Computer Vision with Embedded Machine Learning from Coursera

Computer vision (CV) is a fascinating field of study that attempts to automate the process of assigning meaning to digital images or videos. In other words, we are helping computers see and understand the world around us! A number of machine learning (ML) algorithms and techniques can be used to accomplish CV tasks, and as ML becomes faster and more efficient, we can deploy these techniques to embedded systems.

This course, offered by a partnership among Edge Impulse, OpenMV, Seeed Studio, and the TinyML Foundation, will give you an understanding of how deep learning with neural networks can be used to classify images and detect objects in images and videos. You will have the opportunity to deploy these machine learning models to embedded systems, which is known as embedded machine learning or TinyML.

Familiarity with the Python programming language and basic ML concepts (such as neural networks, training, inference, and evaluation) is advised to understand some topics as well as complete the projects. Some math (reading plots, arithmetic, algebra) is also required for quizzes and projects. If you have not done so already, taking the "Introduction to Embedded Machine Learning" course is recommended.

This course covers the concepts and vocabulary necessary to understand how convolutional neural networks (CNNs) operate, and it covers how to use them to classify images and detect objects. The hands-on projects will give you the opportunity to train your own CNNs and deploy them to a microcontroller and/or single board computer.

What's inside

Syllabus

Image Classification

In this module, we introduce the concept of computer vision and how it can be used to solve problems. We cover how digital images are created and stored on a computer. Next, we review neural networks and demonstrate how they can be used to classify simple images. Finally, we walk you through a project to train an image classifier and deploy it to an embedded system.

Convolutional Neural Networks

In this module, we go over the basics of convolutional neural networks (CNNs) and how they can be used to create a more robust image classification model. We look at the internal workings of CNNs (e.g. convolution and pooling) along with some visualization techniques used to see how CNNs make decisions. We introduce the concept of data augmentation to help provide more data to the training process. You will have the opportunity to train your own CNN and deploy it to an embedded system.

Object Detection

In this module, we will cover the basics of object detection and how it differs from image classification. We will go over the math involved to measure objection detection performance. After, we will introduce several popular object detection models and demonstrate the process required to train such a model in Edge Impulse. Finally, you will be asked to deploy an object detection model to an embedded system.

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Suitable for students with some knowledge of machine learning, Python programming language, and basic mathematics

Students are expected to have familiarity with the Python programming language and basic ML concepts (such as neural networks, training, inference, and evaluation) is advised to understand some topics as well as complete the projects

Teaches students how to deploy these machine learning models to embedded systems, which is known as embedded machine learning or TinyML

Exploration of image classification and object detection using convolutional neural networks (CNNs)

Offers hands-on projects for practical application of concepts

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Computer Vision with Embedded Machine Learning with these activities:

Review introductory Python concepts

Show steps

Brushing up on basic Python concepts will strengthen your foundation for this course.

Browse courses on Python Basics

Show steps

Identify mentors in the CV field

Show steps

Seek guidance from experienced professionals to accelerate your learning.

Browse courses on Computer Vision

Show steps

Attend conferences or meet-ups to network with CV professionals.
Reach out to individuals whose work you admire and request mentorship.

Practice implementing CNNs

Show steps

Reinforce your understanding of CNNs by implementing them from scratch.

Browse courses on Convolutional Neural Networks

Show steps

Choose a simple image classification dataset.
Divide the dataset into training and testing sets.
Implement a simple CNN model.
Train the model on the training set.
Evaluate the model's performance on the testing set.

Three other activities

Expand to see all activities and additional details

Show all six activities

Develop an image classification tool

Show steps

Apply your skills by creating a practical application that leverages image classification.

Browse courses on Image Classification

Show steps

Define the problem you want to solve.
Gather a suitable dataset.
Choose an appropriate machine learning model.
Train and evaluate the model.
Deploy the model to an embedded device.

Explore tutorials on advanced CNN architectures

Show steps

Expand your knowledge by studying advanced CNN architectures used in state-of-the-art applications.

Browse courses on ResNet

Show steps

Identify specific advanced CNN architectures you want to learn.
Search for reputable tutorials or online courses on those architectures.
Follow the tutorials, complete the exercises, and implement the architectures.

Initiate a research project on the latest CV techniques

Show steps

Stay at the forefront of CV by researching and implementing the latest advancements.

