Home
Archive
Creating the Vision

Creating the Vision

Teaching computers to see like we do

The IU Computer Vision Lab investigates and develops advanced statistical and machine learning techniques to analyze, understand, and organize visual information. Applications of the lab’s work 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.

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, but that process is difficult for a computer.

David Crandalls 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 Bloomington, is also director of the Computer Vision Lab, a hub of AI work at the university.

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 - IU Associate Professor of Informatics and Computing at the School of Informatics, Computing and Engineering; Director, IU Computer Vision Lab

Computer vision is changing that, and the field has made huge progress in the last few years. The Computer Vision Lab and its researchers are developing algorithms to help computers see patterns and permutations in complex datasets.

“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.”

Likewise, on the IUPUI campus, researchers are addressing unique AI challenges associated with autonomous vehicles (AVs). AVs are one of the most exciting and impactful areas of AI research. IU’s Transportation Active Safety Institute (TASI) focuses on the research and development of sensing technologies for autonomous driving vehicles. They are applying computer vision, artificial intelligence, and data mining approaches in their work on recognition of vehicles, pedestrians, bicyclists, road environments, traffic flow, dangerous events, and potential accidents.