Computer vision

Pic2Recipe, an artificial intelligence system developed at MIT, can take a photo of an entree and suggest a similar recipe to it.

Artificial intelligence suggests recipes based on food photos

Given a still image of a dish filled with food, CSAIL team's deep-learning algorithm recommends ingredients and recipes.

July 20, 2017

Localizing ground-penetrating radar (LGPR) developed at MIT Lincoln Laboratory uses inherently stable subsurface features and their geolocation to locate a vehicle, even in adverse weather conditions. Below the surface, an earlier map can be seen in gray on the left, while a current scan is shown in light blue under the vehicle, and the registered data is shown in blue and green behind the vehicle...

Lincoln Laboratory enters licensing agreement to produce its localizing ground-penetrating radar

Commercial prototypes of the system will be available to the self-driving vehicle industry.

July 18, 2017

The MIT AgeLab and Toyota CSRC set up a camera system at a busy Cambridge intersection to study minute details of pedestrian movements.

AgeLab researching autonomous vehicle systems in ongoing collaboration with Toyota

Innovative MIT research focuses on developing systems to perceive and identify objects in their environment and understand social interactions in traffic.

June 8, 2017

A GelSight sensor attached to a robot’s gripper enables the robot to determine precisely where it has grasped a small screwdriver, removing it from and inserting it back into a slot, even when the gripper screens the screwdriver from the robot’s camera.

Giving robots a sense of touch

GelSight technology lets robots gauge objects’ hardness and manipulate small tools.

June 5, 2017

In 2016, MIT CSAIL researchers worked on a range of projects in robotics, theory, wireless technology, software systems, and other disciplines.

Ingestible robots, glasses-free 3-D, and computers that explain themselves

A look at 16 of the coolest things that happened at the Computer Science and Artificial Intelligence Laboratory in 2016.

December 16, 2016

The researchers’ neural network was fed video from 26 terabytes of video data downloaded from the photo-sharing site Flickr. Researchers found the network can interpret natural sounds in terms of image categories. For instance, the network might determine that the sound of birdsong tends to be associated with forest scenes and pictures of trees, birds, birdhouses, and bird feeders.

Computer learns to recognize sounds by watching video

Machine-learning system doesn’t require costly hand-annotated data.

December 2, 2016

Given a still image from a scene, new deep-learning algorithm can create a brief video that simulates the future of that scene.

Creating videos of the future

Given a still image, CSAIL deep-learning system generates videos that predict what will happen next in a scene.

November 29, 2016

Imaging scientist and social impact inventor Ramesh Raskar of MIT is the 2016 recipient of the $500,000 Lemelson-MIT Prize.

Ramesh Raskar awarded $500,000 Lemelson-MIT Prize

Imaging scientist and inventor sets sights on launching peer-to-peer invention platforms for global impact.

September 13, 2016

To simulate objects, MIT CSAIL researchers analyzed video clips to find “vibration modes” at different frequencies that each represent distinct ways that an object can move.

Reach in and touch objects in videos with “Interactive Dynamic Video”

Technique from Computer Science and Artificial Intelligence Lab could improve augmented reality and reduce the need for CGI green-screens.

August 2, 2016

A localizing ground-penetrating radar system from the MIT Lincoln Laboratory complements existing technology, with the goal of achieving safe autonomous vehicles.

Pinpointing vehicles with high precision under adverse weather conditions

MIT Lincoln Laboratory radar system achieves centimeter-level localization; could help driverless cars stay in lane when road markings are obscured.

June 23, 2016

From MIT CSAIL: The left-most column shows the frame before the action begins, with the algorithm's prediction below it. The right columns show the next frames of the video.

Teaching machines to predict the future

Deep-learning vision system from the Computer Science and Artificial Intelligence Lab anticipates human interactions using videos of TV shows.

June 21, 2016

Artificial intelligence produces realistic sounds that fool humans

Video-trained system from MIT’s Computer Science and Artificial Intelligence Lab could help robots understand how objects interact with the world.

June 13, 2016

The goal of MIT's "Duckiebot" class was to create a fleet of 50 self-driving taxis that can navigate the roads of a model city with just a single on-board camera and no pre-programmed maps.

Self-driving cars, meet rubber duckies

“Duckietown” class at Computer Science and Artificial Intelligence Lab teaches autonomy, aims to become global research platform.

April 20, 2016

MIT researchers fed their physics prediction system videos of collisions, shown as screenshots in (a) and (b), which were then converted into simulations generated by the 3-D physics engine, shown in (c) and (d).

Computer model matches humans at predicting how objects move

“3-D physics engine” from the Computer Science and Artificial Intelligence Laboratory simulates the human brain to infer physical properties.

January 4, 2016

For each image, the MemNet algorithm creates a heat map identifying its most memorable and forgettable regions.

Deep-learning algorithm predicts photos’ memorability at “near-human” levels

Future versions of an algorithm from the Computer Science and Artificial Intelligence Lab could help with teaching, marketing, and memory improvement.

December 16, 2015

MIT News | Massachusetts Institute of Technology - On Campus and Around the world

Browse By

Topics

Departments

Centers, Labs, & Programs

Schools

Topic