Fire video detection and early warning method based on image multi-feature fusion

Abstract

The invention discloses a fire video detection and early warning method based on image multi-feature fusion, and the method comprises the steps: firstly carrying out the preprocessing after an image sequence of a video is obtained; extracting a foreground region, and obtaining a detected candidate region; secondly, extracting static features and dynamic features from the candidate areas, judging whether flames are contained or not by taking the static features and dynamic features as input of an SVM classifier when the flames are detected, and obtaining whether smoke is contained or not afterlogic combination selection and calculation are conducted on feature judgment results when the smoke is detected; finally, if it is detected that flames or smoke exists, carrying out fire judgment according to the growth trend of the flames or smoke; when it is judged that a fire occurs, carrying out fire alarm on the monitoring site, and otherwise carrying out fire alarm only on the background. The method can be combined with an existing monitoring system to be applied to places such as shopping malls and warehouses, the fire detection and early warning cost is reduced, the detection method is good in generalization ability and applicability, reliable fire detection and early warning functions can be provided, and the method has practical value.

Description

technical field [0001] The invention relates to the field of image processing and recognition in computer vision, in particular to a fire video detection and early warning method based on image multi-feature fusion. Background technique [0002] Fire is one of the main threats to the safety of human life and property. With the development of society, the harm caused by fire to human society and the natural environment is becoming more and more serious. Therefore, it has become an important research topic to be able to detect fire accurately and quickly. The current traditional fire detection equipment is mainly based on temperature-sensing and smoke-sensing detectors, but this kind of sensor-based detectors need to reach their detection threshold before alarming, the delay is serious, and because the detection range is small, it needs to be installed in a large space. Large-scale laying can only achieve the detection effect, resulting in high cost. In addition, in tall bui...

AI Technical Summary

Problems solved by technology

The current traditional fire detection equipment is mainly based on temperature-sensing and smoke-sensing detectors, but this kind of sensor-based detectors need to reach their detection threshold before alarming, the delay is serious, and because the detection range is small, it needs to be installed in a large space. Large-scale laying can only achieve the detection effect, resulting in high cost

In addition, in tall buildings, forests, tunnels, etc., due to the dilution of space and airflow, such equipment often cannot detect fires in time and accurately.

[0003] With the development of video surveillance systems, surveillance cameras have spread all over the streets and alleys. Combining image processing and image recognition technologies on the basis of existing video surveillance systems can not only complete the task of fire detection, but also reduce costs and improve anti-interference capabilities. It is well adapted to complex environments with large spaces and a lot of airflow; there are already many image-based fire detection methods, but these methods have the following problems: on the premise of ensuring reliable detection, the delay needs to be further improved; flame detection is the main , the ability to detect smoldering fires is insufficient; the lack of a mechanism for judging whether the detection results constitute a fire and for grading fire alarms results in panic for the public when fire is normally used or under control

Images