面向森林火灾烟雾识别的深度信念卷积网络
2020-08-07杜嘉欣常青刘鑫
杜嘉欣 常青 刘鑫



摘 要: 对于CNN的图像识别,采用随机初始化网络权值的方法很容易收敛达到局部最优值。针对林火中的烟雾图像识别,提出一种结合无监督和有监督学习的网络权值预训练算法。首先通过使用DBN预学习得到的特征初始化CNN的权值;然后通过卷积、池化等操作,提取训练样本的特征,并采用全连接网络对特征进行分类;最后计算分类损失函数并优化网络参数。实验的训练结果显示,基于DBN?CNN的森林火灾烟雾识别的准确率达到了98.5%,相比于其他算法其准确率更高。
关键词: 深度信念网络; 森林火灾监控; 烟雾识别; 权值初始化; 特征提取; 特征分类
中图分类号: TN911.73?34; TP183 文献标识码: A 文章编号: 1004?373X(2020)13?0044?05
DBN?CNN for forest fire smoke recognition
DU Jiaxin1, CHANG Qing1, LIU Xin2
(1. College of Information and Computer, Taiyuan University of Technology, Taiyuan 030024, China;
2. Network Management Center Wireless Room, Unit 32152 of PLA, Shijiazhuang 050000, China)
Abstract: For image recognition of convolutional neural networks (CNN), the method of randomly initializing network weights can easily converge to local optimal values. In order to realize the smoke image recognition of forest fires, a network weight pre?training algorithm combining unsupervised and supervised learning is proposed in this paper. The weight of CNN is initialized by using the features obtained by the deep belief network (DBN) pre?learning. Then, the features of the training samples are extracted by means of the convolution, pooling and other operations, and the extracted features are classified by the fully connected network. Finally, the classification loss function is calculated and the network parameters are optimized. The experimental training results show that the accuracy of forest fire smoke recognition based on DBN?CNN reaches 98.5%, which is higher than that of other algorithms.
Keywords: deep belief network; forest fire monitoring; smoke recognition; weight initialization; feature extraction; feature classification
0 引 言
火灾对人类社会造成了无可比拟的重大损失,每年因为火灾而造成的人员伤亡不计其数。仅2018年1—8月,全国共发生失火事件16万起,亡933人,伤560人,直接财产损失折合人民币高达20.53亿元。纵观世界范围,同年3月,印度南部山区发生大规模森林火灾,至少导致9人死亡,18人受伤。同年7月,加拿大出现严重的森林火灾,累计超过3 000人接受疏散。火灾严重危及了公共的生命安全,造成了大量经济损失、大气环境污染、生态环境破坏、自然景观毁坏等问题。因此,第一时间准确地发现火灾的源头,对火灾的预警和扑救工作意义重大。与室内火灾成熟的实时监控不同,野外火灾由于各种因素的限制,实时监控技术还不成熟。计算机技术的发展和图像识别技术的广泛应用给户外火灾的实时监控带来了新的转机,未来将通过视频监控智能地进行火情监控。……
