Infrared image human detection method and device used in fire fighting scene

An infrared image and human body detection technology, applied in the field of infrared image human body detection, can solve problems such as poor line of sight and rescue omissions, and achieve the effects of reducing rescue omissions, preventing rescue omissions, and improving rescue efficiency

Inactive Publication Date: 2020-03-06
武汉多谱多勒科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the above-mentioned problems that firefighters may miss rescue due to poor sight conditions at the fire scene, and propose an infrared image human body detection method and device used at the fire scene

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
  • Infrared image human detection method and device used in fire fighting scene
  • Infrared image human detection method and device used in fire fighting scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] see figure 1 , a kind of infrared image human body detection method that fire scene uses, comprises the following steps:

[0033] (1) Collect wide dynamic infrared image data;

[0034] (2) Perform high-frequency filtering on wide dynamic infrared images, extract all detailed information, and obtain high-frequency image data in the scene;

[0035] (3) Use a deep convolutional neural network classifier to detect human targets or local human targets in detailed images in infrared images;

[0036] (4) Give sound, light and vibration alarms to the detected targets, and remind fire rescue personnel to provide timely rescue;

[0037] The deep convolutional neural network classifier is obtained by the following steps:

[0038] (1) Collect wide dynamic infrared image data;

[0039] (2) Perform high-frequency filtering on wide dynamic infrared images, extract all detailed information, and obtain high-frequency image data in the scene;

[0040] (3) For samples of human target...

Embodiment 2

[0043] see figure 2 , an infrared image human detection device used in a fire scene, comprising an infrared camera, a high-frequency filter, a processor, an alarm device and a power supply device, the infrared camera, a high-frequency filter, a processor and an alarm device are all electrically connected to the power supply device , Infrared camera, high frequency filter, processor, alarm device and power supply device can be set on wearable and handheld devices. The shooting lens of the infrared camera uses a wide-angle lens. The alarm device is electrically connected with a warning light, and the alarm device is equipped with a buzzer and a small vibration motor inside. The detection device can be set on a wearable or handheld device, which is convenient for firefighters to carry into the fire scene. Compared with traditional rescue, it has Higher level of intelligence greatly improves rescue efficiency and accuracy.

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 an infrared image human detection method and device used in a fire fighting scene. The infrared image human detection method used in the fire fighting scene comprises the stepsof: acquiring wide dynamic infrared image data; performing high-frequency filtering on a wide dynamic infrared image, and extracting all detailed information, so that high-frequency image data in thescene is obtained; detecting a human target or a local human target in a detailed image in an infrared image by utilizing a deep convolutional neural network classifier; and, giving a sound, light and vibration alarm on the detected target, and reminding a fire rescue personnel to rescue in time. According to the infrared image human detection method and device used in the fire fighting scene inthe invention, extracted image information can be processed through the deep convolutional neural network classifier; the human target or the local human target in an image is detected; therefore, thespeed of searching a stranded person by a fireman is increased; infrared imaging has relatively high anti-interference capability, and is difficultly influenced by delaying; therefore, the visible range of the fireman is enlarged; the stranded person can be easily rescued rapidly; and furthermore, a rescue missing condition can be reduced.

Description

technical field [0001] The invention relates to the technical field of intelligent fire protection technology, in particular to an infrared image human body detection method and device used in a fire scene. Background technique [0002] The intelligent fire protection system is an intelligent fire protection wireless alarm network service system integrating GPS (Global Satellite Positioning System), GIS (Geographic Information System), GSM (Wireless Mobile Communication System), computer, network and other modern high-tech. It successfully solves the problem of coordinated development of public facilities such as telecommunications, construction, power supply, and transportation; because the fire command center is connected to the user unit, it changes the traditional, backward, and passive methods of alarming, receiving, and handling, and realizes alarm automation. , Intelligent alarm reception, pre-planning alarm handling, network management, professional service, and mode...

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): G08B17/12
CPCG08B17/125
Inventor 孙国强
Owner 武汉多谱多勒科技有限公司
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