본문 바로가기
KERD
논문KCI 등재

CNN-based fire detection method on autonomous ships using composite channels composed of RGB and IR data

유원선|Kim DongHyun
대한조선학회 (The Society Of Naval Architects Of Korea)|2022.12|International Journal of Naval Architecture and Ocean Engineering|제14권 |pp. 1-13|DOI 10.1016/j.ijnaoe.2022.100489

2

조회

0

다운로드

7

인용

0

참고문헌

키워드

CNNFire detectionAutonomous ship Fire safetyRGB-IRComposite channel data
주제분류조선공학

초록

Since fires grow exponentially after an outbreak, it is crucial to extinguish them quickly. In the case of fires occurring on commercial ships and naval vessels, smoke and heat in the narrow enclosed compartments of the ships make it difficult to extinguish fires, threatening human safety, and causing massive property damage. So-called autonomous ships are operated without crew members in charge of fire suppression. Therefore, it is crucial to improve the performance and reliability of the automatic fire detection and suppression system. However, the standard fire detection system installed on ships is not adequate for the level of fire risk. Existing fire detection methods still have false alarm problems, and it takes a long time for heat and smoke from the fire to reach the detector. In this study, the use of combined channel data (RGB-IR) is proposed as an image-based fire detection method applicable to ships. In nature, many animals obtain multiple wavelength information, which is advantageous for hunting or risk preparedness in a wild environment. In this way, it is assumed that both the characteristics of RGB data in the visible area and IR data in the infrared area may be utilized through the combined channel data. A fire detection model with composite channel data input was built using deep learning with a Convolution Neural Network (CNN), a fire detection model using composite channel data input was constructed, and hyper-parameters were tuned during the training process to determine the optimal model and compare it with the existing RGB and IR models, respectively. Compared with the model using only conventional RGB or IR data, the fire detection accuracy of the model using RGB-IR combined channel data increased and the false detection rate decreased.

Abstract

Since fires grow exponentially after an outbreak, it is crucial to extinguish them quickly. In the case of fires occurring on commercial ships and naval vessels, smoke and heat in the narrow enclosed compartments of the ships make it difficult to extinguish fires, threatening human safety, and causing massive property damage. So-called autonomous ships are operated without crew members in charge of fire suppression. Therefore, it is crucial to improve the performance and reliability of the automatic fire detection and suppression system. However, the standard fire detection system installed on ships is not adequate for the level of fire risk. Existing fire detection methods still have false alarm problems, and it takes a long time for heat and smoke from the fire to reach the detector. In this study, the use of combined channel data (RGB-IR) is proposed as an image-based fire detection method applicable to ships. In nature, many animals obtain multiple wavelength information, which is advantageous for hunting or risk preparedness in a wild environment. In this way, it is assumed that both the characteristics of RGB data in the visible area and IR data in the infrared area may be utilized through the combined channel data. A fire detection model with composite channel data input was built using deep learning with a Convolution Neural Network (CNN), a fire detection model using composite channel data input was constructed, and hyper-parameters were tuned during the training process to determine the optimal model and compare it with the existing RGB and IR models, respectively. Compared with the model using only conventional RGB or IR data, the fire detection accuracy of the model using RGB-IR combined channel data increased and the false detection rate decreased.

참고문헌 (74)

