用事件相机数据实时检测小事件簇，效率高且与分辨率无关
Event Driven Clustering Algorithm
- 基于事件的时空邻近性，异步处理事件流
- 时间复杂度线性，仅需Θ(N)，N为事件数
- 适合高帧率、低延迟场景，如机器人导航
本文提出一种新型异步、事件驱动算法，用于实时检测事件相机数据中的小事件簇。该算法类似层次聚类，依据事件的时空邻近性识别簇。它充分利用事件相机的异步特性，采用简单高效的判断机制，实现Θ(N)的线性时间复杂度，其中N为事件数量。此外，运行时间与传感器分辨率（即像素数）无关。
原文摘要 · Abstract (English)
This paper introduces a novel asynchronous, event-driven algorithm for real-time detection of small event clusters in event camera data. Similar to hierarchical agglomerative clustering methods, the proposed algorithm detects clusters based on their spatio-temporal proximity. However, it explicitly leverages the asynchronous structure of event camera data and employs a simple yet efficient decision mechanism, achieving a linear time complexity of $Θ(N)$, where $N$ is the number of events. Furthermore, the runtime is independent of the sensor resolution, i.e., the number of pixels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。