Event-based Spatio-temporal down-sampling
Title: Event-based Spatio-temporal down-sampling
Authors: Anindya Ghosh (University of Sussex); Thomas Nowotny (University of Sussex); James Knight (University of Sussex);
Year: 2022
Citation: Ghosh, A., Nowotny, T., Knight, J., (2022). Event-based Spatio-temporal down-sampling. UKRAS22 Conference “Robotics for Unconstrained Environments” Proceedings, 26-27. doi: 10.31256/Ik8Mv1B
Abstract:
Abstract—As vision sensors for autonomous systems, event based cameras provide numerous benefits over conventional cameras including higher dynamic range and temporal resolution as well as lower bandwidth and power requirements. However, while down-sampling is regularly used in standard computer vision, there are no reliable technique to do this for event data, resulting in a bottleneck for event based computer vision systems. Here we propose two novel methods for down-sampling event
data and compare them against a previously used method.