摘要
基于监控视频的入侵检测是保障铁路安全运营,人工智能技术赋能智慧铁路的一项重要业务。然而,传统深度学习模型依赖海量训练数据,实际铁路场景中面临场景差异大、侵限样本稀缺等问题,使得传统深度学习模型在铁路场景中迁移难、过拟合,无法实现高识别准确率。本文提出一种基于MAML元学习算法的铁路入侵检测方案;设计一个轻量级的深度神经网络,并在国产飞桨深度学习平台实现。最终,在目标监控场景下,利用本文所提模型,仅经过少量标注数据快速微调训练,可达到82.4%的检测准确率。
Surveillance-video based intrusion detection empowered by artificial inteligence technologies is an important business to ensure the safe operation of smart railways.However,traditional deep learming models rely on massive amounts of training data.In actual railway scenes there exist the problems of high inter-scene dissimilarity and few shot intrusion samples,which make the traditional deep learming models overfit in the training phase and fail to achieve high detection accuracy when they are transferred to a new railway scene.This paper proposes a railway intrusion detection scheme based on model-agnostic meta-leaming and designs a lightweight deep neural network.By programming on the PaddlePaddle deep learning platform,the proposed method achieves 82.4%intrusion detection aceunacy after only a few fine-tuning steps with only small number of labeled data.
作者
陈为
郭疆远
韩晓极
宫啸
钟章队
Chen Wei;Guo Jiangyuan;Han Xiaoji;Gong Xiao;Zhong Zhangdui(Beijing Jiaotong University,Key Laboratory of Railway Industry of Broadband Mobile Information Communications,Beijing 100044,China;Beijing Jiaotong University,The State Key Laboratory of Rail Traffic Control and Safety,Beijing 100044,China;Beijing Jiaotong University,Beijing Engineering Research Center of High-speed Railway Broadband Mobile Communications,Beijing 100044,China;CCTEG Shenyang Research Institute,Shenyang,Liaoning 133122,China)
出处
《铁道技术标准(中英文)》
2022年第8期1-6,共6页
Railway Technical Standard(Chinese & English)
基金
中央高校基本科研业务费(2021YJS199)
北京市自然科学基金(L202019,L211012)
CCF-百度松果基金(NO.2021PP15002000)
国家铁路局课题研究计划(KF2021-003)
中国国家铁路集团有限公司科技研究开发计划(SY2021G001,P2021G012)。
关键词
铁路入侵检测
小样本学习
元学习
视频监控
飞桨
railway intrusion detection
few-shot learming
meta-leaming
video surveillance
PaddlePaddle