Fire identification system based on multi-feature fusion

Abstract

The invention provides a fire identification system based on multi-feature fusion. The system comprises a detection device, an acquisition device, a mobile device, a processing device, an adjusting device and a processor, and the detection device is used for acquiring data of a fire scene; the acquisition device is used for acquiring fire data; the mobile device is used for adjusting the positions of the detection device, the mobile device and the adjusting device; the adjusting device is used for adjusting the posture of the moving device; and the processing device is used for processing acquired data of the acquisition device. According to the invention, through cooperation of the detection device and the mobile device, coordination between obstacle avoidance and accurate movement and detection is effectively improved under the conditions of a fire disaster and poor visibility; in addition, heat dissipation of the unmanned aerial vehicle can be reduced by releasing water mist, the unmanned aerial vehicle is protected, and fire spreading caused by air flow in a fire scene is reduced.

Description

technical field [0001] The invention relates to the technical field of fire rescue, in particular to a fire recognition system based on multi-feature fusion. Background technique [0002] In order to avoid major accidents caused by fire, people have adopted many fire early detection methods, automatic fire monitoring methods, such as smoke and temperature detectors. The biggest shortcoming is the distance limitation. The effective detection distance is small, and personnel are required to go to the scene after the alarm. Confirmation is not conducive to early detection of fire, and in a large space environment, it is often easily affected by factors such as space height, temperature and humidity, and cannot effectively function. [0003] Such as CN112597975B prior art discloses a kind of video-based fire smoke and spill detection method and system, in order to guarantee people's life and property safety, we have built more than 200,000,000 cameras. How to make full use of t...

AI Technical Summary

Problems solved by technology

In order to overcome the shortcomings of traditional detectors, many researchers have proposed a video-based flame detection method. This method achieves the purpose of fire detection and alarm by analyzing the color, time and space changes of ordinary color video input. , has the advantages of real-time and low cost; the current fire recognition algorithm based on video usually combines static features with dynamic features, and comprehensively judges multiple interrelated features in the fire, in order to more accurately reflect the real fire phenomenon The comprehensive features of the integrated features can improve the recognition rate and make the detection method more intelligent. Although there are many studies on fusion algorithms, most of them use static features as the criterion for whether a fire occurs, and there are too few dynamic features. The false alarm rate of the productized fire detection system is high

[0004] In order to solve the common problems in this field, such as high false alarm rate, poor detection accuracy, lack of feature fusion means, undetectable corner position and lack of early warning means, etc., the present invention is made

Images