Event-based cameras are a new type of vision sensor that can encode spatial-temporal context in a pixel-level event stream. Its appealing properties offer great potential for applications requiring low processing latency and low power consumption. As an effective representation of events, the surface of active event (SAE) has become a favorable choice for corner detection and object classification, among others. These tasks apply normalizations as an essential preprocessing step to extract time-invariant features from SAEs. However, previous normalization methods have some drawbacks, including low efficiency, requiring parameter tuning, etc. These drawbacks largely limit their performances in practical tasks. In this work, we propose a highly efficient normalization method, i.e., chain normalization, to break the limits in the previous state-of-the-art. We leverage the inherent properties of SAE in designing. First, we propose a novel SAE implementation to utilize the characteristics of SAE. Compared with previous works, our method can efficiently capture the spatial and temporal relationships of events and enable robust normalization. Second, we further increase the efficiency by using a novel stacking strategy. We compare our method to the state-of-the-art with extensive experiments, showing high classification accuracy and a significant improvement in runtime performance. We also release the source codes for future distribution and improvement in the community.

中文翻译：

---

事件相机 SAE 表示的高效时空归一化


基于事件的相机是一种新型视觉传感器，可以在像素级事件流中编码时空上下文。其吸引人的特性为需要低处理延迟和低功耗的应用提供了巨大的潜力。作为事件的有效表示，活动事件表面（SAE）已成为角点检测和对象分类等的有利选择。这些任务将归一化作为从 SAE 中提取时不变特征的基本预处理步骤。然而，以前的归一化方法存在一些缺点，包括效率低、需要参数调整等。这些缺点在很大程度上限制了它们在实际任务中的性能。在这项工作中，我们提出了一种高效的归一化方法，即链归一化，以打破先前最先进的限制。我们在设计中利用 SAE 的固有特性。首先，我们提出了一种新颖的 SAE 实现来利用 SAE 的特性。与以前的工作相比，我们的方法可以有效地捕获事件的空间和时间关系并实现稳健的标准化。其次，我们通过使用新颖的堆叠策略进一步提高效率。我们通过大量实验将我们的方法与最先进的方法进行比较，显示出高分类精度和运行时性能的显着改进。我们还发布了源代码，以便将来在社区中分发和改进。