Smoke and flame combined type automatic detection method based on video image

Abstract

Disclosed is a smoke and flame combined type automatic detection method based on a video image. According to different characteristics of video images in the daytime and at night, flames and smoke are detected at the same time and comprehensively judged by applying different methods. The method is characterized by comprising the steps that the input original video image is firstly processed and judged, whether the video image is the video image at night or the video image in the daytime is judged, and processing and detecting are carried out by combining a corresponding night video image smoke and flame detection algorithm and a corresponding daytime video image smoke and flame detection algorithm. Therefore, the processing efficiency of the method is improved, the false reporting rate and the missing reporting rate are reduced, and stability and accuracy of the smoke and flame detection effect are improved.

Description

technical field [0001] The invention belongs to the technical field of image-type fire detection, and relates to a method for automatic detection of pyrotechnic composites of video images. Background technique [0002] In human's daily life, fire seriously threatens the safety of their lives and property. Therefore, it is of great significance to detect fire danger as early as possible to protect human life and property. [0003] The traditional fire detection method mainly uses some sensors to detect pyrotechnics, mainly including: smoke-sensing fire detectors, temperature-sensing fire detectors, combustible gas sensing detectors and other detection methods. This type of traditional detection method mainly requires close contact with high-heat airflow, solid suspended particles, combustion gas, etc. when a fire occurs in a small space. It is difficult to achieve real-time and rapid fire detection in a large space, and it is difficult Locate the location of the fire. Compa...

AI Technical Summary

Problems solved by technology

This method has a good detection effect and can distinguish smoke from other solid-color objects, but this method is time-consuming in two-dimensional discrete wavelet transform and optical flow based on block matching to extract motion features, and its real-time performance is limited in practical applications.

[0010] Deficiencies in the existing technology: the current fire monitoring method based on video images mainly conducts pyrotechnic analysis from static features such as color and texture of flames and smoke, and dynamic features such as shape changes and motion trends

Often the discriminant features are relatively single, and the false positive and false negative rates are high, especially in complex environments, the detection effect is not very ideal

Images