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.

翻译：事件相机（如动态视觉传感器，DVS）以微秒级时间精度报告亮度变化而非完整帧，具有低延迟、高动态范围和运动鲁棒性。DVS-PedX（动态视觉传感器行人探索）是一个神经形态数据集，专为正常与恶劣天气条件下的行人检测和横穿意图分析而设计，包含两个互补来源：（1）在CARLA模拟器中生成的合成事件流，用于不同天气和光照下受控的“接近-横穿”场景；（2）通过v2e工具将真实世界JAAD行车记录仪视频转换而成的事件流，保留了自然行为与背景。每个序列包含配对的RGB帧、逐帧的DVS“事件帧”（33毫秒累积）以及帧级标签（横穿与非横穿）。我们还提供了原始的AEDAT 2.0/AEDAT 4.0事件文件、AVI DVS视频文件及元数据，以支持灵活的再处理。使用SpikingJelly构建的基准脉冲神经网络（SNN）展示了数据集的可用性，并揭示了仿真到现实的差距，从而推动了领域自适应与多模态融合的研究。DVS-PedX旨在加速基于事件的行人安全、意图预测及神经形态感知领域的研究。