Check patentability & draft patents in minutes with Patsnap Eureka AI!

Subway platform safety monitoring method based on voice recognition

A voice recognition, subway platform technology, applied in stations, voice analysis, railway car body parts, etc., can solve the problems of low installation and maintenance costs, inaccurate recognition, and camera occlusion, etc., to prevent subway dangerous events and application scenarios. and the effect of a wide range of applications and accurate identification

Inactive Publication Date: 2021-02-09
TANGSHAN NORMAL UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the problems existing in the prior art, and provide a method for monitoring subway platform safety based on sound recognition, which can not only identify dangerous events (clamping people) between the train and the platform door gap, but also Identify dangerous events in rail trains and on platforms, which solves the problem of inaccurate recognition caused by blocked cameras, poor picture quality, and video blind spots, and lower installation and maintenance costs

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
  • Subway platform safety monitoring method based on voice recognition
  • Subway platform safety monitoring method based on voice recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] Example: as attached Figure 1-2 As shown, the present invention is a method for monitoring subway platform safety based on sound recognition, including a sound collection step and a sound recognition step,

[0032] Described sound collection step comprises the steps:

[0033] S11. Install sound collection devices in different areas of the platform, and each sound collection device has a corresponding position mark;

[0034] S12. Use the sound collection device to collect the surrounding sounds in real time. Normally, the collected sounds are smooth and noisy;

[0035] S13. After filtering out the sound broadcast by the subway station in the sound collected by the sound collection device, the filtered sound is sent to the sound recognition step;

[0036] Sound recognition mainly recognizes two kinds of sounds, one is to identify abnormal soundtracks, such as sudden screams, explosions, and quarrels, which will suddenly oscillate to stable personnel noisy soundtracks; ...

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 subway platform safety monitoring method based on voice recognition, and mainly relates to the technical field of data services. The sound collection step comprises the steps: S11, installing sound collection devices in different areas of a platform; S12, acquiring surrounding sound in real time by using the sound collection devices; S13, filtering out the sound broadcasted by the subway station in the sounds collected by the sound collection devices, and then transmitting the filtered sounds to a sound recognition step; the voice recognition step comprises the following steps: S21, establishing a normal voice data set; S22, establishing an abnormal distress call sound data set; S23, building a voice recognizer with a call-for-help voice recognition model; S24, training the call-for-help voice recognition model; and S25, identifying the sound transmitted by the sound collection devices by using a sound identifier; according to the invention, the problems of shielding of the camera, poor image quality and inaccurate identification caused by video dead angles are solved, and the installation and maintenance cost is lower.

Description

technical field [0001] The invention relates to the technical field of data services, in particular to a sound recognition-based subway platform safety monitoring method. Background technique [0002] As a low-cost, high-efficiency, comfortable and safe travel mode in the city, subway travel is the preferred means of transportation for ordinary people. Because many people choose to travel by subway, subway trains are crowded public gathering places. Especially in the morning and evening peak hours of work, when people go out to play on holidays, when bad weather affects other travel methods, and during the Spring Festival travel season, there will be a large number of people in subway stations. Once explosions, poisonous gas, fires, stampedes and other emergencies occur, mass deaths and mass injuries will occur. or heavy losses, seriously affecting social order and stability. [0003] How to timely and effectively identify the dangerous status of personnel on the subway pla...

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
IPC IPC(8): G10L25/24G10L25/30G10L25/51B61B1/02
CPCG10L25/24G10L25/30G10L25/51B61B1/02
Inventor 杨霞胡添杰
Owner TANGSHAN NORMAL UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More