Early fire smoke video detection method based on wavelet energy
A technology of video detection and wavelet energy, which is applied to fire alarms, fire alarms, instruments, etc. that rely on radiation effects, and can solve problems such as system robustness, poor real-time performance, high false alarm rate, and single identification criteria , to achieve the effect of fast detection speed, obvious effect and low false alarm rate
Active Publication Date: 2018-04-10
JIANGSU UNIV OF TECH
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Traditional fire detectors are difficult to reach the top of the room due to the smoke generated in the event of a fire, and are easily affected by ventilation speed, on-site interference, noise, etc., and cannot perform early fire detection and alarm in time
Combining the characteristics of relatively single fire image recognition criteria at home and abroad, high rates of false positives and false positives, poor system robustness, and poor real-time performance, and aiming at the characteristics of fire smoke images with strong real-time performance and large amount of feature information, fully study the characteristics of early fire smoke. Image features, combined with image processing technology and wavelet transform, propose an early fire smoke video detection method based on wavelet energy, in order to achieve the purpose of early fire alarm
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of the embodiments of the present invention, rather than all embodiments; based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work, all belong to the protection scope of the present invention .
[0033] Such as figure 1 As shown, an early fire smoke video detection method based on wavelet energy includes the following steps:
[0034] S101. Read the RGB video image to be tested, and convert the RGB video image into a grayscale video image;
[0035] Specifically, in step S101, specifically include:
[0036] Calculate the total numb...
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
Login to View More Abstract
The invention belongs to the technical field of smoke detection, and in particular relates to an early fire smoke video detection method based on wavelet energy. The technical problem solved is: providing an early fire smoke video detection method which is simple in operation, high in detection speed and significant in effect, and not only effectively eliminates the influence of non-smoke interference such as people and automobiles, but also has a good detection effect. The adopted technical scheme includes the steps of reading of a RGB video image to be detected, and converting the RGB videoimage into a grayscale video image; detecting a motion foreground image and converting the motion foreground image into a motion foreground binary image; performing product operation on a current frame image of the video and the motion foreground binary image to obtain a frame1 image, performing wavelet decomposition on the frame1 image, and calculating an energy value of the image; and determining the rate of change of the energy value of the image for two consecutive detection periods, and detecting whether smoke is generated in the region of the RGB video image to be detected. The method ofthe invention is applicable to the detection field.
Description
technical field [0001] The invention belongs to the technical field of smoke detection, in particular to an early fire smoke video detection method based on wavelet energy. Background technique [0002] Fire is one of the most common disasters, which directly endangers people's lives and properties and causes environmental pollution. Therefore, it is a key research content in the field of fire prevention and control technology to monitor it in real time and effectively to minimize the loss caused by fire, and the automatic fire detection system plays a vital role. [0003] Traditional fire detectors are difficult to reach the top of the room due to the smoke generated in the event of a fire, and are easily affected by ventilation speed, on-site interference, noise, etc., and cannot perform early fire detection and alarm in time. Combining the characteristics of relatively single fire image recognition criteria at home and abroad, high rates of false positives and false posi...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G08B17/12
CPCG08B17/125
Inventor 王海峰章怡范鑫
Owner JIANGSU UNIV OF TECH