Flame and dense smoke detection method based on YOLOv3

Abstract

The invention discloses a flame and dense smoke detection method based on YOLOv3. The method comprises the following steps: establishing a flame data set and a dense smoke data set; enhancing data ina random horizontal overturning, cutting and rotating mode; respectively training a flame model and a dense smoke model by using a YOLOv3 algorithm, and fusing the flame model and the dense smoke model into a final model; in an existing video monitoring system, adding a flame and smoke detection module; acquiring a monitoring scene video in real time based on a camera of a video monitoring system,and extracting an image frame from the video based on an ffmpeg framework; detecting each frame of image by adopting a fusion detection model, determining whether flames and dense smoke exist in theimages or not, and marking the positions of the flames and the dense smoke; when a fire is detected, giving an alarm automatically, linking automatic fire-fighting equipment wherein a camera providesreal-time monitoring. According to the invention, effective fire monitoring and danger early warning of important places can be realized; and the invention has the advantages of no dependence on manual characteristics, low detection cost, high detection speed, high accuracy and the like.

Description

technical field [0001] The invention belongs to the cross research field of computer vision and machine learning, and more specifically relates to a flame and smoke detection method based on YOLOv3. Background technique [0002] The occurrence of fire will endanger the safety of people's lives and properties, and fires in important places such as substations, hospitals, libraries, forests, etc. will cause irreparable losses. In these important places, timely identification and early warning of flames are of great significance to the personal safety of professionals and the safety of public property. [0003] When a fire occurs, it is usually accompanied by dense smoke, high temperature, high brightness, etc. Therefore, parameters such as smoke density, flame brightness, and temperature are often used as important parameters for fire detection. Accordingly, smoke sensors, temperature sensors, etc. are often used for fire detection. However, the sensor is susceptible to env...

AI Technical Summary

Problems solved by technology

[0008] Purpose of the invention: In view of the problems that the sensors in the prior art are easily affected by environmental factors, have poor sensitivity and insufficient reliability, the present invention provides a flame and smoke detection method based on YOLOv3

Images