Computer Vision

This program requires a functional knowledge of linear algebra, calculus, probability, and statistics. Participants should be comfortable programming in Python. Programming assignments will present opportunities to implement computer vision algorithms using these technologies.

Get Your Brochure

Course Dates

STARTS ON

December 2, 2021

Course Duration

DURATION

10 weeks, online
5-10 hours per week

Course Duration

Dive Into the World of Computer Vision

With advances in machine learning (ML), the field of computer vision and its applications are growing by leaps and bounds, triggering transformations across industries and in daily life. Computer Vision is an online program offered by the Executive Education division of Carnegie Mellon University’s School of Computer Science. It enables software developers, ML engineers, and technology professionals to expand their knowledge with computer vision and image processing skills to become truly future-ready.

#1 in Artificial Intelligence Specialty and Graduate Programs for Computer Science.

Source: U.S. News & World Report

Key Takeaways

This is a 10-week online program designed to provide software developers, technology professionals, data scientists, data analysts, and ML professionals with an understanding of computer vision concepts, tools, and techniques. The program also explores real-world applications of this technology. In this program, you will:

  • Implement fundamental image processing methods and learn about various techniques used in them
  • Use neural networks to perform image recognition and classification
  • Extract 3D information from images and learn the basic principles of geometry-based vision
  • Align and track objects in a video

Program Modules

The program comprises 10 modules designed to help you leverage your Python skills and mathematical knowledge to gain deep insights into computer vision and image processing concepts.

Module 1:

Introduction to Computer Vision

The program begins by clearly defining the core concepts of computer vision and identifying real-world applications of this technology.

Module 2:

Image Processing

Explore the basic principles of image processing and learn the various techniques used for image filtering and decomposition.

Module 3:

Feature Detection and Matching

Feature detection is a cornerstone of computer vision. Explore essential feature-detection methods, and use them to build and train algorithms to detect corners and visualize quadratics in images.

Module 4:

Image Classification and Neural Networks

Leverage your experience in ML to create image representations with features using the Bag-of-Visual Words concept. Learn to use neural networks to classify images.

Module 5:

Convolutional Neural Networks (CNNs)

Learn about the structure and function of CNNs, using a deep CNN to recognize objects in an image.

Module 6:

Transformation and Homographies

Learn to apply 2D planar and linear transformations to given images, the process of performing automatic image warping, and explore basic augmented-reality simulations.

Module 7:

Camera Models

Learn the basics of geometric camera models and how to calibrate a camera.

Module 8:

Geometry-Based Vision

Discover the basic principles of geometry-based vision, learn to reconstruct 3D scene structures from 2D images, and perform robust 3D sensing using stereo.

Module 9:

Dealing With Motion

Study the applications of optical flow and track objects in a video.

Module 10:

Physics-Based Vision

Understand the function of physics-based vision in interpreting and extracting information from an image, and perform photometric stereo for rendering simple images.

Module 1:

Introduction to Computer Vision

The program begins by clearly defining the core concepts of computer vision and identifying real-world applications of this technology.

Module 6:

Transformation and Homographies

Learn to apply 2D planar and linear transformations to given images, the process of performing automatic image warping, and explore basic augmented-reality simulations.

Module 2:

Image Processing

Explore the basic principles of image processing and learn the various techniques used for image filtering and decomposition.

Module 7:

Camera Models

Learn the basics of geometric camera models and how to calibrate a camera.

Module 3:

Feature Detection and Matching

Feature detection is a cornerstone of computer vision. Explore essential feature-detection methods, and use them to build and train algorithms to detect corners and visualize quadratics in images.

Module 8:

Geometry-Based Vision

Discover the basic principles of geometry-based vision, learn to reconstruct 3D scene structures from 2D images, and perform robust 3D sensing using stereo.

Module 4:

Image Classification and Neural Networks

Leverage your experience in ML to create image representations with features using the Bag-of-Visual Words concept. Learn to use neural networks to classify images.

Module 9:

Dealing With Motion

Study the applications of optical flow and track objects in a video.

Module 5:

Convolutional Neural Networks (CNNs)

Learn about the structure and function of CNNs, using a deep CNN to recognize objects in an image.

Module 10:

Physics-Based Vision

Understand the function of physics-based vision in interpreting and extracting information from an image, and perform photometric stereo for rendering simple images.

Download Brochure

Program Experiences

Decorative image relating to important official documents

Office Hours With Learning Facilitators

Decorative image relating to a Computer Screen

Programming Assignments

Decorative image relating a Camera Recorder

Recorded Videos

Decorative image relating to a light bulb representing thinking in an instant

Knowledge Checks

Decorative image relating to an Organogram representing a Team illustration

Dedicated Program Support Team

Decorative image relating to a discussion between two people

Discussion Boards

Decorative image relating to Bit seized Learning

Bite-Sized Learning

Who Should Attend

This program is designed for participants who have programming experience in Python, and knowledge of multivariable calculus, linear algebra, probability, and statistics. The program is most suitable for:

Software developers/technology professionals who want to get a deep understanding of computer vision tools and advance their career with a certificate from a renowned school.

Representative roles include:

  • Software engineer
  • Software developer
  • Automation engineer
  • Tester design
  • Engineer
  • Full-stack developer
  • Tech lead

Data science/data analytics/machine learning (ML) professionals looking to improve their knowledge of computer vision technologies and their applications across industries.

Representative roles include:

  • Data scientist
  • ML engineer
  • AI application engineer
  • Data engineer
  • Senior data engineer
  • ML developer
  • ML research engineer
  • Data analyst

PREREQUISITES: This program requires a functional knowledge of linear algebra, calculus, probability, and statistics. Participants should be comfortable programming in Python. Programming assignments will present opportunities to implement computer vision algorithms using these technologies.

Faculty Members

Faculty Member Kris Kitani

Kris Kitani

Associate Research Professor, Robotics Institute, School of Computer Science Courtesy Professor, Electrical and Computer Engineering Department, Carnegie Mellon University

Kris Kitani works in the areas of computer vision, machine learning and human-computer interaction. His research interests lie at the intersection of first-person vision, human activity modeling, and inverse reinforcement learning... More info

Faculty Member Ioannis Gkioulekas

Ioannis Gkioulekas

Assistant Professor, Robotics Institute, Carnegie Mellon University

Ioannis Gkioulekas works on computational imaging — the process of forming images from measurements using algorithms that rely on a significant amount of computing. While imaging involves optics, sensors, and illumination, computation includes physics-based modeling and rendering, inverse algorithms, and learning... More info

Certificate

Example image of certificate that will be awarded after successful completion of this program

Certificate

Upon successful completion of the program, participants will receive a verified digital certificate of completion from Carnegie Mellon University’s School of Computer Science Executive Education.

Download Brochure

Your digital certificate will be issued in your legal name and emailed to you at no additional cost, upon completion of the program, per the stipulated requirements. All certificate images are for illustrative purposes only and may be subject to change at the discretion of Carnegie Mellon University’s School of Computer Science Executive Education.

Apply Now

Early registrations are encouraged. Seats fill up quickly!

Flexible payment options available. Learn more.