High-Performance Neuromorphic Sensor Processing
Neuromorphic, or event-based, sensors capture events at a microsecond resolution, which requires low-latency processing via FPGAs for real-time performance. By leveraging both the temporal and spatial components of the events, some algorithms, like a Hierarchy of event- based Time-Surfaces (HOTS), we find relationships between the two components for enhanced feature extraction and object detection. In contrast, using k-means clustering on spatial information can explore the tradeoff between increased accuracy at the expense of performance.
Speaker(s)
Luke Kljucaric - University of Pittsburgh/Lead computer engineer PhD student
Luke Kljucaric is the lead computer engineering PhD student of the HPC/Reconfigurable systems group in NSF SHREC at the University of Pittsburgh. His research focuses on accelerated machine learning, which includes traditional and neuromorphic classification studied on CPUs, GPUs, and FPGAs.
