Different from traditional video cameras, event cameras capture asynchronous events stream in which each event encodes pixel location, trigger time, and the polarity of the brightness changes. In this paper, we introduce a novel graph-based framework for event cameras, namely SlideGCN. Unlike some recent graph-based methods that use groups of events as input, our approach can efficiently process data event-by-event, unlock the low latency nature of events data while still maintaining the graph's structure internally. For fast graph construction, we develop a radius search algorithm, which better exploits the partial regular structure of event cloud against k-d tree based generic methods. Experiments show that our method reduces the computational complexity up to 100 times with respect to current graph-based methods while keeping state-of-the-art performance on object recognition. Moreover, we verify the superiority of event-wise processing with our method. When the state becomes stable, we can give a prediction with high confidence, thus making an early recognition. Project page: \url{https://zju3dv.github.io/slide_gcn/}.

翻译：不同于传统视频相机，事件相机捕捉异步事件流，其中每个事件编码了像素位置、触发时间和亮度变化的极性。本文提出了一种新颖的基于图的事件相机框架，名为SlideGCN。与近期一些使用事件组作为输入的基于图的方法不同，我们的方法能够逐事件高效处理数据，释放事件数据低延迟特性的同时，在内部保持图结构。为了实现快速图构建，我们开发了一种半径搜索算法，该算法相比基于k-d树的通用方法，能更好地利用事件云的局部规则结构。实验表明，与当前基于图的方法相比，我们的方法在保持物体识别最先进性能的同时，将计算复杂度降低了高达100倍。此外，我们通过该方法验证了逐事件处理的优越性。当状态趋于稳定时，我们可以给出高置信度的预测，从而实现早期识别。项目页面：\url{https://zju3dv.github.io/slide_gcn/}。