Advancing AI to see differently

Apr 10, 2019

Article written by Indiana University:

Whether it’s reading you the weather forecast with a simple voice command, or analyzing vast amounts of data to help inform a life-saving medical treatment, artificial intelligence is influencing our daily lives more than ever before. At Indiana University, researchers are working to advance the promise of artificial intelligence, while also making this crucial technology understandable to a wider audience.

David Crandall’s research with computer vision and machine learning is improving the way computers and robots think. Crandall, an associate professor of informatics and computing at the School of Informatics, Computing and Engineering at Indiana University is also director of IU’s Computer Vision Lab, a hub of AI work at the university.

Creating the vison

The IU Computer Vision Lab investigates and develops advanced statistical and machine learning techniques for automatically analyzing, understanding, and organizing visual information. The lab’s applications include recognizing objects in consumer images, analyzing human activity in video, discovering patterns in large scientific datasets, reconstructing 3-D models of world landmarks, and even studying visual attention in toddlers.

“Computers are really good at fast, precise calculations and they are really good at storing huge amounts of data. What they aren’t good at is making subjective comparisons between things.” – David Crandall, Associate Professor, School of Informatics, Computing, and Engineering.

The goal of computer vision is for computers to be able to understand the visual world the way people do. Computers have been able to take and store pictures for decades, but they haven’t been able to know what is in a photo—what objects and people are in it, what is going on, and what is about to happen. People do this automatically, almost instantly, thinking nothing of it. Yet, this process is still difficult for a computer. Computer vision is changing that, and the field has made huge progress in the last few years.

“The challenge of the computer vision work we’re doing—and with a lot of real-world problems—is that it requires very fine-grain analysis,” said Crandall. “We’re not trying to distinguish cats from dogs or cars from pedestrians; we’re trying to find very subtle differences in integrated circuits that might signal a problem. That’s really the challenge: to bring techniques that have been successful in the last few years in consumer photography to this new field that has unique challenges.”

The Computer Vision Lab and its researchers are developing algorithms to help computers see patterns and permutations in complex datasets.

Innovation through partnership

Crandall along with IU faculty members Sara Skrabalak and Martin Swany are also the first IU researchers whose work is being advanced through the Indiana Innovation Institute, or IN3.

IN3, a statewide applied research institute, is composed of top leaders from academia, government and industry. It seeks to solve real-world problems that impact industry and the U.S. Department of Defense in a faster, more efficient and cost-effective way. Currently, it is engaged in projects focused on trusted microelectronics, hypersonics, electro-optics and target machine learning.

“An exciting vision of IN3 is to bring together groups of people working in different areas, who might not otherwise have thought to collaborate with one another, in order to jointly solve big problems that none of us could address individually,” said Crandall.

“I work in computer vision and artificial intelligence. We’re looking for ways to apply these techniques to new, important, exciting problems. As we apply them, we discover new technical challenges, which leads us to go back to the drawing board to create new, better algorithms. I don’t have deep expertise in microelectronics, so I wouldn’t be able to impact this field alone. Collaborating with experts via IN3 will be the way we impact their field and bring back important, interesting problems for us to work on as well.”

IN3 is not only bringing together groups at IU, but also creating stronger connections between IU and Purdue, Notre Dame and NSWC Crane.

“This is pretty cutting-edge AI stuff,” says Crandall.