基于特征工程的S-FCN火灾图像检测方法  

S-FCN fire image detection method based on feature engineering

作　　者：李海 熊升华 孙鹏[2] LI Hai;XIONG Shenghua;SUN Peng(College of Civil Aviation Safety Engineering,Civil Aviation Flight University of China,Guanghan Sichuan 618307,China;School of Public Security Information Technology,Criminal Investigation Police University of China,Shenyang Liaoning 110036,China)

机构地区：[1]中国民用航空飞行学院民航安全工程学院,四川德阳618307 [2]中国刑事警察学院公安信息技术与情报学院,辽宁沈阳110036

出　　处：《中国安全科学学报》2024年第9期191-201,共11页China Safety Science Journal

基　　金：中央高校基本科研业务费专项资金资助(Q2023-051,J2023-062);四川省科技厅重点研发计划项目(2022YFG0213);民机火灾科学与安全工程四川省重点实验室自主资助项目(MZ2022JB03)。

摘　　要：针对复杂背景下火灾图像检测深度学习算法存在的计算复杂度高、检测实时性差等问题,提出一种基于特征工程的单隐层全连接网络(S-FCN)火灾图像检测方法。首先,从图像中提取多色彩空间颜色特征,并使用互信息量进行多色彩空间颜色特征降维;其次,简化深度学习模型的网络结构,将单隐层全连接网络作为其主干网络,其中,多色彩空间下的颜色特征能够更好地表征火灾烟雾与火焰,多色彩空间颜色特征降维能够有效降低输入特征的冗余度,单隐层全连接网络能够有效减少模型在传递过程中的参数数量;最后,将该方法在真实的复杂背景火灾图像数据集上进行试验评估。结果表明:所提方法取得的检测精度为93.83%,取得的检测实时性帧率为10869帧/s,能够实现复杂场景下高精度、高速度的火灾图像检测。The S-FCN fire image detection method based on feature engineering was proposed to address the issues of high computational complexity and poor real-time performance of deep learning algorithms for fire image detection in complex backgrounds.Firstly,this method extracted color features from images in multiple color spaces and reduced the dimensionality of these features using mutual information.Secondly,the network structure of the deep learning model was simplified by using a single hidden layer of a fully connected network as its backbone.The color features in multiple color spaces can better represent fire smoke and flames,and reducing the dimensionality of color features in multiple color spaces effectively reduces the redundancy of input features.The single hidden layer fully connected network can significantly reduce the number of parameters during the model propagation process.Finally,this method was evaluated on a real and complex background fire image dataset.The experimental results show that the detection accuracy achieved by this method is 93.83%,and the real-time frame rate is 10869 f/s.This method achieves high accuracy and high-speed fire image detection in complex scenes.

关 键 词：特征工程 单隐层全连接网络(S-FCN) 火灾图像 检测方法 色彩空间 特征降维 

分 类 号：X932[环境科学与工程—安全科学]