A high-speed railway foreign matter invasion detection device and method based on FPGA and deep learning

A technology for high-speed railways and foreign object invasion, applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve the problems of high staff requirements and low efficiency, achieve enhanced effectiveness, liberate labor, and Difficulties and Pain Points of Foreign Object Intrusion Monitoring

Inactive Publication Date: 2019-04-30
ZHEJIANG UNIV
View PDF4 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing technology mainly relies on the manual identification of cameras at both ends of the railway to distinguish foreign object invasion and illegal intrusion. This method is inefficient, real-time, and has high requirements for staff

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A high-speed railway foreign matter invasion detection device and method based on FPGA and deep learning
  • A high-speed railway foreign matter invasion detection device and method based on FPGA and deep learning
  • A high-speed railway foreign matter invasion detection device and method based on FPGA and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0043] Such as figure 1 As shown, a kind of high-speed railway foreign matter invasion detection device based on FPGA and deep learning provided by the present invention includes the following parts:

[0044] (1) Video acquisition module: take FPGA as the system processing core, adopt SAA7113H video decoding chip, pass I 2 The C bus protocol initializes the configuration of the camera, and connects an external analog PAL / NTAL camera. The camera is arranged along the high-speed railway to collect real-time monitoring video of the high-speed railway track, and compresses and encodes the video signal format;

[0045] Furthermore, the FPGA chip used is the Cyclone IV series EP4CE617C8 developed by Alter Company. This FPGA has rich I / O interfaces and logic units, which can realize the control and processing of each module; the video decod...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a high-speed railway foreign matter invasion detection device and method based on FPGA and deep learning, the device comprises a video acquisition module, an image storage module, two data processing modules and an early warning feedback module, and the video acquisition module is used for acquiring a high-speed railway track monitoring video in real time; the video processing module I is used for training the marked training set by using an improved ICnet neural network to obtain ICnet neural network weights, completing the construction of a track region segmentation model, and dividing a track region of a video into monitoring regions with different security levels; the video processing module II is used for carrying out target detection on the track area by utilizing a target recognition neural network; and the early warning feedback module is used for continuously transmitting each frame of target and image segmentation result to the FPGA for calculation andanalysis, and performing semantic analysis on intrusion behaviors. According to the invention, foreign matter invasion along the railway can be accurately monitored in real time, the actual needs ofthe railway department are met, and the operation safety of the high-speed railway can be effectively ensured.

Description

technical field [0001] The invention relates to the field of detection of foreign matter intrusion on high-speed railways, in particular to a device and method for detecting foreign matter intrusion on high-speed railways based on FPGA and deep learning. Background technique [0002] The rapid increase in the operating mileage and passenger volume of high-speed railways in my country has put forward higher and higher requirements for ensuring the safety of high-speed train operation. Foreign object invasion and illegal intrusion are one of the main sources of emergencies in high-speed railways. Therefore, real-time and effective monitoring and early warning of foreign object intrusion and illegal intrusion is an important basis for ensuring the safety of train operation, improving emergency response capabilities for emergencies, and ensuring efficient operation of high-speed railways. [0003] The existing technology mainly relies on the manual identification of cameras at ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/46G06N3/08
CPCG06N3/08G06V20/41G06V20/58G06V10/267G06V10/44G06V2201/07
Inventor 陈积明孙精辰贺诗波
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap