Neuromorphic Imaging and Classification with Graph Learning

arXiv:2309.15627v2 Announce Type: replace
Abstract: Bio-inspired neuromorphic cameras asynchronously record pixel brightness changes and generate sparse event streams. They can capture dynamic scenes with little motion blur and more details in extreme illumination conditions. Due to the multidimensional address-event structure, most existing vision algorithms cannot properly handle asynchronous event streams. While several event representations and processing methods have been developed to address such an issue, they are typically driven by a large number of events, leading to substantial overheads in …

abstract algorithms arxiv asynchronous bio bio-inspired cameras classification cs.cv dynamic event generate graph graph learning imaging multidimensional neuromorphic pixel type vision