Research

Paper

AI LLM February 25, 2026

RGB-Event HyperGraph Prompt for Kilometer Marker Recognition based on Pre-trained Foundation Models

Authors

Xiaoyu Xian, Shiao Wang, Xiao Wang, Daxin Tian, Yan Tian

Abstract

Metro trains often operate in highly complex environments, characterized by illumination variations, high-speed motion, and adverse weather conditions. These factors pose significant challenges for visual perception systems, especially those relying solely on conventional RGB cameras. To tackle these difficulties, we explore the integration of event cameras into the perception system, leveraging their advantages in low-light conditions, high-speed scenarios, and low power consumption. Specifically, we focus on Kilometer Marker Recognition (KMR), a critical task for autonomous metro localization under GNSS-denied conditions. In this context, we propose a robust baseline method based on a pre-trained RGB OCR foundation model, enhanced through multi-modal adaptation. Furthermore, we construct the first large-scale RGB-Event dataset, EvMetro5K, containing 5,599 pairs of synchronized RGB-Event samples, split into 4,479 training and 1,120 testing samples. Extensive experiments on EvMetro5K and other widely used benchmarks demonstrate the effectiveness of our approach for KMR. Both the dataset and source code will be released on https://github.com/Event-AHU/EvMetro5K_benchmark

Metadata

arXiv ID: 2602.22026
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-25
Fetched: 2026-02-26 05:00

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22026v1</id>\n    <title>RGB-Event HyperGraph Prompt for Kilometer Marker Recognition based on Pre-trained Foundation Models</title>\n    <updated>2026-02-25T15:34:15Z</updated>\n    <link href='https://arxiv.org/abs/2602.22026v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22026v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Metro trains often operate in highly complex environments, characterized by illumination variations, high-speed motion, and adverse weather conditions. These factors pose significant challenges for visual perception systems, especially those relying solely on conventional RGB cameras. To tackle these difficulties, we explore the integration of event cameras into the perception system, leveraging their advantages in low-light conditions, high-speed scenarios, and low power consumption. Specifically, we focus on Kilometer Marker Recognition (KMR), a critical task for autonomous metro localization under GNSS-denied conditions. In this context, we propose a robust baseline method based on a pre-trained RGB OCR foundation model, enhanced through multi-modal adaptation. Furthermore, we construct the first large-scale RGB-Event dataset, EvMetro5K, containing 5,599 pairs of synchronized RGB-Event samples, split into 4,479 training and 1,120 testing samples. Extensive experiments on EvMetro5K and other widely used benchmarks demonstrate the effectiveness of our approach for KMR. Both the dataset and source code will be released on https://github.com/Event-AHU/EvMetro5K_benchmark</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-25T15:34:15Z</published>\n    <arxiv:comment>Accepted by IEEE Transactions on Cognitive and Developmental Systems (IEEE TCDS) 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Xiaoyu Xian</name>\n    </author>\n    <author>\n      <name>Shiao Wang</name>\n    </author>\n    <author>\n      <name>Xiao Wang</name>\n    </author>\n    <author>\n      <name>Daxin Tian</name>\n    </author>\n    <author>\n      <name>Yan Tian</name>\n    </author>\n  </entry>"
}