RIT researcher working to improve aerial tracking
New system will adopt deep learning, an artificial intelligence technology, to refine the understanding of overhead video and imaging
Researchers at RIT are developing an improved visual tracking system that can more accurately locate and follow moving objects under surveillance. Using deep learning, an artificial intelligence technology, the system could generate more reliable readings of moving objects—even of those objects become obscured or change patterns and direction.
Andreas Savakis, a professor of computer engineering, is developing the technology through advanced adaptive visual tracking algorithms for aerial platforms, a three-year, $250,000 project funded by the Department of the Air Force’s Materials Command/Systems and Technology. It is one of several inter-related projects that use deep learning to refine the computing algorithms and visual tools needed to follow object movements and understand activities.
Although many systems have the ability to recognize and classify various objects, it is essential to track them under variations in illumination or appearance to re-acquire them when they are occluded by other objects, said Savakis. This research has potential applications in autonomous navigation, drones, traffic monitoring, safety and security, disaster response and human-computer interaction.
“We need to track the right object and keep tracking it in real time. Often an object disappears behind buildings or trees only to appear later. We want to identify it when it is occluded and when it returns to the field of view,” he said.
Some challenges to current imaging technology and the need for improvements rise from objects seeming to change size and appearance because of distance and perspective, or lighting which can produce different colorings of objects. Researchers will be training the system to understand each of these distinct aspects by leveraging the power of deep neural networks and visual tracking algorithms.
“We’ll be able to learn more about the objects as we track them,” Savakis explained. His team will produce a prototype tracking system, building upon earlier research conducted on video analytics. Systems are supplied with this type of data to build a knowledgebase and distinguish the variety of visual imagery a computing system is asked to detect and track, most being complex scenes that are continually changing.
April 19, 2019
RIT professor created simulation that could help treat heart patients
WROC-TV features Elizabeth Cherry, associate professor and director of the mathematical modeling program.
April 18, 2019
Imagine RIT visitors get to control RIT’s ‘Weather Machine’ in new two-story-high video game
Imagine RIT visitors will help keep the skies above RIT clear during the festival on April 27, in a new video game on display at the MAGIC Spell Studios building. Festivalgoers can play “Weather Defense: A Two Stories High Video Wall Game” on six large 4K displays, mounted two stories up the atrium wall of the new 52,000-square-foot MAGIC building.
April 18, 2019
Student Spotlight: Participating in the ASCE Concrete Canoe competition
Meet Brady Smith, a fourth-year civil engineering technology student and captain of this year’s Concrete Canoe team.
April 18, 2019
Apple iPhones get recycled in this secretive lab. Now it's opening up
CNET quotes Callie Babbitt, associate professor of sustainability.