用于前馈目标检测的高效多时间尺度事件表示
Efficient Multi-Timescale Event Representations for Feed-Forward Object Detection
浏览论文内容
中文总结 AI 辅助
该研究针对事件相机目标检测的循环架构效率问题,提出了基于对数B样条编码的多时间尺度事件表示,在PEDRo和Gen1数据集上优于CSTR表示,为高效前馈事件驱动目标检测提供了基础。
中文摘要 AI 辅助
自主系统需要在快速变化的场景动态和具有挑战性的光照条件下实现鲁棒、低延迟的感知。在事件相机中,目标检测通常依赖循环架构来随时间累积稀疏的时间信息。本研究探讨如何将时间信息直接编码到事件表示中。我们提出一种基于对数B样条时间编码的置信度归一化连续多时间尺度表示,以及一种利用事件生成空间结构的几何感知局部置信度机制。使用固定的前馈EventCenterNet检测器,我们表明所提出的表示在PEDRo和Gen1数据集上始终优于紧凑的CSTR表示。我们进一步引入递归指数多项式近似,该近似支持逐事件的高效更新,同时在很大程度上保持检测性能。这些结果表明,精心设计的事件表示能够捕获通过循环时间建模学习到的大部分时间信息,为高效的前馈、事件驱动以及未来的神经形态目标检测提供了有前景的基础。
英文摘要
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.
发表机构
- Linköping University(林雪平大学)
- Saab AB(萨博公司)
机构由 AI 辅助整理,请以论文原文为准。