Fire identification method and system based on block chain

Abstract

The invention provides a fire identification method and system based on a block chain. The method comprises the steps of obtaining a standard fire image U1, and segmenting a flame region image from the standard fire image, obtaining a video image P0 sent by each node of the block chain to obtain a negative sample image set Um, splicing the video image P0 and the flame region image to form a spliced image set U2, and combining the spliced image set U2 with a standard fire image U1 to obtain a positive sample image Un, constructing a convolutional neural network structure for fire identification, and constructing a training sample and a test sample by using the negative sample image set Um and the positive sample image set Un, and storing the convolutional neural network model to the block chain network. According to the method, the defects of information islands of traditional fire recognition are overcome through the block chain network, sharing of the training data and the convolutional neural network model is achieved, the convolutional neural network model has very high stability and robustness, and the accuracy of fire recognition is improved.

Description

technical field [0001] The invention belongs to the field of fire identification, and in particular relates to a block chain-based fire identification method and system. Background technique [0002] With the widespread application of security video surveillance systems in various fields and buildings, fire image recognition technology has attracted people's attention and research. Compared with traditional disaster detection technology, visual detection has the advantages of large detection area, short response time, information Rich and intuitive, low maintenance cost and other advantages. [0003] Deep learning based on convolutional neural networks has been successfully applied in character recognition, face recognition and other fields, and fire recognition methods based on convolutional neural networks have also been gradually applied. However, since deep learning requires a large number of data sets, its use The datasets are usually large fire pictures searched on Go...

AI Technical Summary

Problems solved by technology

[0003] Deep learning based on convolutional neural network has been successfully applied in the fields of character identification and face recognition, and the method of fire recognition based on convolutional neural network has gradually been applied. However, since deep learning requires a large amount of data s

Images