DVS-PedX: Synthetic-and-Real Event-Based Pedestrian Dataset

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sakhai, Mustafa, Sithu, Kaung, Oke, Min Khant Soe, Wielgosz, Maciej
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912570207633408
author Sakhai, Mustafa
Sithu, Kaung
Oke, Min Khant Soe
Wielgosz, Maciej
author_facet Sakhai, Mustafa
Sithu, Kaung
Oke, Min Khant Soe
Wielgosz, Maciej
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04117
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DVS-PedX: Synthetic-and-Real Event-Based Pedestrian Dataset
Sakhai, Mustafa
Sithu, Kaung
Oke, Min Khant Soe
Wielgosz, Maciej
Computer Vision and Pattern Recognition
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.
title DVS-PedX: Synthetic-and-Real Event-Based Pedestrian Dataset
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.04117