Method for judging burning area of object in complex environment

Abstract

The invention belongs to the technical field of fire detection, solves a problem that judgment for a burning area in the prior art is too complicated and inaccurate, and particularly relates to a method for judging a burning area of an object in a complex environment. The method comprises the steps of firstly performing image preprocessing, then calculating an expected maximum return value of a flame image sample, then building a weight updating equation of a deep learning network, then training the deep learning network, and finally recognizing the flame by using the trained deep learning network. Compared with the prior art, the method has the characteristic of deep learning and is comprehensive in burning area judgment, high in operability and more accurate and faster in judgment for aburning area.

Description

technical field [0001] The invention belongs to the technical field of fire detection, and in particular relates to a method for judging the burning area of ​​an object in a complex environment. Background technique [0002] Fire is one of the most destructive disasters. On a global scale, fires that occur every year will have a very large impact on the economy, society, and environment. When the background environment is relatively complex, the change of the fire will be more irregular, and the combustion will present three-dimensional and multi-layered characteristics. The fire is difficult to control, which will cause certain difficulties for fire fighting, and therefore will bring more serious losses and risks. [0003] At present, most places use sensor detection, such as temperature-sensitive, smoke-sensitive, light-sensitive and composite sensors. These sensors are widely used in fire monitoring, but they have not completely solved the problem that traditional monito...

AI Technical Summary

Problems solved by technology

[0006] Chinese patent CN201885804U and Chinese patent CN201844880U belong to the fire detection technology in the infrared band. They use dual-wavelength infrared light to detect flames. The dual wavelengths are 4.3 microns and 5.0 microns respectively. On the basis of the former, a 3.8-micron wavelength infrared sensor is added to improve the detection accuracy of flames; Chinese patent CN202195883U and Chinese patent CN201191222 belong to the fire detection technology in the ultraviolet band, and the system judges whether there is a flame by processing the collected ultraviolet radiation signals; Chinese patent CN202306757U belongs to the multi-band composite detection technology, which uses color cameras and near-infrared cameras to capture color video images and near-infrared video images of the monitoring site to determine the presence or absence of flames; compared with visible light band sensors, infrared and ultraviolet sensors Usually expensive, which limits its widespread use

[0008] Chinese patent CN101106727 adopts a color CCD camera system, adopts the image difference method, uses the flame color template obtained by statistics, and combines the characteristics of fire jumping, flickering, and instability to judge the flame; Chinese patent CN101493980 discloses a method based on multi-feature fusion Video flame detection method, this method is based on the mixed Gaussian model technology to detect moving targets, and combined with the color characteristics of the flame, motion characteristics and flickering characteristics of the flame area to model, and step by step according to the recognition sequence of motion, color, and flickering For flame detection, the above two patents have simple criteria. For objects similar to flame color, dithering at a certain frequency may cause false alarms.

[0009] The image flame detection systems mentioned above all use relatively expensive professional CCD cameras, and the global CMOS image sensor market will achieve substantial growth in the fields of PC cameras, mobile communication markets, digital cameras, and video camera markets at the beginning of the 21st century. At present, CMOS sensors will be the mainstream, and video flame detection technology for CMOS sensors is also rare.

Images