Rapid video flame detection method based on multi-characteristic fusion

Abstract

The invention discloses a video flame-detecting method based on multi-features fusion, which is characterized in that: a fast Gaussian hybrid model is established and a pixel counter is arranged when a computer reads a first frame image a monitoring site captured by a colored camera; when the computer reads new images of a second frame and the following frames, a fast Gaussian hybrid method is firstly used for carrying out motion detection so as to extract a moving object and then a flame color decision is carried out to the moving object to obtain an alternative flame area; and finally, flicker analysis is carried out on the alternative flame area so as to identify a real flame object. The video flame-detecting method carries out modeling to flame color characteristics, motion characteristics and flickering characteristics in flame areas; various flame detection interfering resources are gradually and rapidly eliminated in accordance with the recognition sequence of motion, color and flickering. The test results show that the method has relatively strong robustness; in addition, based on an AMD 2.04GHz processor, the processing speed can reach 22 frames per second for video images with pixels of 320 multiplied by 240.

Description

technical field [0001] The invention belongs to the technical field of fire detection, and in particular relates to a video flame detection technology that uses digital image processing and pattern recognition methods to extract flame features, thereby judging whether there is a fire flame in a detection scene. Background technique [0002] Traditional fire detection generally uses smoke and temperature detectors to conduct contact detection of smoke and temperature generated in the fire; but when it is in a tall space or outdoor place, the detection distance becomes larger and the detection signal is weak, so the detector cannot Effectively forecast fire danger. Video fire detection technology is to automatically analyze the real-time video sequence collected by the camera using digital image processing and pattern recognition methods to obtain fire information. It can effectively overcome the shortcomings of traditional detection technology in high space and other occasion...

AI Technical Summary

Problems solved by technology

[0006] The present invention proposes a fast video flame detection method based on multi-feature fusion, which comprehensively uses the time-space characteristics such as the color feature, motion feature and stroboscopic feature of the flame area of ​​the flame to effectively improve the real-time performance and reliability of the video flame detection method. Overcome the high algorithm complexity of the existing video flame detection technology, the lack of real-time performance and reliability, and the defects of false positives and false negatives that are prone to occur in complex scenes

Images