Smoke detection method based on local extreme co-occurrence pattern and energy analysis

Abstract

The invention provides a novel and robust video smoke detection method under a scene with thin smoke. The method is manly composed of three stages, namely a preprocessing stage, a feature extraction stage and an image classification stage. At the preprocessing stage, a background differential algorithm is used to extract a motion foreground region of video frames; then an HSV color space is adopted to act on the motion foreground region to recognize smoke pixels; then a local extreme co-occurrence pattern (LECoP) is used to calculate texture features, and smoke energy analysis is used to calculate energy features; and last, a feature vector training support vector machine (SVM) is used for smoke recognition. It can be seen from an experiment result that the method can effectively detect smoke.

Description

[0001] Yuan Mei technical field [0002] The invention belongs to the technical field of video processing, and in particular relates to a video smoke detection method based on local extremum co-occurrence mode and energy analysis. Background technique [0003] Fire is often accompanied by smoke and fire, so smoke or fire can be used as a detection element for effective early warning of fire to a certain extent. This paper mainly focuses on smoke detection. For the fire detection system, in the early days, fire detection was mainly carried out through smoke sensors, heat sensors, CO sensors, etc., but these methods have many shortcomings. Propagation time, which creates a time delay, which poses major difficulties for fire fighting; moreover, these methods are suitable for inspection indoors, if they are applied to a larger detection area, because the smoke travels in all directions For the sake of this, the performance is greatly degraded. Due to the limitations of traditi...

AI Technical Summary

Problems solved by technology

[0006] The methods mentioned above are effective when the smoke concentration is relatively high, but the effect is obviously reduced when the smoke concentration is relatively low.

Images