Browse courses on Computer Vision

Show steps

Identify a specific area of CV that interests you.
Conduct a literature review to gather relevant knowledge.
Design a research project to investigate your chosen area.
Implement your project and document your findings.

Career center

Learners who complete Computer Vision with Embedded Machine Learning will develop knowledge and skills that may be useful to these careers:

Computer Vision Engineer

Computer Vision Engineers develop and implement computer vision algorithms and models. This course is a perfect fit for aspiring Computer Vision Engineers because it provides a comprehensive overview of computer vision and its applications.

See salaries and explore the career path for Computer Vision Engineer

Machine Learning Engineer

Machine Learning Engineers work on developing machine learning algorithms and models, preparing data for analysis, and optimizing model performance. This course may be useful for aspiring Machine Learning Engineers because it provides a foundation in computer vision, a field that is increasingly being used in machine learning applications.

See salaries and explore the career path for Machine Learning Engineer

Data Scientist

Data Scientists use data to solve business problems. They collect, clean, and analyze data to identify trends and patterns. This course may be useful for aspiring Data Scientists because it provides a foundation in computer vision, a field that is increasingly being used in data science applications.

See salaries and explore the career path for Data Scientist

Software Engineer

Software Engineers design, develop, and maintain software applications. This course may be useful for aspiring Software Engineers because it provides a foundation in computer vision, a field that is increasingly being used in software development applications.

See salaries and explore the career path for Software Engineer

Robotics Engineer

Robotics Engineers design, develop, and maintain robots. This course may be useful for aspiring Robotics Engineers because it provides a foundation in computer vision, a field that is increasingly being used in robotics applications.

See salaries and explore the career path for Robotics Engineer

Deep Learning Engineer

Deep Learning Engineers design, develop, and maintain deep learning algorithms and models. This course may be useful for aspiring Deep Learning Engineers because it provides a foundation in computer vision, a field that is increasingly being used in deep learning applications.

See salaries and explore the career path for Deep Learning Engineer

Image Processing Engineer

Image Processing Engineers design, develop, and maintain image processing algorithms and models. This course may be useful for aspiring Image Processing Engineers because it provides a foundation in computer vision, a field that is closely related to image processing.

See salaries and explore the career path for Image Processing Engineer

Embedded Systems Engineer

Embedded Systems Engineers design, develop, and maintain embedded systems. This course may be useful for aspiring Embedded Systems Engineers because it provides a foundation in embedded machine learning, a field that is increasingly being used in embedded systems applications.

See salaries and explore the career path for Embedded Systems Engineer

Artificial Intelligence Engineer

Artificial Intelligence Engineers design, develop, and maintain artificial intelligence systems. This course may be useful for aspiring Artificial Intelligence Engineers because it provides a foundation in computer vision, a field that is increasingly being used in artificial intelligence applications.

See salaries and explore the career path for Artificial Intelligence Engineer

Business Intelligence Analyst

Business Intelligence Analysts use data to solve business problems. This course may be useful for aspiring Business Intelligence Analysts because it provides a foundation in computer vision, a field that is increasingly being used in business intelligence applications.

See salaries and explore the career path for Business Intelligence Analyst

Data Analyst

Data Analysts collect, clean, and analyze data to identify trends and patterns. This course may be useful for aspiring Data Analysts because it provides a foundation in computer vision, a field that is increasingly being used in data analysis applications.

See salaries and explore the career path for Data Analyst

Product Manager

Product Managers are responsible for the development and launch of new products. This course may be useful for aspiring Product Managers because it provides a foundation in computer vision, a field that is increasingly being used in product development.

See salaries and explore the career path for Product Manager

UX Designer

UX Designers design the user experience for websites and applications. This course may be useful for aspiring UX Designers because it provides a foundation in computer vision, a field that is increasingly being used in UX design.

See salaries and explore the career path for UX Designer

Technical Writer

Technical Writers create documentation for software and hardware products. This course may be useful for aspiring Technical Writers because it provides a foundation in computer vision, a field that is increasingly being used in technical writing.

See salaries and explore the career path for Technical Writer

Marketer

Marketers develop and execute marketing campaigns. This course may be useful for aspiring Marketers because it provides a foundation in computer vision, a field that is increasingly being used in marketing.

See salaries and explore the career path for Marketer