Fire hazard identification method and system based on artificial intelligence and binocular vision

A technology of binocular vision and artificial intelligence, applied to fire alarms that rely on radiation, fire alarms, radiation pyrometry, etc., can solve the problem of easy misdetection of objects, low accuracy and reliability, and flame Problems such as low extraction accuracy can be achieved to reduce the possibility of fire misjudgment, improve accuracy, and reduce the layout scale

Pending Publication Date: 2021-08-24
SHANGHAI DIANJI UNIV
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above-mentioned documents are all based on the detection model to detect two-dimensional images, and a large amount of sample data is needed to train the detection model. This process depends on the sample data. When the sample data is unbalanced, the detection model often falls into a local optimum, resulting in The extraction accuracy of the flame in the two-dimensional image is not high, and the flame area cannot be fully detected for the place where the edge of the flame is sparse, or the place covered by smoke, and the object with a similar color to the flame is easy to be misdetected. and less reliable

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
  • Fire hazard identification method and system based on artificial intelligence and binocular vision
  • Fire hazard identification method and system based on artificial intelligence and binocular vision
  • Fire hazard identification method and system based on artificial intelligence and binocular vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] A fire recognition method based on artificial intelligence and binocular vision, which is used for fire monitoring in the area to be tested. A binocular camera and an infrared temperature sensor probe are installed near the area to be tested, such as figure 1 , methods include:

[0047] 1) Use the calibrated binocular camera to shoot the binocular image of the area to be tested;

[0048] 2) Use the target detection network model to judge whether there is a flame in the binocular image to be tested, if so, output the flame area image in the binocular image to be tested, otherwise perform step 1);

[0049] 3) Use the binocular vision 3D reconstruction technology to perform 3D space positioning on the image of the flame area, and obtain the 3D information of the image of the flame area;

[0050] 4) Calculate the optimal field angle of the infrared temperature sensor according to the three-dimensional information of the flame area image and the three-dimensional coordinate...

Embodiment 2

[0067] A fire recognition system based on artificial intelligence and binocular vision, including a binocular camera module, an image detection module, a pose adjustment module, an infrared temperature measurement module and a fire recognition module;

[0068] The binocular camera module is used to use the calibrated binocular camera to shoot the binocular image of the area to be tested;

[0069] The image detection module is used to segment the flame area image from the binocular image to be tested by using the target detection network model;

[0070] The pose adjustment module includes a three-dimensional reconstruction unit and a pose calculation unit. The three-dimensional reconstruction unit uses the binocular vision three-dimensional reconstruction technology to perform three-dimensional space positioning on the image of the flame area to obtain the three-dimensional information of the image of the flame area. Three-dimensional information and three-dimensional coordinat...

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 relates to a fire hazard identification method and system based on artificial intelligence and binocular vision. The method comprises the following steps: 1) obtaining a to-be-detected binocular image of a to-be-detected area; 2) using the target detection network model to determine whether flames exist in the binocular image to be detected, if yes, outputting a flame area image, and if not, executing the step 1); 3) performing three-dimensional space positioning on the flame area image to obtain three-dimensional information of the flame area image; 4) calculating the optimal field angle of the infrared temperature measurement sensor; 5) controlling the infrared temperature measurement sensor to measure the temperature of the flame area at the optimal field angle to obtain a temperature measurement value of the flame area; and 6) judging whether the temperature measurement value exceeds a set value, if so, judging that a fire occurs in the flame area, otherwise, judging that no fire occurs in the flame area, and executing the step 1). Compared with the prior art, the system is good in accuracy, high in reliability, high in safety, wide in application range and low in layout and maintenance cost, flame positioning is provided, and the fire extinguishing efficiency is improved.

Description

technical field [0001] The invention relates to the field of artificial intelligence machine vision, in particular to a fire recognition method and system based on artificial intelligence and binocular vision. Background technique [0002] When a fire occurs, if it can be detected and called in time, the loss can be minimized. Existing fire detection methods mainly include sensor detection method and image detection method. [0003] The sensor detection method mainly uses sensors to monitor the temperature of the detection area, but the installation process and detection range of the sensors are restricted by space. When performing indoor detection, it is necessary to arrange sensors at multiple points and in a full range to ensure that no corner is missed, even in the flames. It can only be detected when a certain scale is formed. The monitoring is not timely, the layout is troublesome, the installation requirements are high, and the cost is high. When performing outdoor d...

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): G08B17/12G06T7/70G06T7/80G06T7/11G06T15/00G01J5/00
CPCG08B17/125G06T7/70G06T7/85G06T7/11G06T15/00G01J5/0018G06T2207/10012
Inventor 陈飞宇张晓宇刘哲昊冯嘉琳
Owner SHANGHAI DIANJI 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