Unlock instant, AI-driven research and patent intelligence for your innovation.

Video flame detection method based on multi-feature fusion

A multi-feature fusion, flame detection technology, applied in instruments, calculations, character and pattern recognition, etc., can solve the problem of low reliability of the algorithm, and achieve the effect of high accuracy, good application prospects and strong robustness

Active Publication Date: 2019-12-06
FUJIAN CHUANZHENG COMM COLLEGE
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Video flame detection technology is easily affected by complex scenes, interference objects similar to flame color and lighting conditions, which makes the reliability of the algorithm not high, and is still in the initial stage of research

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
  • Video flame detection method based on multi-feature fusion
  • Video flame detection method based on multi-feature fusion
  • Video flame detection method based on multi-feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0077] Please refer to figure 1 , the present invention provides a kind of video flame detection method based on multi-feature fusion, it is characterized in that, comprises the following steps:

[0078] Step S1: read the first frame of image;

[0079] Step S2: Initialize the selective background update model and set the pixel accumulator;

[0080] Step S3: read the next frame of image;

[0081] Step S4: Carry out moving object detection based on the selective background update model, and determine whether there is a moving object, and if so, perform color detection on the moving object, otherwise return to step S3;

[0082] When there is a fire, the flame presents a dynamic characteristic of changing and developing from scratch. In this system, firstly, the moving foreground object is segmented through the moving object detection, and the static in...

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 video flame detection method based on multi-feature fusion. First, an improved selective background update model is used to obtain moving foreground targets in video images, and then suspicious flame targets are extracted through flame color detection and identification, and then the frequency of flames is analyzed. Flash features, sharp corner features, circularity features, area growth features and overall movement features, and finally a detection and recognition method based on the fusion of multiple dynamic features of flames based on Analytic Hierarchy Process (AHP). The invention can accurately and effectively detect and recognize the flame information in the video.

Description

technical field [0001] The invention relates to the field of flame detection, in particular to a video flame detection method based on multi-feature fusion. Background technique [0002] Visual flame detection is one of the topics of great theoretical significance and practical value in machine vision, and it is a research hotspot in the field of flame detection at present. The flame monitoring method based on video images can effectively overcome the disadvantages of traditional non-contact detectors such as small detection distance, large environmental impact and single fire criterion, which can help improve the accuracy and reliability of fire detection. [0003] At present, many scholars have proposed many detection methods on flame image detection and recognition. The following are the existing references on flame image detection: [0004] [1] Bugaric M, Jakovcevic T, Stipanicev D.Adaptive estimation of visual smoke detection parameters based on spatial data and fire r...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/46G06F18/2411G06F18/253
Inventor 曾思通刘克陈天炎王水发张伟张志川
Owner FUJIAN CHUANZHENG COMM COLLEGE