用多尺度事件表示提升感知速度，无需循环结构也能高效检测
Efficient Multi-Timescale Event Representations for Feed-Forward Object Detection
- 设计对数B样条多时标编码，结合空间结构信心机制
- 在PEDRo和Gen1数据集上优于传统紧凑表示，精度提升显著
- 支持事件级快速更新，适合实时神经形态视觉系统
自主系统需在快速变化的场景和复杂光照下实现低延迟感知。事件相机中的目标检测通常依赖循环架构来累积稀疏的时间信息。本文研究如何直接在事件表示中编码时间信息。提出一种基于对数B样条的置信度归一化连续多时标表示，并引入几何感知的局部置信度机制，利用事件生成的空间结构。使用固定前馈的EventCenterNet检测器，结果表明该表示在PEDRo和Gen1数据集上持续优于紧凑的CSTR表示。进一步提出递归指数多项式近似方法，实现高效的逐事件更新，同时保持较高检测性能。结果表明，精心设计的事件表示可捕获循环建模所学的大量时序信息，为高效前馈、事件驱动的未来神经形态目标检测提供良好基础。
原文摘要 · Abstract (English)
Autonomous systems require robust low-latency perception under rapidly changing scene dynamics and challenging illumination. In event cameras object detection commonly relies on recurrent architectures to accumulate sparse temporal information over time. This work investigates how temporal information can be encoded directly within the event representation. We propose a confidence-normalized continuous multi-timescale representation based on logarithmic B-spline temporal encoding together with a geometry-aware local confidence mechanism that exploits the spatial structure of event generation. Using a fixed feed-forward EventCenterNet detector, we show that the proposed representations consistently outperform the compact CSTR representation on PEDRo and Gen1 datasets. We further introduce a recursive exponential-polynomial approximation that enables efficient event-by-event updates while largely preserving detection performance. These results demonstrate that carefully designed event representations can capture a substantial portion of the temporal information learned through recurrent temporal modeling, providing a promising foundation for efficient feed-forward, event-driven, and future neuromorphic object detection.
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。