Fire smoke detection method based on motion feature hybrid deep network

Abstract

The invention provides a fire smoke detection method based on a motion feature hybrid deep network, which is used for solving the technical problem of low detection precision of video smoke in a complex scene. The method comprises the following steps: firstly, acquiring a data set from a video image library, and dividing the data set into a training set and a test set; secondly, constructing a motion feature hybrid deep network, inputting the training set into the motion feature hybrid deep network for training to obtain a motion feature hybrid deep network model, and testing the motion feature hybrid deep network model by using the test set; then, obtaining a to-be-detected video sequence, and processing a detected video by using a motion area detection algorithm to obtain a video motion image; and finally, inputting the motion image into the motion feature mixed deep network model, outputting a detection result, and completing video smoke detection. According to the invention, continuous transmission of smoke characteristics can be realized on the whole video stream, the timeliness of smoke detection is improved, and the false alarm rate of smoke early warning is reduced.

Description

technical field [0001] The invention relates to the technical field of fire early warning, in particular to a fire smoke detection method based on a motion feature mixed deep network. Background technique [0002] Smoke is a characteristic of the early stage of a fire, and rapid and efficient detection and identification of fire smoke is one of the important ways of fire early warning. The traditional smoke detection method is mainly based on smoke detectors, which can achieve fire warning to a certain extent. Warning against fire. With the development of video image technology and computer vision technology, smoke detection algorithms based on video images have been widely studied. [0003] Literature [Peng Y, Wang Y. Real-time forest smoke detection using hand-designed features and deep learning [J]. Computers and Electronics in Agriculture, 2019, 167: 105029.] Use the manual design algorithm to extract the suspected smoke area and input it Improved deep neural network ...

AI Technical Summary

Problems solved by technology

[0004] In view of the deficiencies in the above-mentioned background technology, the present invention proposes a fire smoke detection method based on a motion feature mixed deep network, which solves the technical problems of low detection accuracy, high false alarm rate and missed detection rate of video smoke in complex scenes

Images