Smoke and fire intelligent identification method based on programmable photographing technology

An intelligent identification and pyrotechnic technology, applied in the field of programmable cameras, can solve the problems that pyrotechnic intelligent identification technology cannot achieve the ideal working state, high false alarm rate and false alarm rate, and many human factors, so as to avoid video quality degradation and false alarms. The effect of low reporting rate, reducing false negative rate and false positive rate

Active Publication Date: 2010-10-27
重庆市海普软件产业有限公司
View PDF2 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Artificial lookout mainly has the following disadvantages: due to too many human factors, it is easy to cause false positives
[0015] To sum up, the current field of forest fire prevention has adopted different technical means to prevent forest fires, but none of them can eff

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
  • Smoke and fire intelligent identification method based on programmable photographing technology
  • Smoke and fire intelligent identification method based on programmable photographing technology
  • Smoke and fire intelligent identification method based on programmable photographing technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Embodiment 1 Front-end video acquisition device

[0042] Due to the particularity of the field of forest fire prevention, the radius that video surveillance needs to scan is generally more than 3km, and the signal transmission between the monitoring tower and the monitoring center is mostly carried out by wireless communication.

[0043] The traditional method is to use a heavy-duty pan-tilt to carry a camera and a high-power lens to perform 360° stereoscopic scanning to collect video, then encode and compress the video, and then send it back to the monitoring center through microwaves. After decoding the video, it is handed over to an intelligent recognition computer for centralized intelligent pyrotechnic recognition (see Figure 2a ). There are two main weaknesses in this method: First, the video collected by the front-end has been coded and compressed, and the video quality has declined. In addition, the packet loss caused by microwave transmission and other phenomen...

Embodiment 2

[0046] Embodiment 2 Setting the preset position and the running track of the front-end video acquisition device

[0047] Due to the particularity of the field of forest fire prevention, video surveillance needs to scan a radius of more than 3km. In places with no shelter and relatively high transparency, the scanning radius can even reach more than 15km.

[0048] With traditional methods of video surveillance, there are several major weaknesses. For example, the area under video surveillance is a continuous mountain range (see image 3 a), using S-scan (see image 3 b) Regardless of the terrain, distance, whether there is a key monitoring area, it can only be scanned with the same focal length. When monitoring a key area or a distant mountain, a relatively large image cannot be obtained, and the collected video is dynamic. , the image angle of each frame changes, which is very unfavorable for the intelligent recognition of fireworks based on video images.

[0049] By settin...

Embodiment 3

[0053] Embodiment 3 Intelligent identification of day / night

[0054] This technology determines whether the scene captured by the video image is daytime or night by performing random fixed-point sampling average on the image brightness and continuously judging the video image sequence. The specific implementation process is as follows:

[0055] First generate fixed-point number N random numbers R(n) between (0, 1), n=1, 2, ..., N, then utilize these N random numbers to current frame video image X t (i, j) for random sampling, the calculation method of sampling point coordinates is shown in formula (1):

[0056] I(n)=W*R(n), J(n)=H*R(n), n=1, 2, ..., N (1)

[0057] In the formula, W and H are the width and height of the video image respectively; (I(n), J(n)), n=1, 2,..., N are the image coordinates of N random sampling points.

[0058] Then calculate the image X t The average brightness of these N random sampling points in (i, j):

[0059] M t ...

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

Aiming at the defects of the traditional monitoring device for intelligent video monitoring in the field of forest fire prevention, the invention provides a smoke and fire intelligent identification method based on a programmable photographing technology, which can accurately and quickly analyze and judge fire in forest arrears. The smoke and fire intelligent identification method comprises the steps of: setting preset position of each monitored point which needs to be monitored by a front monitoring video acquisition device and setting time within which the front video acquisition device stays at each preset position; sequentially acquiring the video image information of each preset position step by step by the front video acquisition device; intelligently identifying daylight and night; intelligently identifying daylight/night smoke and fire detection; analyzing and processing pre-detected results by using secondary discrimination technology. The method has the advantages of high accuracy, low rate of missing alarm, low rate of false alarm and the like.

Description

technical field [0001] The invention relates to a programmable camera method in forest firework monitoring and intelligent early warning, in particular to a firework intelligent identification method based on programmable camera technology. Background technique [0002] Various technical means have been adopted in various parts of the world to prevent the occurrence of forest fires. [0003] Canada uses electromagnetic rays from satellites to detect the temperature of forest areas. When it detects that the local temperature in a forest area rises to 150°C-200°C and the infrared wavelength reaches 3.7 microns, it is a sign of a fire. Measure the specific temperature immediately and take timely measures. fire prevention. [0004] The United States uses the "Land" satellite to orbit the earth about 705 kilometers above the ground to detect high-temperature areas, dense smoke areas and fire sites on the ground. At the same time, the United States also uses unmanned forest fire...

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): G08B17/00H04N5/232
Inventor 陈秀祥
Owner 重庆市海普软件产业有限公司
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