Computer vision

An MIT system uses an algorithm that can take 2-D videos and turn them into 3-D-printed “motion sculptures” that show how a human body moves through space.

Creating 3-D-printed “motion sculptures” from 2-D videos

CSAIL system could help athletes, dancers, and others better analyze how they move.

September 18, 2018

MIT computer scientists have developed a system that learns to identify objects within an image, based on a spoken description of the image.

Machine-learning system tackles speech and object recognition, all at once

Model learns to pick out objects within an image, using spoken descriptions.

September 18, 2018

MIT researchers have developed a module that helps artificial-intelligence systems fill in the gaps between video frames to improve activity recognition.

Helping computers fill in the gaps between video frames

Machine learning system efficiently recognizes activities by observing how objects change in only a few key frames.

September 13, 2018

PhD student Lucas Manuelli worked with lead author Pete Florence to develop a system that uses advanced computer vision to enable a Kuka robot to pick up virtually any object.

Robots can now pick up any object after inspecting it

Breakthrough CSAIL system suggests robots could one day be able to see well enough to be useful in people’s homes and offices.

September 10, 2018

Department of Aeronautics and Astronautics grad students Sebastien Mannai (left) and Antoni Rosinol Vidal won the FutureMakers Challenge first prize by demonstrating the utility of machine vision and signal processing in a complex mechanical engineering system.

Sebastien Mannai, Antoni Rosinol Vidal win FutureMakers first prize

AeroAstro grad students win multi-university challenge by demonstrating the utility of machine vision in a complex system.

September 4, 2018

A new AI system can look at an image and determine which set of pixels are responsible for making specific sets of soundwaves.

An AI system for editing music in videos

Given a video of a musical performance, CSAIL’s deep-learning system can make individual instruments louder or softer.

July 5, 2018

A system developed at MIT aims to teach artificial agents a range of chores, including setting the table and making coffee.

Teaching chores to an artificial agent

Activity simulator could eventually teach robots tasks like making coffee or setting the table.

May 30, 2018

MIT engineers have developed a new virtual-reality training system for drones that enables a vehicle to “see” a rich, virtual environment while flying in an empty physical space.

Researchers develop virtual-reality testing ground for drones

With new system, drones navigate through an empty room, avoiding crashes while “seeing” a virtual world.

May 17, 2018

A team of MIT researchers tested MapLite on a Toyota Prius outfitted with a range of LIDAR and IMU sensors.

Self-driving cars for country roads

Today’s autonomous vehicles require hand-labeled 3-D maps, but CSAIL’s MapLite system enables navigation with just GPS and sensors.

May 7, 2018

To create complete road maps companies like Google often have to have employees take existing aerial images with incomplete information and manually fill in the gaps.

A new way to automatically build road maps from aerial images

“RoadTracer” system from the Computer Science and Artificial Intelligence Laboratory could reduce workload for developers of apps like Google Maps.

April 17, 2018

Guy Satat, a graduate student in the MIT Media Lab, who led the new study.

Depth-sensing imaging system can peer through fog

Computational photography could solve a problem that bedevils self-driving cars.

March 20, 2018

Skydio, a San Francisco-based startup founded by three MIT alumni, is commercializing an autonomous video-capturing drone — dubbed by some as the “selfie drone” — that tracks and films a subject, while freely navigating any environment.

The autonomous “selfie drone”

Alumni’s video-capturing drone tracks moving subjects while freely navigating any environment.

March 13, 2018

Escher Reality, co-founded by Ross Finman in the MIT Sandbox, was recently acquired by augmented-reality (AR) giant Niantic — and plans to give back to the program that helped it launch. The startup is developing a platform that allows cross-platform, fully multiplayer AR games that save digital objects in the real world.

MIT Sandbox’s first acquired startup gives back

Augmented-reality startup Escher Reality, which recently sold to Niantic, gives back to the program that helped it launch.

February 21, 2018

Butterfly Network, a startup co-founded by MIT alumnus Nevada Sanchez ’10, SM ’11, has developed a low-cost, handheld scanner that generates clinical-quality ultrasounds on a smartphone. Ultrasounds are uploaded to the cloud, where any expert with permission can give second opinions or help analyze images.

Giving everyone a window into the human body

Startup’s low-cost, portable scanner generates clinical-quality ultrasounds on a smartphone.

February 6, 2018

$MIT spinout PlenOptika has developed a highly accurate, portable autorefractor called QuickSee that measures refractive errors of the eye. More affordable than the current technology, the device has potential to reach patients in previously inaccessible areas of developing countries.$

Startup aims to make vision care more accessible in developing world

Portable device can generate corrective lens prescriptions in areas with no optometry care.

January 10, 2018

MIT News | Massachusetts Institute of Technology

Browse By

Topics

Departments

Centers, Labs, & Programs

Schools

Topic