«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

33

期数:

2023年01期

页码:

56-61

栏目:

媒体计算

出版日期:

2023-01-10

文章信息/Info

Title:

Fire Detection Algorithm Based on Multi-task Learning

文章编号:

1673-629X(2023)01-0056-06

作者:

吕 鹏¹ ; 曹江涛¹ ; 姬晓飞^2*

1. 辽宁石油化工大学 信息与控制工程学院,辽宁 抚顺 113001;

2. 沈阳航空航天大学 自动化学院,辽宁 沈阳 110136

Author(s):

LYU Peng1 ; CAO Jiang-tao1 ; JI Xiao-fei2*

1. School of Information and Control Engineering,Liaoning Petrochemical University,Fushun 113001,China;

2. School of Automation,Shenyang Aerospace University,Shenyang 110136,China

关键词:

深度学习; 多任务学习算法; 生成对抗网络; 卷积神经网络; 长短时记忆网络

Keywords:

deep learning; multi-task learning algorithm; generative adversarial network ( GAN) ; convolutional neural network ( CNN) ; long and short-term memory network ( LSTM)

分类号:

TP391

DOI:

10. 3969 / j. issn. 1673-629X. 2023. 01. 009

摘要:

烟雾和火焰是相辅相成的,在火焰检测中充分利用火焰和烟雾的内在关系,将更好地提高火灾检测的准确性。 目前,大多数的火灾检测算法只关注烟雾或火焰两者间的某一个任务来设计检测算法。 该文提出了一种基于多任务学习的火灾检测算法。 首先,将 RGB 视频序列作为网络的输入,运用 CNN 网络与 LSTM 网络提取空间特征和时序特征。 然后,设计生成对抗网络将特征空间划分为共享特征空间和私有特征空间两个部分,共享特征空间用于提取烟雾和火焰内在联系中的共享特征,私有特征空间用于提取烟雾和火焰各自的私有特征。 最终,将上述两部分特征通过 concat 方式结合,送到全连接层与 softmax 中,得到最终的识别结果。 将多任务学习应用于火灾检测,其优势在于充分考虑到火灾发生时烟雾与火焰之间的关联性,利用这种关联性丰富烟雾与火焰的特征语义信息,进而提高检测的准确性。 实验结果表明,在烟雾检测的准确率上提升 2. 2% ,火焰检测的准确率上提升 1. 4% ,提出的多任务学习模型性能上优于单任务学习模型。

Abstract:

Smoke and fire are complementary to each other. Making full use of the inherent relationship between flame and smoke inflame detection will better improve the accuracy of fire detection. 　At present,most fire detection algorithms only focus on a certain taskbetween smoke or flame to design detection algorithms. We propose a fire detection algorithm based on multi-task learning. Firstly,theRGB video sequence is used as the input of the network, and the CNN network and LSTM network are used to extract spatial and temporal features. Then,the generative confrontation network is designed to divide the feature space into two parts:a shared feature spaceand a private feature space. The shared feature space is used to extract the shared features in the internal connection of smoke and flames,and the private feature space is used to extract the private features of smoke and flames. Finally, the above two parts of features arecombined by concat and sent to the fully connected layer and softmax for the final recognition result. The advantage of applying multi-task learning to fire detection is that the correlation between smoke and flame when fire occurs is fully taken into account,and the featuresemantic information of smoke and flame is enriched by this correlation,thus improving the accuracy of detection. The experimentalresults show that the accuracy of smoke detection is increased by 2. 2% ,and the accuracy of flame detection is increased by 1. 4% . Theperformance of the multi-task learning model proposed is better than that of the single-task learning model.

常用功能

更新日期/Last Update: 2023-01-10