|Table of Contents|

Flame Detection Based on Fast-CAANet(PDF)

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

Issue:
2024年02期
Page:
109-116
Research Field:
计算机科学与技术
Publishing date:

Info

Title:
Flame Detection Based on Fast-CAANet
Author(s):
Gong Chengzhang1; Yan Yunyang1; 2; Bian Suyang1; Zhu Qiaoqiao1; Leng Zhichao1
(1.Faculty of Computer & Software Engineering,Huaiyin Institute of Technology,Huaian 223003,China)
(2.School of Computer Engineering,Jiangsu Ocean University,Lianyungang 222005,China)
Keywords:
deep learning; feature extraction; attention mechanism; flame detection
PACS:
TP391.44
DOI:
10.3969/j.issn.1001-4616.2024.02.013
Abstract:
High efficiency and high speed flame detection plays an important role in preventing fire and protecting social security. In this paper,a flame detection method based on Fast-CAANet is proposed to meet the needs of social security applications. Firstly,a CAA module is proposed to strengthen the effective integration of convolution and attention mechanism. Then the main network of CAANet(CAABlock)is constructed to extract the rich characteristics of flame more effectively. The Fast-CAABlock module with smaller parameters and higher accuracy is proposed to enhance the flame feature extraction scheme. Experimental results show that the accuracy of Fast-CAANet is up to 91.42%,and the calculation amount is 3.9 GMac. Compared with other algorithms,the proposed flame detection algorithm has better performance and effect.

References:

[1]中国消防. 河南震兴武馆“6·25”火灾事故责任人被查处[J]. 中国消防,2022(1):42-43.
[2]刘宇. 关于推进落实高层民用建筑消防安全主体责任的认识与思考[J]. 法制博览,2022(15):141-143.
[3]陈亚光,陈云,侯建成,等. 基于单片机的烟雾报警器设计与实现[J]. 辽宁科技学院学报,2016,18(5):4-6.
[4]KIM H,PARK J. Fire flame detection based on color modeland motion Estimation[C]//2016 IEEE International Conference on Consumer Electronics-Asia(ICCE-Asia). USA:IEEE,2016.
[5]陈浩霖,高尚兵,相林,等. FIRE-DET:一种高效的火焰检测模型[J]. 南京信息工程大学学报(自然科学版),2023,15(1):76-84.
[6]张慧珍,严云洋,刘以安,等. 基于超像素分割与闪频特征判别的视频火焰检测[J]. 数据采集与处理,2018,33(3):512-520.
[7]GONG F,LI C,GONG W,et al. A real-time fire detection method from video with multifeature fusion[J]. Computational intelligence and neuroscience,2019,2019(1):1939171.
[8]KIM Y J,KIM H,LEE S,et al. Trustworthy building fire detection framework with simulation-based learning[J]. IEEE access,2021,9:55777-55789.
[9]梁秦嘉,刘怀,陆飞. 基于改进YOLOv3模型的交通视频目标检测算法研究[J]. 南京师范大学学报(工程技术版),2021,21(2):47-53.
[10]石跃祥,朱茂清. 基于骨架动作识别的协作卷积Transformer网络[J]. 电子与信息学报,2023,45(4):1485-1493.
[11]严忱,严云洋,高尚兵,等. 基于多级特征融合的视频火焰检测方法[J]. 南京师大学报(自然科学版),2021,44(3):131-136.
[12]HOSSEINI A,HASHEMZADEH M,FARAJZADEH N. UFS-Net:a unified flame and smoke detection method for early detection of fire in video surveillance applications using CNNs[J]. Journal of computational science,2022,61:101638.
[13]LIU Z,MAO H,WU C Y,et al. A convnet for the 2020s[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. USA:IEEE,2022:11976-11986.
[14]CHEN H Y,SU C Y. An enhanced hybrid MobileNet[C]//2018 9th International Conference on Awareness Science and Technology(iCAST). USA:IEEE,2018:308-312.
[15]VASWANI A,SHAZEER N,PARMAR N,et al. Attention is all you need[J]. Advances in neural information processing systems,2017,30.
[16]DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al. An image is worth 16×16 words:transformers for image recognition at scale[J/OL]. arXiv Preprint arXiv:2010. 11929,2020.
[17]HUANG G,LIU Z,van der MAATEN L,et al. Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. USA:IEEE,2017:4700-4708.
[18]LIU Z,LIN Y,CAO Y,et al. Swin transformer:hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. USA:IEEE,2021:10012-10022.
[19]林诗妍,刘宇翔,魏宏安. 基于边缘计算的鱼眼相机高空抛物检测系统[J]. 福建师范大学学报(自然科学版),2024,39(6):52-62.

Memo

Memo:
-
Last Update: 2024-06-15