Fire Detection Algorithm Based on an Improved Strategy of YOLOv5 and Flame Threshold Segmentation
作者机构：School of Information Science and TechnologyHainan Normal UniversityHaikou571158China
出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)
年 卷 期：2023年第75卷第6期
页 面：5639-5657页
核心收录：
学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：supported by Hainan Natural Science Foundation of China(No.620RC602) National Natural Science Foundation of China(No.61966013,12162012) Hainan Provincial Key Laboratory of Ecological Civilization and Integrated Land-sea Development
主 题：YOLOv5 fire safety deep learning flame detection
摘 要：Due to the rapid growth and spread of fire,it poses a major threat to human life and *** use of fire detection technology can reduce disaster *** traditional threshold segmentation method is unstable,and the flame recognition methods of deep learning require a large amount of labeled data for *** order to solve these problems,this paper proposes a new method combining You Only Look Once version 5(YOLOv5)network model and improved flame segmentation *** the basis of the traditional color space threshold segmentation method,the original segmentation threshold is replaced by the proportion threshold,and the characteristic information of the flame is maximally *** the YOLOv5 network model,the training module is set by combining the ideas of Bootstrapping and cross validation,and the data distribution of YOLOv5 network training is *** the same time,the feature information after segmentation is added to the data *** from the training method that uses large-scale data sets for model training,the proposed method trains the model on the basis of a small data set,and achieves better model detection results,and the detection accuracy of the model in the validation set reaches *** results show that the proposed method can detect flame features with faster speed and higher accuracy compared with the original method.
维普期刊数据库