Neuromorphic Downsampling of Event-Based Camera Output
Neuromorphic Downsampling of Event-Based Camera Output
复制标题
基于事件的相机输出的神经形态下采样
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
J. Plank
中科院分区：
文献类型：
--
作者：
Charles P. Rizzo;C. Schuman;J. Plank
在这项工作中，我们解决的问题，训练神经形态代理工作的数据从基于事件的相机。尽管基于事件的摄像机数据比标准视频帧稀疏得多，但事件的绝对数量可能会使观察空间过于复杂，无法有效地训练代理。我们构建了多个神经形态网络，对相机数据进行下采样，以使训练更有效。然后，我们进行了一个案例研究，通过将每个帧转换为事件并对它们进行下采样来训练代理玩Atari Pong游戏。最终的网络结合了下采样和代理。我们还讨论了一些实际问题。
In this work, we address the problem of training a neuromorphic agent to work on data from event-based cameras. Although event-based camera data is much sparser than standard video frames, the sheer number of events can make the observation space too complex to effectively train an agent. We construct multiple neuromorphic networks that downsample the camera data so as to make training more effective. We then perform a case study of training an agent to play the Atari Pong game by converting each frame to events and downsampling them. The final network combines both the downsampling and the agent. We discuss some practical considerations as well.