This course may be taken individually or as part of the Professional Certificate Program in Machine Learning & Artificial Intelligence.
In this course participants will learn the latest trends and newest technologies to develop an imaging and machine learning strategy that will create competitive advantage through devices, visual data mining and domain-specific techniques. Advances in Imaging and Machine Learning surveys the landscape of imaging hardware, optics, sensors, and computational techniques through a mix of theory, hands-on open-ended exercises (rapid prototyping), several participatory discussions and practical applications. You will learn about and observe high-end imaging devices and explore computer vision using installed cameras, connected cameras in the cloud, and OpenCV on mobile platforms. Focus areas include digital health and medical imaging, self-driving cars and AR/ VR where we explore current approaches and potential disruptions to the fields including review of hardware, sensor technology, imaging devices, and algorithms. In addition, we will discuss solutions and applications that are opening up new research and commercial opportunities, including smart phones, robotics, smart cities, agriculture, satellite and geo-spatial imaging and in emerging worlds.
Group discussions will let participants share their industry or academic experiences on what imaging technology trends. As a group, at the end of each day, we will try to predict the evolution of imaging technology on 5 and 10+ year timeframes. You will tour the Media Lab and learn about its research, its philosophy, and how it works through demos, case studies, and discussions with the members of the Camera Culture Group, as well as Boston-area startups and innovators. All members get a special invite for a Boston meet-up of Imaging and AI startups on the 3rd day evening.
“Most creative work is a process of people passing ideas and inspirations from the past into the future and adding their own creativity along the way.” -Joichi Ito, Director, MIT Media Lab
- Understanding the basics of a variety of computational imaging and visual mining techniques, both those used in industry today and cutting-edge techniques from the laboratory
- Observing demonstrations of various imaging hardware and visual analysis software
- Learning new methods for overcoming the traditional constraints in imaging using machine learning, optics, sensors, and computer vision
- Understanding of current self-driving car technologies and potential disruptions
- Exploring new emerging solutions that are opening up new research and commercial opportunities in current and future applications
- Participating in small group discussions about the future of imaging, including future products, services, and societal impact
- Meeting and networking with the Boston-area imaging community via tours and social events planned each evening
Who Should Attend
The course is suitable for decision-makers and planners for the next generation of imaging solutions, engineers and designers of imaging systems, and anyone interested in reviewing existing and emerging solutions in machine learning, optics, sensors, image analysis, and computer vision. Application areas include consumer photography (including mobile phones), industrial machine vision, and scientific and medical imaging.
Background: There are no pre-requisites but a general knowledge of technologies that involve image processing, optics, and sensors is a plus.
Laptops are required for this course.
Class runs 9:30 am - 5:00 pm each day.
There will be a reception and dinner for faculty and participants on Monday evening. On Tuesday evening, there will be a networking event with the Boston-area imaging community.
Day 1 – Advances in Imaging
- 9:30 - 10:00am - Intro to Advances in Imaging and fast forward
- 10:00am - 12:30pm - Infrared, thermal imaging, millimeter wave, terahertz, thermal cameras, multi-spectral, highspeed cameras, and 3D range-sensing time-of-flight cameras and camera arrays, visual analysis and scene understanding
- 12:30 - 1:30pm - Lunch on your own
- 1:30 - 3:00pm - Overview of computational imaging for self-driving car industry LIDAR, RADAR and sensors
- 3:00 - 4:00pm - Landscape of current AR-VR challenges Explore current technologies: Oculus Rift, Meta, Hololens Computer Vision for Augmented Reality and Gestural Interactions
- 4:00 - 5:00pm - Landscape Medical imaging, Diagnostics, Optics and sensors for health, CT, MRI, visualization and predictive analytics
- 5:00 - 7:00pm - Group Dinner with members of the Camera Culture group and alums
Day 2 – AI and Machine Learning: Deep Dive
- 9:30 - 11am - Introduction to machine learning, clustering and classification, introduction to compressive sensing and sparse representations, internet vision and online photo collections
- 11am - 1:00pm - Hands-on Activity: Dive into DNN
- 1:00 - 2:00pm - Lunch at the MIT Media Lab
- 2:00 - 3:15pm - Computer Vision: Low-level image features, and analysis; mid-level and high level, shape recovery, object recognition, and new applications for CV using machine learning
- 3:15 - 5:00pm - Future products and services, defining questions that span technology, application, social impact and business opportunity: Team exercise to brainstorm emerging sectors and applications, followed by short team presentations
- 6:00pm - 8:00pm - Imaging Café event with 20 Imaging startups in Boston area (Optional Event: Opportunity for participants to present their own work in the audience) Imaging Café is a monthly event bringing together researchers, engineers, and students to foster deeper conversation with entrepreneurs, mentors and investors. This gathering is for people excited about mobile camera phones, cameras in developing countries, image-search, medical imaging, online photo sharing, home automation, computational photography, 3D printing and more.
Links & Resources
- Innovating for Billions: Ramesh Raskar at the Emerging Worlds Conference, October 27, 2015
- 1,000,000,000,000 Frames/Second Photography - Ramesh Raskar
- TEDxBeaconStreet: How to Think Like an MIT Media Lab Inventor: Ramesh Raskar
- YouTube: Ramesh Raskar, MIT Media Lab
- Federated Learning Balnaces Maching Learning with Patient Privacy. HIT Infrastructure, April 12, 2019
- Ramesh Raskar to give 2019 Doctoral Hooding Ceremony keynote address. UNC News, March 4, 2019
- The New Science of Seeing Around Corners. Quanta Magazine, August 30, 2018
- Music as a gateway to shared humanity: Iconic composer A.R. Rahman visits MIT campus to learn about new technologies. MIT News, August 2, 2018
- Depth-sensing imaging system can peer through fog: Computational photography could solve a problem that bedevils self-driving cars. MIT News, March 20, 2018
- New depth sensors could be sensitive enough for self-driving cars: Computational method improves the resolution of time-of-flight depth sensors 1,000-fold. MIT News, December 21, 2017
- A faster single-pixel camera: New technique greatly reduces the number of exposures necessary for “lensless imaging.” MIT News, March 29, 2017
- Ramesh Raskar awarded $500,000 Lemelson-MIT Prize: Imaging scientist and inventor sets sights on launching peer-to-peer invention platforms for global impact. MIT News, September 13, 2016
- Judging a book through its cover: New computational imaging method identifies letters printed on first nine pages of a stack of paper MIT News, September 9, 2016
- Smarter lenses: Newly launched mobile eye-test device could lead to prescription virtual-reality screens MIT News, October 19, 2015
- Compressive Displays
- Camera Culture | MIT Media Lab - Femto-Photography: Visualizing Photons in Motion at a Trillion Frames per Second
- Livemint/Wall Street Journal article: Hardware is becoming the new software: Ramesh Raskar
The type of content you will learn in this course, whether it's a foundational understanding of the subject, the hottest trends and developments in the field, or suggested practical applications for industry.
How the course is taught, from traditional classroom lectures and riveting discussions to group projects to engaging and interactive simulations and exercises with your peers.
What level of expertise and familiarity the material in this course assumes you have. The greater the amount of introductory material taught in the course, the less you will need to be familiar with when you attend.