Deep Convolutional Generative Adversarial Network and Convolutional Neural Network for Smoke Detection
Real-time smoke detection is of great significance for early warning of fire, which can avoid the serious loss caused by fire. Detecting smoke in actual scenes is still a challenging task due to large variance of smoke color, texture, and shapes. Moreover, the smoke detection in the actual scene is...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi-Wiley
2020-01-01
|
Series: | Complexity |
Online Access: | http://dx.doi.org/10.1155/2020/6843869 |
id |
doaj-1391af81348742129c2758806795e631 |
---|---|
record_format |
Article |
spelling |
doaj-1391af81348742129c2758806795e6312020-11-30T09:11:23ZengHindawi-WileyComplexity1076-27871099-05262020-01-01202010.1155/2020/68438696843869Deep Convolutional Generative Adversarial Network and Convolutional Neural Network for Smoke DetectionHang Yin0Yurong Wei1Hedan Liu2Shuangyin Liu3Chuanyun Liu4Yacui Gao5Academy of Smart Agricultural Engineering Innovations, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaSchool of Computer Science, Shenyang Aerospace University, Shenyang 110136, ChinaSchool of Computer Science, Shenyang Aerospace University, Shenyang 110136, ChinaAcademy of Smart Agricultural Engineering Innovations, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaSchool of Computer Science, Shenyang Aerospace University, Shenyang 110136, ChinaSchool of Computer Science, Shenyang Aerospace University, Shenyang 110136, ChinaReal-time smoke detection is of great significance for early warning of fire, which can avoid the serious loss caused by fire. Detecting smoke in actual scenes is still a challenging task due to large variance of smoke color, texture, and shapes. Moreover, the smoke detection in the actual scene is faced with the difficulties in data collection and insufficient smoke datasets, and the smoke morphology is susceptible to environmental influences. To improve the performance of smoke detection and solve the problem of too few datasets in real scenes, this paper proposes a model that combines a deep convolutional generative adversarial network and a convolutional neural network (DCG-CNN) to extract smoke features and detection. The vibe algorithm was used to collect smoke and nonsmoke images in the dynamic scene and deep convolutional generative adversarial network (DCGAN) used these images to generate images that are as realistic as possible. Besides, we designed an improved convolutional neural network (CNN) model for extracting smoke features and smoke detection. The experimental results show that the method has a good detection performance on the smoke generated in the actual scenes and effectively reduces the false alarm rate.http://dx.doi.org/10.1155/2020/6843869 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hang Yin Yurong Wei Hedan Liu Shuangyin Liu Chuanyun Liu Yacui Gao |
spellingShingle |
Hang Yin Yurong Wei Hedan Liu Shuangyin Liu Chuanyun Liu Yacui Gao Deep Convolutional Generative Adversarial Network and Convolutional Neural Network for Smoke Detection Complexity |
author_facet |
Hang Yin Yurong Wei Hedan Liu Shuangyin Liu Chuanyun Liu Yacui Gao |
author_sort |
Hang Yin |
title |
Deep Convolutional Generative Adversarial Network and Convolutional Neural Network for Smoke Detection |
title_short |
Deep Convolutional Generative Adversarial Network and Convolutional Neural Network for Smoke Detection |
title_full |
Deep Convolutional Generative Adversarial Network and Convolutional Neural Network for Smoke Detection |
title_fullStr |
Deep Convolutional Generative Adversarial Network and Convolutional Neural Network for Smoke Detection |
title_full_unstemmed |
Deep Convolutional Generative Adversarial Network and Convolutional Neural Network for Smoke Detection |
title_sort |
deep convolutional generative adversarial network and convolutional neural network for smoke detection |
publisher |
Hindawi-Wiley |
series |
Complexity |
issn |
1076-2787 1099-0526 |
publishDate |
2020-01-01 |
description |
Real-time smoke detection is of great significance for early warning of fire, which can avoid the serious loss caused by fire. Detecting smoke in actual scenes is still a challenging task due to large variance of smoke color, texture, and shapes. Moreover, the smoke detection in the actual scene is faced with the difficulties in data collection and insufficient smoke datasets, and the smoke morphology is susceptible to environmental influences. To improve the performance of smoke detection and solve the problem of too few datasets in real scenes, this paper proposes a model that combines a deep convolutional generative adversarial network and a convolutional neural network (DCG-CNN) to extract smoke features and detection. The vibe algorithm was used to collect smoke and nonsmoke images in the dynamic scene and deep convolutional generative adversarial network (DCGAN) used these images to generate images that are as realistic as possible. Besides, we designed an improved convolutional neural network (CNN) model for extracting smoke features and smoke detection. The experimental results show that the method has a good detection performance on the smoke generated in the actual scenes and effectively reduces the false alarm rate. |
url |
http://dx.doi.org/10.1155/2020/6843869 |
work_keys_str_mv |
AT hangyin deepconvolutionalgenerativeadversarialnetworkandconvolutionalneuralnetworkforsmokedetection AT yurongwei deepconvolutionalgenerativeadversarialnetworkandconvolutionalneuralnetworkforsmokedetection AT hedanliu deepconvolutionalgenerativeadversarialnetworkandconvolutionalneuralnetworkforsmokedetection AT shuangyinliu deepconvolutionalgenerativeadversarialnetworkandconvolutionalneuralnetworkforsmokedetection AT chuanyunliu deepconvolutionalgenerativeadversarialnetworkandconvolutionalneuralnetworkforsmokedetection AT yacuigao deepconvolutionalgenerativeadversarialnetworkandconvolutionalneuralnetworkforsmokedetection |
_version_ |
1715028004037459968 |