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
CN111145234APending Publication Date: 2020-05-12SHENYANG HONGJI ELECTRICAL
7 Cites 4 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHENYANG HONGJI ELECTRICAL
Publication Date
2020-05-12
Patent Text Reader

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.
Need to check novelty before this filing date? Find Prior Art

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