We may earn an affiliate commission when you visit our partners.
Course image
Jianbo Shi, Kostas Daniilidis, and Dan Lee

How do robots “see”, respond to and learn from their interactions with the world around them? This is the fascinating field of visual intelligence and machine learning. Visual intelligence allows a robot to “sense” and “recognize” the surrounding environment. It also enables a robot to “learn” from the memory of past experiences by extracting patterns in visual signals.

Read more

How do robots “see”, respond to and learn from their interactions with the world around them? This is the fascinating field of visual intelligence and machine learning. Visual intelligence allows a robot to “sense” and “recognize” the surrounding environment. It also enables a robot to “learn” from the memory of past experiences by extracting patterns in visual signals.

You will understand how Machine Learning extracts statistically meaningful patterns in data that support classification, regression and clustering. Then by studying Computer Vision and Machine Learning together you will be able to build recognition algorithms that can learn from data and adapt to new environments.

By the end of this course, part of the Robotics MicroMasters program, you will be able to program vision capabilities for a robot such as robot localization as well as object recognition using machine learning.

Projects in this course will utilize MATLAB and OpenCV and will include real examples of video stabilization, recognition of 3D objects, coding a classifier for objects, building a perceptron, and designing a convolutional neural network (CNN) using one of the standard CNN frameworks.

What you'll learn

  • The fundamentals of image filtering and tracking, and how to apply those principles to face detection, mosaicking and stabilization
  • How to use geometric transformations to determine 3D poses from 2D images for augmented reality tasks and visual odometry for robot localization
  • How to recognize objects and the basics of visual learning and neural networks for the purpose of classification

Here's a deal for you

We found an offer that may be relevant to this course.
Save money when you learn. All coupon codes, vouchers, and discounts are applied automatically unless otherwise noted.

What's inside

Learning objectives

  • The fundamentals of image filtering and tracking, and how to apply those principles to face detection, mosaicking and stabilization
  • How to use geometric transformations to determine 3d poses from 2d images for augmented reality tasks and visual odometry for robot localization
  • How to recognize objects and the basics of visual learning and neural networks for the purpose of classification

Syllabus

Week 1: Camera Geometry and Color Sensing
Week 2: Fourier Transforms, Image Convolution, Edge DetectionWeek 3: Image Convolution and Edge Detection Part 2, Image PyramidsWeek 4: Feature Detection: Filters, SIFT, HOGWeek 5: Geometrical Transformation, Affine, Protective and RansacWeek 6: Optical Flow EstimationWeek 7: Image MorphingWeek 8: Image BlendingWeek 9: Image CarvingWeek 10: Probability and Statistics, Regression and ClassificationWeek 11: SVM and Object RecognitionWeek 12: Convolutional Neural Network

Good to know

Know what's good
, what to watch for
, and possible dealbreakers
This course provides a strong foundation for learners who seek to learn more about visual intelligence and machine learning
Taught by instructors who are recognized for their work in visual intelligence and machine learning
Covers the fundamental principles of image filtering, tracking, and geometric transformations
Introduces learners to object recognition, visual learning, and neural networks
Projects utilize MATLAB and OpenCV, providing practical experience in image processing

Save this course

Save Robotics: Vision Intelligence and Machine Learning to your list so you can find it easily later:
Save

Activities

Coming soon We're preparing activities for Robotics: Vision Intelligence and Machine Learning. These are activities you can do either before, during, or after a course.

Career center

Learners who complete Robotics: Vision Intelligence and Machine Learning will develop knowledge and skills that may be useful to these careers:
Robotics Engineer
Robotics Engineers use their understanding of robotics, vision intelligence, and machine learning to work with robots. Robots today perform many functions, as they are advancing quickly. The programming of these machines uses many different techniques, making this course a suitable choice for building upon existing robotics knowledge.
Computer Vision Engineer
Computer Vision Engineers use computer software and applications to give computers the ability to see and interpret images, such as photographs. As they are based on machine learning, the techniques taught in this course are directly applicable to this work and would provide an excellent foundation for getting into this field.
Machine Learning Engineer
Machine Learning Engineers use their understanding of machine learning algorithms and techniques to help computers learn from data without being explicitly programmed. By completing this course, you will gain the understanding and tools necessary for this work.
Artificial Intelligence Engineer
Artificial Intelligence Engineers research, design, develop, and test software and systems that are based on artificial intelligence. By understanding how to use machine learning with computer vision, you will gain a more well-rounded background for work in this field.
Data Scientist
Data Scientists use their knowledge of data analysis and machine learning to extract insights from data. The statistical and probabilistic learning techniques you will learn in this course will be useful for getting into the field of data science.
Software Engineer
Software Engineers design, develop, test, and maintain software systems. As many software systems use artificial intelligence and machine learning, this course will give you the tools you need to work with these techniques in your software engineering work.
Product Manager
Product Managers are responsible for the overall success of a product. As more products leverage machine learning and image recognition, it is helpful for Product Managers to have an understanding of these technologies. This course will help you build that foundational understanding.
Business Analyst
Business Analysts use their understanding of business processes to help organizations improve their performance. With the growing need for organizations to leverage machine learning to improve operations, taking this course will give you a leg up on the competition.
Project Manager
Project Managers plan, execute, and close projects. As machine learning and image recognition become more common in project work, those with an understanding of these technologies are likely to succeed.
Sales Engineer
Sales Engineers use their technical expertise to help customers understand and purchase products and services. As machine learning and image recognition are being used in more and more products, having a foundational understanding of these technologies will help you be successful as a Sales Engineer.
Technical Writer
Technical Writers create documentation for software and hardware products. This course will help you build a solid foundation in machine learning and image recognition, which will make you an ideal candidate for jobs creating content for these technologies.
Quality Assurance Analyst
Quality Assurance Analysts test software and hardware products to ensure they meet quality standards. With the increasing use of machine learning and image recognition in products, understanding these technologies will be helpful for finding and fixing defects.
System Administrator
System Administrators maintain and troubleshoot computer systems. As machine learning and image recognition are increasingly being used in computer systems, gaining a background in these technologies will be helpful for you.
Database Administrator
Database Administrators maintain and troubleshoot databases. As machine learning and image recognition become more common, these technologies are being used with databases more often. This course will give you the background you need to be successful as a Database Administrator.
Network Administrator
Network Administrators maintain and troubleshoot computer networks. As machine learning and image recognition become more common, these technologies are being used with networks more often. Taking this course will give you the background you need to excel as a Network Administrator.

Reading list

We haven't picked any books for this reading list yet.

Share

Help others find this course page by sharing it with your friends and followers:

Similar courses

Similar courses are unavailable at this time. Please try again later.
Our mission

OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.

Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.

Find this site helpful? Tell a friend about us.

Affiliate disclosure

We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.

Your purchases help us maintain our catalog and keep our servers humming without ads.

Thank you for supporting OpenCourser.

© 2016 - 2024 OpenCourser