Fire-fighting robot intelligent flame combustion state identification method

A flame burning state, fire-fighting robot technology, applied in character and pattern recognition, instruments, artificial life, etc., can solve the problems of lack of image rotation, translation and scaling processing capabilities, single visual angle of processing images, and unrecognizable problems, so as to improve Global optimization ability, strong recognition performance, and the effect of preventing repeated shocks

Pending Publication Date: 2020-12-08
TONGJI UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a fire-fighting robot intelligent flame combustion state identification method to overcome the inability to identify the combustion state in the above-mentioned prior art, the visual angle of the image processing is single, and the lack of sensitive issues such as image rotation, translation, and zoom processing deficiencies in ability

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-fighting robot intelligent flame combustion state identification method
  • Fire-fighting robot intelligent flame combustion state identification method
  • Fire-fighting robot intelligent flame combustion state identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] This embodiment provides a method for identifying a fire-fighting robot's intelligent flame combustion state, including the following steps:

[0042] Image collection step: use the camera to collect a series of candidate images to construct an image data set and obtain a test sample set;

[0043] Segmentation preprocessing step: use the color criterion segmentation rule based on YCbCr color space to process the original image of the test sample set to obtain the corresponding segmented processed image, and then use the Canny operator to perform edge detection on the segmented processed image Processing, extracting the contour of the suspected flame area, and obtaining the edge image;

[0044] Flame feature extraction step: calculate the rotation, translation and scaling invariants of the radial Tchebichef moments of the segmented image and the edge image, obtain the region moment invariants and contour moment invariants respectively, and combine the two to construct a f...

Embodiment approach

[0073] This embodiment also provides an optimal implementation mode, and the specific implementation process is as follows:

[0074] Based on the radial Tchebichef moment invariant and the improved firefly algorithm-wavelet support vector machine, the process flow of the fire robot intelligent flame combustion state recognition method is as follows figure 1 As shown, it specifically includes the following steps:

[0075] S1: Image acquisition

[0076] Use the camera to collect a series of candidate images to build an image data set, and divide the collected image data set into a training sample set and a test sample set. The former is used to build the improved firefly algorithm-wavelet support vector machine model, and the latter is used for Evaluate the model's performance in identifying the combustion state of a flame.

[0077] S2: Segmentation preprocessing

[0078] S21: According to the following formula, use the color criterion segmentation rule based on the YCbCr col...

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-fighting robot intelligent flame combustion state identification method. The method comprises the following steps: carrying out segmentation preprocessing on an original image; calculating radial Tchebichef moment rotation, translation and scaling invariants of the segmented image and an edge image, and constructing a multi-feature composite vector; and inputting the multi-feature composite vector into a pre-established and trained improved firefly algorithm-wavelet support vector machine model, and finally obtaining a classification and recognition result of the flame combustion state. According to the improved firefly algorithm wavelet support vector machine model, an improved step length factor and an improved attraction degree are introduced into a firefly algorithm, iterative search optimization is carried out on wavelet support vector machine kernel parameters, and optimal kernel parameters are obtained. The method is not influenced by the positionand direction of a flame in a visual field scene and the distance between the flame and an image equipment, the algorithm optimization efficiency is high, the recognition performance is high, the combustion state of the classified flame can be effectively recognized, and the fire-fighting robot is assisted in subsequent targeted fire extinguishing operation.

Description

technical field [0001] The invention relates to the field of fire-fighting robots, in particular to an intelligent flame recognition method for a fire-fighting robot. Background technique [0002] With the rapid development of the national economy and urbanization, various large-scale storage buildings for chemicals, high-rise buildings, and long-span commercial buildings have emerged one after another. This type of building usually has the characteristics of high mobility of people, storage of many combustible substances, and intricate internal passages. Once a fire occurs, it is very easy to cause national property losses and casualties. As an intelligent means of fire fighting, firefighting robots can replace firefighters to complete the reconnaissance and information feedback of the fire scene environment when faced with an unknown and complex fire scene environment, and perform fire extinguishing work in the first place. In the process of fire-fighting robots performin...

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): G06K9/62G06T7/12G06T7/13G06T7/90G06N3/00G06N20/20
CPCG06T7/12G06T7/13G06T7/90G06N3/006G06N20/20G06T2207/10004G06T2207/20081G06T2207/20084G06F18/2411G06F18/214
Inventor 杨濛卞永明季鹏成刘广军
Owner TONGJI 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