Fire smoke detection method based on binocular vision

A binocular vision, smoke detection technology, applied in image data processing, instrument, character and pattern recognition, etc., can solve the problems of long response time of fire smoke alarm, untimely alarm, low smoke concentration, etc., to improve the accuracy, The effect of reducing false alarms and increasing accuracy

Pending Publication Date: 2020-05-12
SHENYANG HONGJI ELECTRICAL
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the object of the present invention is to provide a fire smoke detection method based on binocular vision, to solve the fire smoke alarm response time in the prior art is long, the alarm is not timely when the smoke concentration is low

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be further explained below in conjunction with specific embodiments, but the present invention is not limited thereto.

[0021] The fire smoke detection method based on binocular vision comprises the following steps:

[0022] S1: Use the infrared thermal imaging camera in binocular vision to monitor the temperature in the scene. If the measured temperature in the scene exceeds the preset temperature value Tmax, start the visible light camera;

[0023] S2: Use the visible light camera to collect the video in the scene and perform single-frame processing, and set the first frame image collected as the background frame;

[0024] S3: Row and column sampling is performed on each frame of the image, and the original image is proportionally reduced to obtain the image M to be processed. Then, the image M is subjected to YUV space conversion, and the pixel value of the corresponding pixel point of the current frame and the background frame is subtract...

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 fire smoke detection method based on binocular vision, and the method comprises the steps of firstly monitoring the temperature in a scene through employing an infrared thermal imaging camera, and starting a visible light camera if a temperature measurement value in the scene exceeds a preset temperature value Tmax; then, using the visible light camera for collecting a video in the scene, carrying out the single-frame processing, obtaining a target candidate area external rectangular frame and a target candidate area image, and then carrying out bilinear interpolationsampling on the target candidate area image, and obtaining an image Q with the unified size; then, extracting the color information and texture features of the image Q, and obtaining the feature vectors; and finally, inputting the feature vector into a BP classifier to obtain a judgment result of whether smoke exists in the target candidate region or not. The fire smoke detection method based onbinocular vision is small in data processing amount and high in smoke detection accuracy.

Description

technical field [0001] The invention relates to the field of smoke detection, and in particular provides a fire smoke detection method based on binocular vision. Background technique [0002] Fires seriously endanger the safety of the people themselves and their property. In the prior art, the detection of fires is usually achieved through the detection of smoke. Visible light cameras are usually used for smoke detection. Each frame of image is processed, analyzed and identified, and the amount of processed data is relatively large, which is relatively time-consuming. In addition, the accuracy of smoke detection using existing image processing methods is low. [0003] Therefore, it has become an urgent problem to propose a fire smoke detection method based on binocular vision to quickly detect the smoke in the early stage of fire. Contents of the invention [0004] In view of this, the object of the present invention is to provide a fire smoke detection method based on bi...

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): G06T7/41G06T7/90G06K9/62
CPCG06T7/41G06T7/90G06T2207/10024G06F18/2411
Inventor 马胤刚张冠男张森森
Owner SHENYANG HONGJI ELECTRICAL
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