  1. Abadi, M., "{TensorFlow}: a system for {Large-Scale} machine learning", 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pp.265~283 (2016)
  2. Akhloufi, M. A., "Unmanned aerial vehicles for wildland fires: sensing, perception, cooperation and assistance", Drones, 5, pp.15~ (2021)
  3. Astrup, J., "Ultrasound detection in fish-a parallel to the sonar-mediated detection of bats by ultrasound-sensitive insects?", Comp. Biochem. Physiol. Mol. Integr. Physiol, 124(1), pp.19~27 (1999)
  4. Baalisampang, T., "Review and analysis of fire and explosion accidents in maritime transportation", Ocean Eng, 158, pp.350~366 (2018)
  5. Bradski, G., "Learning OpenCV: Computer Vision with the OpenCV Library" (2008), O'Reilly Media, Inc
  6. Chen, T. H., "An intelligent real-time fire-detection method based on video processing", IEEE 37th Annual 2003 International Carnahan Conference OnSecurity Technology, pp.104~111 (2003), IEEE
  7. 최홍석, "움직임 정보와 칼라정보 분석을 통한 화재검출 알고리즘", 멀티미디어학회논문지, 19(2), pp.180~188 (2016), 한국멀티미디어학회[DOI]
  8. Chollet, F., "Xception: deep learning with depthwise separable convolutions", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1251~1258 (2017)
  9. Ciprian-Sanchez, J. F., "FIRe-GAN: a novel Deep Learning-based infrared-visible fusion method for wildfire imagery", Neural Comput. Appl, pp.1~13 (2021)
  10. "Fireflame Dataset" (2019)[URL]
  11. Du, J., "CNN-based infrared dim small target detection algorithm using target-oriented shallow-deep features and effective small anchor", IET Image Process, 15, pp.1~15 (2021)
  12. Dzigal, D., "Forest fire detection based on color spaces combination", 2019 11th International Conference on Electrical and Electronics Engineering (ELECO), pp.595~599 (2019), IEEE
  13. Foggia, P., "Real-time fire detection for videosurveillance applications using a combination of experts based on color, shape, and motion", IEEE Trans. Circ. Syst. Video Technol, 25(9), pp.1545~1556 (2015)
  14. Geetha, S., "Machine vision based fire detection techniques: a survey", Fire Technol, 57(2), pp.591~623 (2021)
  15. Gulli, A., "Deep Learning with Keras" (2017), Packt Publishing Ltd
  16. 하태영, "최근 주변국 해군력 증강과 한국의 대응방향 - 해군력의 증강방향과 함정과학기술 발전방향을 중심으로 -", 전략연구, 22(3), pp.165~193 (2015), (사) 한국전략문제연구소
  17. 한정우, "비전투(非戰鬪) 사고에 의한 손실예방을 위한 해군 안전보건경영시스템 도입 연구", 한국위험물학회지, 8(1), pp.86~91 (2020), 한국위험물학회
  18. Harkat, H., "Fire detection using residual deeplabv3þ model", 2021 Telecoms Conference (Conftele), pp.1~6 (2021), IEEE
  19. Harris, C. R., "Array programming with NumPy", Nature, 585, pp.357~362 (2020)
  20. He, K., "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.770~778 (2016)
  21. He, K., "Mask r-cnn", Proceedings of the IEEE International Conference on Computer Vision, pp.2961~2969 (2017)
  22. 홍성호, "열방출률을 이용한 열감지기의 오동작 경계값 분석", 한국화재소방학회 논문지, 17(3) (2003), 한국화재소방학회
  23. Hong, M., "SSPNet: scale selection pyramid network for tiny person detection from UAV images", Geosci. Rem. Sens. Lett. IEEE, 19, pp.1~5 (2021)
  24. Hunter, J. D., "Matplotlib: a 2D graphics environment", Comput. Sci. Eng, 9(3), pp.90~95 (2007)
  25. 황의홍, "소방차 출동 시 효율적인 골든타임 확보 방안에 관한 연구", 한국방재학회논문집, 18(5), pp.119~126 (2018), 한국방재학회[DOI]
  26. 황인하, "해군 함정 승조원 수 예측 모형에 관한 연구", 대한조선학회 논문집, 56(6), pp.523~531 (2019), 대한조선학회[DOI]
  27. 전계룡, "해군함정 화재 위험도 평가에 관한 연구", 한국화재소방학회 논문지, 22(5), pp.35~42 (2008), 한국화재소방학회
  28. Khudayberdiev, O., "Fire detection approach based on vision transformer", International Conference on Adaptive and Intelligent Systems, pp.41~53 (2022), Springer
  29. 김영진, "CNN과 Grad-CAM 기반의 실시간 화재 감지", 한국정보통신학회논문지, 22(12), pp.1596~1603 (2018), 한국정보통신학회[DOI]
  30. Kim, B. J., "A video-based fire detection using deep learning models", Appl. Sci, 9(14), pp.2862~ (2019)
  31. "Kmu Fire & Smoke Database" (2012)[URL]
  32. Krizhevsky, A., "Imagenet classification with deep convolutional neural networks", Adv. Neural Inf. Process. Syst, 25 (2012)
