LJ Rich reports for The BBC on an algorithm created by MIT and Google researchers that can remove reflections and obstructions from images. “The technique separates the foreground from the background using frames from a short video,” explains Rich.
“MIT PhD student Abe Davis has developed video technology that reveals an object’s hidden properties,” writes Joanna Goodman for The Guardian. “Davis uses high-speed silent video to capture and reproduce sound, including music and intelligible speech, from the vibrations it makes on inanimate objects.”
Dave Gershgorn writes for Popular Science about an algorithm created by MIT and Google researchers that can remove obstructions from photos: “[T]he algorithm detects what obstruction is in the foreground,” writes Gershgorn, “then replaces the space that would be missing, when the foreground and backgrounds layers are separated, with pixels from the other photos.”
“Researchers at MIT and Google have created an algorithm that uses multiple images taken from different angles to separate foreground obstacles from the subject that's in the background,” writes Lucy Perkins for NPR. The algorithm can be used to remove unwanted reflections from photos.
“Researchers at the Camera Culture Group, headed by Ramesh Raskar at the MIT Media Lab, have designed the eyeSelfie, an inexpensive hand-held device for taking a photograph of the retina,” writes Vijee Venkatraman for BetaBoston. Retinal monitoring has been shown to help identify a variety of diseases and risk factors.
Fortune reporter Jonathan Vanian writes that researchers from MIT’s Computer Science and Artificial Intelligence Laboratory have developed a new method to restore old, malfunctioning code. The system, called Helium, “discovers the most crucial lines of code that the original programmers developed to make it function, and then builds a revised version of the program.”
MarketWatch reporter Sally French writes that researchers from MIT CSAIL have developed an algorithm that can be used to predict how memorable a person’s is. “The algorithm was created from a database of more than 2,000 images that were awarded a “memorability score” based on human volunteers’ ability to remember the pictures,” French writes.
In this video, Monika Auger of The Wall Street Journal describes how MIT engineers have developed a robotic cheetah that can jump over obstacles autonomously. Auger explains that the robot’s vision and path planning systems give it "complete autonomous control over its movements.”
Neel Patel writes for Wired about how MIT researchers have trained their robotic cheetah to detect and leap over obstacles. The robot “estimates the height, size, and distance of objects in its path, and adjusts its approach to prepare a jump and safe landing—all without slowing down.”
Writing for The Washington Post, Rachel Feltman describes how the MIT robotic cheetah can jump over obstacles up to 18 inches tall. “The robot uses an algorithm to gauge the height and distance of upcoming obstacles, so it can clear them without breaking its (record-breaking) stride,” Feltman explains.
Victor Luckerson writes for TIME about the robotic cheetah created by a team of MIT researchers that can “autonomously leap tall obstacles in a single bound.” Luckerson explains that, “the cheetah can clear hurdles as high as 18 in. (46 cm) at an average running speed of 5 m.p.h. (8 km/h).”
Newsweek reporter Felicity Capon writes about the robotic cheetah developed by MIT researchers that can jump over hurdles autonomously. The cheetah uses an onboard mapping system to detect obstacles and estimate their height and distance.
MIT researchers have developed a robotic cheetah that can jump over obstacles while running, reports Sandrine Ceurstemont for New Scientist. “The robot spots obstacles in its path with its built-in lidar system, which can build up a picture of the object in its way from reflected laser light,” explains Ceurstemont.
MIT researchers have trained a cheetah robot they developed to make “flying leaps” over obstacles, reports Devin Coldewey for NBC News. The researchers behind the robotic cheetah aim to “build a ‘high-speed locomotion platform’ with the fastest land animal as its inspiration.”
The robotic cheetah developed by MIT researchers can now autonomously jump over obstacles, reports Nitya Rajan for The Huffington Post. “This is the first time a four-legged robot has used laser sensors to gauges the distance and height of obstacles in its way to plan its jump,” writes Rajan.