Efficient Multi-Timescale Event Representations for Feed-Forward Object Detection

2026-09-04

AI Summary

本文提出一种基于对数B样条时间编码的多时间尺度事件表示方法，用于前馈目标检测，以解决快速变化场景下的低延迟感知问题。

Abstract

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.

Problem

• event representation
• temporal information
• autonomous systems
• low-latency perception
• object detection

Innovation

• multi-timescale representation
• logarithmic B-spline temporal encoding
• geometry-aware local confidence mechanism
• recursive exponential-polynomial approximation
• event-by-event updates