合成与真实事件数据融合，提升恶劣天气下行人检测与意图识别性能。
DVS-PedX: Synthetic-and-Real Event-Based Pedestrian Dataset
- 结合CARLA模拟与真实行车视频生成事件流，覆盖多种天气光照条件。
- 提供每帧33毫秒事件帧与交叉/不交叉标签，支持多模态分析。
- 适用于神经形态感知、自动驾驶意图预测研究，推动仿真到现实迁移。
动态视觉传感器（DVS）通过报告微秒级亮度变化而非完整帧，实现低延迟、高动态范围和运动鲁棒性。DVS-PedX（动态视觉传感器行人探索）是一个类脑数据集，用于正常及恶劣天气下的行人检测与过街意图分析，包含两部分：(1) 在CARLA模拟器中生成的合成事件流，涵盖不同天气与光照下的“接近-穿越”场景；(2) 使用v2e工具将真实JAAD行车记录仪视频转换为事件流，保留自然行为与背景。每个序列均包含配对的RGB帧、每帧33毫秒累积的DVS事件帧及帧级标签（过街/未过街）。同时提供原始AEDAT 2.0/AEDAT 4.0事件文件、AVI DVS视频文件及元数据，支持灵活重处理。基于SpikingJelly的基线脉冲神经网络验证了数据集可用性，并揭示了仿真到现实的差距，推动领域自适应与多模态融合研究。DVS-PedX旨在加速事件驱动行人安全、意图预测与类脑感知研究。
原文摘要 · Abstract (English)
Event cameras like Dynamic Vision Sensors (DVS) report micro-timed brightness changes instead of full frames, offering low latency, high dynamic range, and motion robustness. DVS-PedX (Dynamic Vision Sensor Pedestrian eXploration) is a neuromorphic dataset designed for pedestrian detection and crossing-intention analysis in normal and adverse weather conditions across two complementary sources: (1) synthetic event streams generated in the CARLA simulator for controlled "approach-cross" scenes under varied weather and lighting; and (2) real-world JAAD dash-cam videos converted to event streams using the v2e tool, preserving natural behaviors and backgrounds. Each sequence includes paired RGB frames, per-frame DVS "event frames" (33 ms accumulations), and frame-level labels (crossing vs. not crossing). We also provide raw AEDAT 2.0/AEDAT 4.0 event files and AVI DVS video files and metadata for flexible re-processing. Baseline spiking neural networks (SNNs) using SpikingJelly illustrate dataset usability and reveal a sim-to-real gap, motivating domain adaptation and multimodal fusion. DVS-PedX aims to accelerate research in event-based pedestrian safety, intention prediction, and neuromorphic perception.
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。