A Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs

The efficiency and the effectiveness of railway intrusion detection are crucial to the safety of railway transportation. Most current methods of railway intrusion detection or obstacle detection are inappropriate for large-scale applications due to their high cost or limited coverage. In this study,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yao Wang, Peizhi Yu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	intrusion detection SSD improved MobileNet feature fusion module embedded GPU Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/56974943a8054710992b9d947449fd78
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:56974943a8054710992b9d947449fd78
record_format	dspace
spelling	oai:doaj.org-article:56974943a8054710992b9d947449fd782021-11-11T19:14:08ZA Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs10.3390/s212172791424-8220https://doaj.org/article/56974943a8054710992b9d947449fd782021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7279https://doaj.org/toc/1424-8220The efficiency and the effectiveness of railway intrusion detection are crucial to the safety of railway transportation. Most current methods of railway intrusion detection or obstacle detection are inappropriate for large-scale applications due to their high cost or limited coverage. In this study, we present a fast and low-cost solution to intrusion detection of high-speed railways. As the solution to heavy computational burdens in the current convolutional-neural-network-based detection methods, the proposed method is mainly a novel neural network based on the SSD framework, which includes a feature extractor using an improved MobileNet and a lightweight and efficient feature fusion module. In addition, aiming to improve the detection accuracy of small objects, the feature map weights are introduced through convolution operation to fuse features at different scales. TensorRT is employed to optimize and deploy the proposed network in the low-cost embedded GPU platform, NVIDIA Jetson TX2, to enhance the efficiency. The experimental results show that the proposed methods achieved 89% mAP on the railway intrusion detection dataset, and the average processing time for a single frame was 38.6 ms on the Jetson TX2 module, which satisfies the need of real-time processing.Yao WangPeizhi YuMDPI AGarticleintrusion detectionSSDimproved MobileNetfeature fusion moduleembedded GPUChemical technologyTP1-1185ENSensors, Vol 21, Iss 7279, p 7279 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	intrusion detection SSD improved MobileNet feature fusion module embedded GPU Chemical technology TP1-1185
spellingShingle	intrusion detection SSD improved MobileNet feature fusion module embedded GPU Chemical technology TP1-1185 Yao Wang Peizhi Yu A Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs
description	The efficiency and the effectiveness of railway intrusion detection are crucial to the safety of railway transportation. Most current methods of railway intrusion detection or obstacle detection are inappropriate for large-scale applications due to their high cost or limited coverage. In this study, we present a fast and low-cost solution to intrusion detection of high-speed railways. As the solution to heavy computational burdens in the current convolutional-neural-network-based detection methods, the proposed method is mainly a novel neural network based on the SSD framework, which includes a feature extractor using an improved MobileNet and a lightweight and efficient feature fusion module. In addition, aiming to improve the detection accuracy of small objects, the feature map weights are introduced through convolution operation to fuse features at different scales. TensorRT is employed to optimize and deploy the proposed network in the low-cost embedded GPU platform, NVIDIA Jetson TX2, to enhance the efficiency. The experimental results show that the proposed methods achieved 89% mAP on the railway intrusion detection dataset, and the average processing time for a single frame was 38.6 ms on the Jetson TX2 module, which satisfies the need of real-time processing.
format	article
author	Yao Wang Peizhi Yu
author_facet	Yao Wang Peizhi Yu
author_sort	Yao Wang
title	A Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs
title_short	A Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs
title_full	A Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs
title_fullStr	A Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs
title_full_unstemmed	A Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs
title_sort	fast intrusion detection method for high-speed railway clearance based on low-cost embedded gpus
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/56974943a8054710992b9d947449fd78
work_keys_str_mv	AT yaowang afastintrusiondetectionmethodforhighspeedrailwayclearancebasedonlowcostembeddedgpus AT peizhiyu afastintrusiondetectionmethodforhighspeedrailwayclearancebasedonlowcostembeddedgpus AT yaowang fastintrusiondetectionmethodforhighspeedrailwayclearancebasedonlowcostembeddedgpus AT peizhiyu fastintrusiondetectionmethodforhighspeedrailwayclearancebasedonlowcostembeddedgpus
_version_	1718431585109278720

A Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs

Ejemplares similares