresponding point in the scene.
- Pixels can provide brightness, color, depth, and material properties of points in the scene.
Introduction to Computer Vision
In this section, the speaker introduces computer vision and explains how it is challenging yet fun.
Computer Vision is Challenging Yet Fun
- Computer vision allows us to perceive things about a scene that are not visible to the naked eye.
- Images provide a three-dimensional structure of the scene, vegetation, time of day, weather and even mood in just a fraction of a second.
- Extracting information from digital images is challenging because it involves an array of numbers.
- Computer vision is multidisciplinary and draws on optics for imaging, signal processing as in electrical engineering, algorithms in computer science, neuroscience and psychology.
Progress Made in Computer Vision
- Considerable progress has been made in computer vision over the past 50 years.
- Successful applications have been developed using computer vision technology.
- The impact of computer vision on our lives will continue to grow over the coming decades.