Researchers tout AI that can predict 25 video frames into the future

91692C51-E8C1-4486-B5C4-BBB788FEF5BD

AI video prediction

AI and machine learning algorithms are becoming increasingly good at predicting next actions in videos. The very best can anticipate fairly accurately where a baseball might travel after it has been pitched, or the appearance of a road miles from a starting position. To this end, a novel approach proposed by researchers at Google, the University of Michigan, and Adobe advances the state of the art with large-scale models that generate high-quality videos from only a few frames. All the more impressive, it does so without relying on techniques like optical flows (the pattern of apparent motion of objects, surfaces, or edges in a scene) or landmarks, as previous methods have.

“In this work, we investigate whether we can achieve high-quality video predictions … by just maximizing the capacity of a standard neural network,” wrote the researchers in a preprint paper describing their work. “To the best of our knowledge, this work is the first to perform a thorough investigation on the effect of capacity increases for video prediction.”

Continue reading… “Researchers tout AI that can predict 25 video frames into the future”

0

Energy-Recycling Foot Makes It Easier For Amputees To Walk

artifical-footsmall 432

What’s better than an artificial nose? Why, an artificial foot, of course! University of Michigan researchers have developed a new prosthetic foot that could one day make it much easier for amputees to walk. Put simply, this new prototype drastically cuts the energy spent per step, as it harnesses the energy exerted when taking a step and enhances the power of ankle push-off. The device is able to capture dissipated energy, and an inbuilt microcontroller tells the foot to return the energy to the system at precisely the right time.

Continue reading… “Energy-Recycling Foot Makes It Easier For Amputees To Walk”

0

Intelligent Bridge Monitoring System To Prevent Tragedies

Intelligent Bridge Monitoring System To Prevent Tragedies

Smart bridges will know when they are in trouble 

From mundane traffic overpasses to marvelous feats of soaring engineering, bridges are something we tend to take for granted – until something goes wrong that is. A team from the University of Michigan is leading a five-year, $19 million project to engineer an intelligent infrastructure monitoring system designed to prevent tragedies like the collapse of the Interstate 35 West bridge over the Mississippi river in 2007 in which 13 people were killed and 145 were injured.

Continue reading… “Intelligent Bridge Monitoring System To Prevent Tragedies”

0