Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fire hazard early warning method based on video image

A video image and fire early warning technology, applied in fire alarms, alarms, instruments, etc., can solve problems such as inability to respond to fire, easy aging of fire detectors, failure to reach thresholds, etc.

Inactive Publication Date: 2017-07-14
天津安平易视智能影像科技有限公司
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 1. Traditional fire detectors need the smoke concentration or temperature in the environment to reach a certain threshold before they can issue an alarm. At this time, the fire is often already large or even difficult to control
The consequences are especially serious where the alarm is far from the fire source
[0004] 2. Due to factors such as particle concentration and temperature in tall spaces and open spaces often do not reach the alarm threshold of traditional fire detectors, traditional fire detectors cannot work properly in these spaces
[0005] 3. Traditional fire detectors are prone to aging and need to be replaced regularly, otherwise they cannot respond to fires in a timely and effective manner
[0006] 4. In the traditional fire detection system, the activation of the fire extinguishing system often causes damage to objects and facilities in the adjacent area, and after the alarm, relevant personnel must go to the scene to confirm, which is not only inconvenient, but also delays the timing of fire extinguishing

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 early warning method based on video image
  • Fire hazard early warning method based on video image
  • Fire hazard early warning method based on video image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0030] Such as figure 1 As shown, the present invention provides a kind of fire early warning method based on video image, comprises the following steps:

[0031] Step one 101, collecting video images to obtain video frames;

[0032] Step 2 102, selecting 1000 flame samples in the video frame; 1000 smoke samples and 4000 non-smoke and non-fire negative samples to generate pre-check values;

[0033] Step 3 103, taking one frame every 10 frames for the video frame to generate a detection frame; the frame rate of the video frame in the step 3 is 25 frames / second.

[0034] Step four 104, calculating the flame feature value generated by each pixel in the detection frame; wherein, the flame feature value is used to represent the spatio-temporal feature of the video image block through the time-domain normalized covariance descriptor.

[0035] R i,j,n =Red(i,j,n),

[0...

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 hazard early warning method based on a video image. The method comprises the following steps of step 1, collecting video images to obtain video frames; step 2, selecting 1000 flame samples, 1000 smoke samples and 4000 non-smoke non-fire negative samples in the video frames for generating pre-test values; step 3, generating detection frames by selecting one of the video frames at every 10 frames; step 4, calculating the flame of each pixel point in the detection frames to generate a flame characteristic value; and step 5, calculating the smoke of each pixel point in the detection frames to generate a smoke characteristic value; and step 6, selecting 10 flame characteristic values to calculate 55 flame determination dimensions, and at the same time, selecting 10 smoke characteristic values to calculate 55 smoke determination dimensions and other steps. The method timely monitor the video image and accurately and rapidly determine the fire hazard condition, so as to effectively guarantee the personal and property safety.

Description

technical field [0001] The invention relates to a smoke detection method, in particular to a video image-based fire early warning method. Background technique [0002] Fire is one of the major disasters in daily life, and timely and accurate fire warning is very important. There are some problems in the effect of the existing pyrotechnic detection system. [0003] 1. Traditional fire detectors need the smoke concentration or temperature in the environment to reach a certain threshold before they can issue an alarm. At this time, the fire is often already large or even difficult to control. The consequences are particularly serious where the alarm is far from the fire source. [0004] 2. Due to factors such as particle concentration and temperature in tall spaces and open spaces, the threshold value of traditional fire detectors is often not reached, which leads to the failure of traditional fire detectors to work normally in these spaces. [0005] 3. Traditional fire dete...

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): G08B17/00G06K9/00
CPCG08B17/00G06V20/47
Inventor 华卫中
Owner 天津安平易视智能影像科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products