- This event has passed.
Spring 2022 GRASP SFI: Anthony Bisulco, University of Pennsylvania, “A Tutorial on Neuromorphic Vision for High-Speed Perception”
February 2, 2022 @ 3:00 pm - 4:00 pm
ABSTRACT
Mobile robot systems operate in dynamic environments, such as forests, caves, or roadways, where they must perceive and react to incoming stimuli. Each of these environments presents unique challenges such as perception in low-light conditions, high-speed understanding of objects, and low power requirements. Neuromorphic Vision Systems such as event-based cameras have appealing properties for the above challenges such as high-temporal resolution, low-power footprint, and high-dynamic-range. As opposed to conventional frame-based imagers, event-based cameras output a stream of asynchronous events consisting of spatial illumination changes. This presents an expansive new processing model for event-based computer vision applications. In this talk, I will begin with a tutorial on event-based cameras, review processing techniques for the event-stream, and highlight our recent work on developing high-speed perception action systems for object catching.
Presenter
Anthony Bisulco
Anthony Bisulco is a first year PhD student in Electrical and Systems Engineering working with Kostas Daniilidis and Vijay Kumar. Anthony’s research interests lie at the intersection of perception, machine learning and hardware. He previously was a researcher at the Samsung Artificial Intelligence Center New York, under Daniel Lee, working on event-based vision, reinforcement learning, and robotic manipulation. Anthony received a Master of Engineering degree from Cornell University and a Bachelor of Science degree from Northeastern University