[1]黄文锋,徐珊珊,孙燚,等.基于多分辨率卷积神经网络的火焰检测[J].郑州大学学报(工学版),2019,40(05):79-83.[doi:10.13705/j.issn.1671-6833.2019.05.022]
　Huang Wenfeng,Susan Hsu,Sun Yi,et al.Fire Detection Based on Multi-resolution Convolution Neural Network in Various Scenes[J].Journal of Zhengzhou University (Engineering Science),2019,40(05):79-83.[doi:10.13705/j.issn.1671-6833.2019.05.022]
点击复制

基于多分辨率卷积神经网络的火焰检测()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
40卷
期数:
2019年05期
页码:
79-83
栏目:
出版日期:
2019-10-23

文章信息/Info

Title:
Fire Detection Based on Multi-resolution Convolution Neural Network in Various Scenes
作者:
黄文锋; 徐珊珊; 孙燚; 周兵
.河南省科学技术信息研究院，河南郑州450003； 郑州大学信息工程学院，河南郑州450001
Author(s):
Huang Wenfeng 1; Susan Hsu 2; Sun Yi 2; Zhou Bing 2
1. Henan Academy of Science and Technology Information; 2. School of Information Engineering, Zhengzhou University
关键词:
多分辨率卷积神经网络; 火焰检测; 深度学习; 弱监督定位
Keywords:
Multi-resolution convolutional neural network; flame detection; deep learning; weakly supervised localization
DOI:
10.13705/j.issn.1671-6833.2019.05.022
文献标志码:
A
摘要:
BN_Inception网络作为基础架构，采用不同分辨率的神经网络互补学习复杂场景中火焰的多尺度视觉特征，同时该算法重点关注检测目标场景的背景环境、局部目标和整体布局等特征。本文还构造了一个涵盖大多数真实场景的火焰数据集，并在该数据集上进行了相应测试，实验结果表明该论文提出的算法相较于其他方法能够取得更好的检测效果，并在实际场景中得到了有效验证。
Abstract:
Considering the multi-scale characteristics of various scenes for the fire detection, in this paper, we propose a fire detection algorithm based on multi-resolution convolutional neural network. This algorithm leverages the BN_Inception network as the basic structure. Different coarse and fine resolution neural networks complementarily learn the multi-scale visual features of the fire in complex scenes, while paying attention to the background environment, local targets and overall layout of the scene. We also construct a fire dataset covering most of natural scenes, and test our method in this dataset. The experiment proves that the proposed method can achieve better detection results that other methods and can be effectively applied in the real world
更新日期/Last Update: 2019-11-02