Intelligent fire monitoring system based on depth learning and method thereof

Abstract

The invention discloses an intelligent fire monitoring system based on depth learning and a method thereof. The system includes an image acquisition module performing real-time monitoring through a binocular camera, an image analysis module utilizing a deep learning model to perform real-time flame detection of monitoring video images, an alarm module used for prompting monitoring personnel to observe the fire in the monitoring video images, a flame positioning module used for receiving the flame pixel position information detected by the deep learning model and mapping the flame pixel position information to the space through the binocular stereo visual positioning algorithm to obtain the flame space position information, and a fixed point fire extinguishing module used for receiving theflame space position information at preset time intervals under the condition that the alarm module has no response and the alarm continues. The system is advantaged in that through combination of depth learning and the camera positioning algorithm for flame identification, a new convolutional kernel module is proposed, feature extraction capability is stronger, alarm can be performed when the flame is detected, and fixed point fire extinguishing for the flame area in the event of no reaction of the monitoring personnel is performed.

Description

technical field [0001] The invention relates to the fields of image recognition and computer vision, in particular to a deep learning-based intelligent fire monitoring system and method thereof. Background technique [0002] Fire is one of the most common disasters. If it cannot be controlled in time in the early stage, it will further cause a large area of ​​fire, which will cause irreparable loss of life and property. Especially in some special non-smoking places, such as bus stations, gas stations, logistics warehouses, etc., once a fire is caused by artificial smoking or other factors, the consequences will be very serious. Therefore, it is very necessary to monitor smoking behavior and detect fires early. [0003] Flame is a physical phenomenon in the early stage of fire. The early flame detection technologies mainly include temperature sensing, smoke sensing and light sensing. They have been widely used, but there are still technical defects such as low sensitivity, e...

AI Technical Summary

Problems solved by technology

However, the image processing unit in the monitoring system still uses manual extraction of the morphological and color features of the flame as the basis for classification, making it difficult to effectively monitor the occurrence of small fires in indoor places and non-smoking places

Images