Image detection method of ship engine room fire based on transfer learning

JIANG Xing-jia; LIU Yun-zhi; SONG Zhi-min; MU Sheng-quan; ZHANG Peng; ZHANG Yue-wen; SUN Pei-ting

doi:10.16411/j.cnki.issn1006-7736.2023.01.011

Journal of Dalian Maritime University >

2023 , Vol. 49 >Issue 1: 103 - 109

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2023.01.011

Image detection method of ship engine room fire based on transfer learning

JIANG Xing-jia ,
LIU Yun-zhi ,
SONG Zhi-min ,
MU Sheng-quan ,
ZHANG Peng ,
ZHANG Yue-wen ,
SUN Pei-ting

Expand

(1.Marine Engineering College, Dalian Maritime University, Dalian 116026, China; 2.Dalian Shipbuilding Industry Group Co.LTD, Dalian 116021, China)

Received date: 2022-10-03

Revised date: 2022-12-09

Online published: 2022-12-09

Fold

Abstract

In order to solve the problem that the traditional smoke detectors were easily affected by the environment and location of the ship engine room, resulting in untimely fire response, a smoke recognition model of the ship engine room based on machine vision was proposed. Firstly, the universal database, real ship scenes and smoke images were used to build a graphic knowledge base. Secondly, the fusion model of migration learning and residual network was constructed to realize the migration and learning of smoke characteristics, and the validity of the model was verified by using the validation data set. Finally, the fire photos of a real ship workshop were selected to verify the validity of the model. The results show that compared with the traditional smoke detector, the proposed model can provide 83 s early warning, and compared with other intelligent algorithms, this model can improve the accuracy of smoke recognition. This method can identify ship smoke more quickly and avoid major catastrophic fire accidents, therefore can be used as an intelligent monitoring method for ships.

Key words： engine room; fire image; detection method; machine vision; engine room smoke; transfer learning

Cite this article

JIANG Xing-jia , LIU Yun-zhi , SONG Zhi-min , MU Sheng-quan , ZHANG Peng , ZHANG Yue-wen , SUN Pei-ting . Image detection method of ship engine room fire based on transfer learning[J]. Journal of Dalian Maritime University, 2023 , 49(1) : 103 -109 . DOI: 10.16411/j.cnki.issn1006-7736.2023.01.011

References

[1]徐全香, 刘庆亮, 毛洪伟, 等. 远程故障诊断技术在科考船上的应用 [J]. 水运管理, 2017, 39(12): 33-35.

XU Q X, LIU Q L, MAO H W, et al. Application of remote fault diagnosis technology on scientific research ships [J]. Water Transport Management, 2017, 39 (12): 33-35.(in Chinese)

[2]盛虎, 朱勇. 基于CAN总线的船舶火灾报警系统的设计[J]. 仪器仪表用户, 2006 (3): 27-28.

SHENG H, ZHU Y. Design of ship fire alarm system based on CAN bus [J]. Instrument User, 2006 (3): 27-28.(in Chinese)

[3]黄宪勇. 船舶机舱火灾分析与扑救 [J]. 航海技术, 2014 (2): 67-69.

HUANG X Y. Fire analysis and fighting of ship engine room [J]. Navigation Technology, 2014(2): 67-69.(in Chinese)

[4]APPANA D K, ISLAM R, KHAN S A, et al. A video-based smoke detection using smoke flow pattern and spatial-temporal energy analysis for alarm systems[J]. Information Sciences, 2017, 418-419: 91-101.

[5]YUAN F N. A double mapping framework for extraction of shape-invariant features based on multi-scale partitions with AdaBoost for video smoke detection[J]. Pattern Recognition, 2012, 45(12): 4326-4336.

[6]PARK K M, BAE C O. Smoke detection in ship engine rooms based on video images [J]. IET Image Processing, 2020, 14(6): 1141-1149.

[7][JP2]FRIZZI S, KAABI R, BOUCHOUICHA M, et al. Convolutional neural network for video fire and smoke detection[C]//Proceedings of the 42nd Annual Conference of the IEEE-Industrial-Electronics-Society (IECON). Florence：IEEE,2016. doi: 10.1109/IECON.2016.7793196.

[8]耿梦雅. 基于视频的复杂场景火灾检测技术研究 [D]. 武汉：华中师范大学, 2019.

GENG M Y. Research on video based fire detection technology in complex scenes[D]. Wuhan: Central China Normal University, 2019.(in Chinese)

[9]MAO W T, WANG W P, DOU Z, et al. Fire recognition based on multi-channel convolutional neural network [J]. Fire Technology, 2018, 54: 531-554.

[10]陈钦柱, 姚冬, 黄松. 基于卷积神经网络和优化GoogleNet架构的监控视频火灾探测 [J]. 自动化技术与应用, 2021, 40(9): 124-129.

CHEN Q Z, YAO D, HUANG S. Surveillance video fire detection based on convolutional neural network and optimized GoogleNet architecture[J]. Automation Technology and Application, 2021, 40(9): 124-129.(in Chinese)

[11]DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]// Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami: IEEE,2009. doi: 10.1109/CVPR.2009.5206848.

[12]管淑贤, 葛万成. 基于ResNet18的减速带识别及其环境影响研究[J]. 通信技术, 2021, 54(3): 597-603.

GUAN S X, GE W C. ResNet18 based deceleration strip identification and its environmental impact study [J]. Communication Technology, 2021, 54 (3): 597-603.(in Chinese)

[13]兰名扬, 刘宇龙, 金涛, 等. 基于可视化轨迹圆和ResNet18的复合电能质量扰动类型识别 [J]. 中国电机工程学报, 2022, 42(17): 6274-6286.

LAN M Y, LIU Y L, JIN T, et al. Recognition of composite power quality disturbance type based on visual track circle and ResNet18 [J]. Chinese Journal of Electrical Engineering, 2022, 42 (17): 6274-6286.(in Chinese)

[14]ZHUANG F, QI Z, DUAN K, et al. A comprehensive survey on transfer learning[J]. Proceedings of the IEEE, 2021, 109(1): 43-76.

[15]张方言, 赵梦, 周弈志, 等. 基于ResNet50和迁移学习的红鳍东方鲀病鱼检测方法[J]. 渔业现代化, 2021, 48(4): 51-60.

ZHANG F Y, ZHAO M, ZHOU Y Z, et al. Detection method of red finned puffer fish disease based on ResNet50 and transfer learning[J]. Fisheries Modernization, 2021, 48 (4): 51-60.(in Chinese)

[16]夏坚, 周利君, 张伟. 基于迁移学习与VGG16深度神经网络的建筑物裂缝检测方法 [J]. 福建建设科技, 2022(1): 19-22+60.

XIA J, ZHOU L J, ZHANG W. Building crack detection method based on migration learning and VGG16 depth neural network[J]. Fujian Construction Science and Technology, 2022(1): 19-22+60.(in Chinese)

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References