ITSC 2025 Paper Abstract

Close

Paper TH-EA-T16.6

Ma, Feng (Beijing Jiaotong University), Zhao, Hongli (BEIJING JIAOTONG UNIVERSITY), Zhu, Li (Beijing Jiaotong University), Tan, Lei (Beijing Municipal Engineering Research Institute), yang, xiaohui (the Beijing Municipal Engineering Research Institute), TANG, Tao (Beijing Jiaotong University)

A Deep Learning-Based Real-Time Detection Model for Water Leakage in Subway Tunnels

Scheduled for presentation during the Invited Session "S16b-Control, Communication and Emerging Technologies in Smart Rail Systems" (TH-EA-T16), Thursday, November 20, 2025, 14:50−15:30, Southport 1

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords Autonomous Rail Systems and Advanced Train Control Technologies, Smart Roadway and Charging Infrastructure for Public Transport, Autonomous Public Transport Systems and Mobility-as-a-Service (MaaS)

Abstract

随着城市化进程的加速,该 地铁隧道结构面安全监测 前所未有的挑战,尤其是在检测 隧道衬砌表面漏水。传统的 检测方法在以下方面存在重大局限性 实时性能和准确性。为了解决这个问题, 本研究提出了一种轻量级深度学习模型,该模型 结合了 MobileNetV2 和 DeepLabV3 架构。这 Task Prompt Adapter (TPA) 专为 漏水检测任务。此适配器嵌入在 MobileNetV2 的中间层(在 Block3 和 Block4),增强了模型的特征提取 通过整合边缘信息和 密切相关的亮度差异特征 到漏水分段。实验结果表明 改进后的模型实现了平均交集 经盘 (mIoU) 为 81.6%,比 baseline 模型,同时保持实时推

 

 

All Content © PaperCept, Inc.


This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2025 PaperCept, Inc.
Page generated 2025-10-18  21:52:18 PST  Terms of use