Since 2000, the National Science Foundation has bestowed Early Career Development Awards on 20 of RPI’s young faculty members. The CAREER Award is the NSF’s most prestigious award for faculty in their early professional careers. The award includes financial support for research over the course of five years, the amount based on a budget request submitted by the honoree, with the minimum total award amount set at $400,000.
Richard Radke has been honored with an NSF CAREER Award for his research involving distributed processing on a network with many video cameras. Networked cameras would be able to figure out where they are in relation to each other with no camera controlling any of the others. With such independence, if one camera were taken out of the network, the system would still operate. In addition, this system is being designed to work with limited power, such as with batteries.
Possible applications for this technology include battlefields, where the military might drop 100 cameras to develop a map of an area. In this system, a camera that is destroyed in battle would have no effect on the other cameras. A user could tell the system that he or she wants to see more of a certain kind of image, such as brick or mountains. The system would then be able to turn and face those objects that the user has requested.
Some of the challenges include how to prioritize the information that comes into the camera. If the user wanted the system to track a fire, the system would need to increase its response time on the cameras that see fire. Another challenge includes creating a distributed algorithm that is efficient and practical for low power operation.
Radke enjoys his work, especially the immediate result one receives when working with images. This immediate sense of achievement is what motivated him to study computer vision when, as an undergraduate, an advisor showed him interesting research going on in the field. This deviated from his original study of mathematics at Rice University in Houston, Tex. He went on to earn an M.A. in mathematics from Rice and then an M.A. and a Ph.D in electrical engineering from Princeton.
As computer vision has many applications which have not yet been realized, Radke “enjoys getting his hands dirty.” He hopes to soon make large distributed camera networks a reality.
