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

Forest fire smoke detection method based on wavelet change image enhancement and multiple characteristics

A technology of image enhancement and wavelet change, applied to instruments, character and pattern recognition, computer components, etc., can solve the problems of missed or false positives, low contrast of diffuse smoke images, etc., and achieve low false negative rate and high accuracy High, stable performance

Inactive Publication Date: 2019-05-14
HARBIN UNIV OF SCI & TECH
View PDF0 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 solve the existing forest fire smoke detection method. Due to the strong diffusivity of the smoke itself and the low contrast of the smoke image, the application effect in the actual situation is quite different from the experimental environment, and there will be leakage. In view of the problem of alarm or false alarm phenomenon, a forest fire smoke detection method based on wavelet change image enhancement and multi-features is proposed

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

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0019] The forest fire smoke detection method based on wavelet change image enhancement and multi-feature of the present embodiment, described method comprises:

[0020] Carry out wavelet decomposition on the smoke image, and carry out gray-scale correlation calculation and wavelet coefficient correction on the wavelet coefficient, suppress the noise of the smoke image under the complex background, and enhance the smoke image, by calculating the fractal characteristics of the smoke image and based on the gray-level co-occurrence matrix The image texture features of the image, using the difference in fractal features and texture features between the smoke area and the non-smoke area of ​​the image, and inputting the features into SVM for training, realize the effective detection of forest fire smoke area through machine learning and large sample size.

specific Embodiment approach 2

[0021] Different from Embodiment 1, the forest fire smoke detection method based on wavelet change image enhancement and multi-features in this embodiment, the method includes specific steps as follows:

[0022] Step 1, select the haar wavelet base, and perform wavelet decomposition on the image to obtain the low-frequency components after wavelet decomposition and the high-frequency components in three directions: horizontal, vertical, and diagonal;

[0023] Step 2, using the gray correlation degree between high-frequency components on different scales of the image to correct the wavelet coefficient of the image;

[0024] Step 3, obtain the enhanced image through haar wavelet inverse transform;

[0025] Step 4, select a 5×5 image sliding window, and calculate the fractal characteristics of the enhanced image;

[0026] Step 5, calculating the enhanced image energy, entropy, and contrast features based on the gray-level co-occurrence matrix;

[0027] Step 6, input image featu...

specific Embodiment approach 3

[0028] The difference from the second embodiment is that the forest fire smoke detection method based on wavelet change image enhancement and multi-features of the present embodiment, for the discrete image I, it is decomposed by the haar wavelet base, first in the row of the image Use the low-pass filter and high-pass filter to decompose upward, and then use the low-pass filter and high-pass filter to decompose the row direction decomposition results along the column direction of the image again, LL 1 is the low frequency component, LH 1 is the horizontal component, HL 1 is the vertical component, HH 1 Diagonal components.

[0029] As the original image decomposed by wavelet, repeat the second-level wavelet decomposition process, and continue to decompose the third-level wavelet decomposition of the image in turn.

[0030] After the image is transformed by wavelet, the energy is concentrated on the low-frequency component, and the coefficient amplitude on the high-frequenc...

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 forest fire smoke detection method based on wavelet change image enhancement and multiple characteristics, and belongs to the field of fire smoke detection methods. An existing forest fire smoke detection method has the problem of missing report or false report. The invention discloses a forest fire smoke detection method based on wavelet change image enhancement and multiple characteristics. The method comprises: carrying out wavelet decomposition on the smoke image; gray scale correlation degree calculation and wavelet coefficient correction are carried out on the wavelet coefficient; smoke image noise under a complex background is suppressed; Enhancing smoke images, Fractal features of a smoke image and image texture features based on a gray level co-occurrencematrix are calculated, the difference between the fractal features and the texture features of an image smoke area and a non-smoke area is utilized, the features are input into an SVM for training, and effective detection of a forest fire smoke area is achieved through machine learning and a large sample size. The fire smoke video detection method is stable in performance, low in missing report rate and high in accuracy.

Description

technical field [0001] The invention relates to a forest fire smoke detection method based on wavelet change image enhancement and multi-features. Background technique [0002] Forest fires are extremely destructive and have the characteristics of being difficult to predict and fight. Forest fire is an important aspect of the construction of the national public emergency system. Real-time monitoring of forest fires is very important. Ensuring that fires can be effectively detected and extinguished in the early stages of fire occurrence is the focus of fire prevention. The current forest fire detection is mainly based on ground inspection, satellite detection, electronic monitoring, etc. These methods have certain advantages, but at the same time, they also have some defects such as untimely fire detection, high manpower and material resources consumption, and poor flexibility. It cannot play a role efficiently in real-time fire monitoring. [0003] Intelligent image proces...

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): G06K9/00G06K9/36G06K9/40G06K9/62
Inventor 张玉萍曹蕾
Owner HARBIN UNIV OF SCI & TECH
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com