Date:
Location:
PANEL I: NEXT GENERATION OF NEUROMORPHIC VISION SENSORS FOR MOTION SEGMENTATIONS
Neuromorphic cameras have emerged as a revolutionary technology with a high temporal resolution that far surpasses conventional cameras. Dynamic Vision Sensors (DVS) draw biological inspiration from photoreceptors and the initial retinal synapse. Our research showcases the potential of additional retinal functionalities for the extraction of visual features. We provide a domain-agnostic and efficient algorithm to distinguish object motion from self-motion based on Object Motion Sensitivity (OMS), one of the several robust features computed within the mammalian retina. We develop a framework based on experimental neuroscience that translates OMS' biological circuitry to a low-overhead algorithm. OMS processes DVS data from dynamic scenes to perform pixel-wise object motion segmentation. We highlight OMS' ability to differentiate object motion from ego-motion, bypassing the need for deep networks. Our work paves the way to robust, high-speed, and low-bandwidth real-time decision-making for in-sensor computations.
Speaker: Maria Victoria Clerico (Telecommunication Engineer and double-degree master's student at Universidad Politecnica de Madrid (UPM); Research Assistant at George Mason University (GMU))
Sponsor: RCCHU; UPM; GMU