  33. LeCun, Y., "Gradient-based learning applied to document recognition", Proc. IEEE, 86(11), pp.2278~2324 (1998)
  34. Li, C., "Fire flame image detection based on transfer learning", 2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS), pp.370~374 (2018), IEEE
  35. Li, P., "Image fire detection algorithms based on convolutional neural networks", Case Stud. Therm. Eng, 19, pp.100625~ (2020)
  36. Lin, M., "Network in network arXiv Prepr", ~ (2013)
  37. Liu, W., "Ssd: single shot multibox detector", European Conference on Computer Vision, pp.21~37 (2016), Springer
  38. Majid, S., "Attention based CNN model for fire detection and localization in real-world images", Expert Syst. Appl, 189, pp.116114~ (2022)
  39. Martínez-de Dios, J. R., "Automatic forest-fire measuring using ground stations and unmanned aerial systems", Sensors, 11, pp.6328~6353 (2011)
  40. Maurer, D. C., "Navy Maintenance: Persistent and Substantial Ship and Submarine Maintenance Delays Hinder Efforts to Rebuild Readiness", Government accountability office, ~ (2019)
  41. McKinney, W., "pandas: a foundational Python library for data analysis and statistics", Python High Perform. Sci. Comput, 14(9), pp.1~9 (2011)
  42. Mseddi, W. S., "Fire detection and segmentation using YOLOv5 and U-net", 2021 29th European Signal Processing Conference (EUSIPCO), pp.741~745 (2021), IEEE
  43. Muhammad, K., "Efficient deep CNN-based fire detection and localization in video surveillance applications", IEEE Transact. Syst. Man Cybernet.: Syst, 49(7), pp.1419~1434 (2018)
  44. Nakıp, M., "Multi-sensor fire detector based on trend predictive neural network", 2019 11th International Conference on Electrical and Electronics Engineering (ELECO), pp.600~604 (2019), IEEE
  45. Standard Portable Fire Extinguishers 2013 Edition, "National Fire Protection Association", National Fire Protection Association, ~, pp.NFPA 10 (2013)
  46. Ohkubo, T., "A color compensation vision system for color-blind people", 2008 SICE Annual Conference, pp.1286~1289 (2008), IEEE
  47. 박경민, "선박의 기관실에서의 연기 검출을 위한 LBP-GLCM 알고리즘에 관한 연구", 해양환경안전학회지, 25(1), pp.111~116 (2019), 해양환경안전학회[DOI]
  48. 박주헌, "함정 재해의 신속 진압을 위한 경로 탐색에 관한 연구", 대한조선학회 논문집, 57(4), pp.221~229 (2020), 대한조선학회[DOI]
  49. Pundir, A. S., "Dual deep learning model for image based smoke detection", Fire Technol, 55(6), pp.2419~2442 (2019)
  50. Qiang, L. I., "Estimation of fire detection time", Procedia Eng, 11, pp.233~241 (2011)
  51. Redmon, J., "You only look once: unified, real-time object detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.779~788 (2016)
  52. Ren, S., "Faster r-cnn: towards real-time object detection with region proposal networks", Adv. Neural Inf. Process. Syst, 28 (2015)
  53. Ren, Y., "Small object detection in optical remote sensing images via modified faster R-CNN", Appl. Sci, 8(5), pp.813~ (2018)
  54. , 2004
  55. 사공성호, "화재실험을 통한 주택용 연기감지기 응답특성에 관한 연구", 한국화재소방학회 논문지, 23(4), pp.98~103 (2009), 한국화재소방학회
  56. Selvaraju, R. R., "Gradcam: visual explanations from deep networks via gradient-based localization", Proceedings of the IEEE International Conference on Computer Vision, pp.618~626 (2017)
  57. Shi, L., "Video-based fire detection with spatiotemporal SURF and color features", 2016 12th World Congress on Intelligent Control and Automation (WCICA), pp.258~262 (2016), IEEE
  58. Shi, X., "Smoke detection based on dark channel and convolutional neural networks", 2019 5th International Conference on Big Data and Information Analytics (BigDIA), pp.23~28 (2019), IEEE
  59. Sousa, M. J., "Wildfire detection using transfer learning on augmented datasets", Expert Syst. Appl, 142, pp.112975~ (2020)
  60. Szegedy, C., "Rethinking the inception architecture for computer vision", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2818~2826 (2016)
  61. Tong, K., "Deep learning-based detection from the perspective of small or tiny objects: a survey", Image Vision Comput, pp.104471~ (2022)
  62. Torrey, L., "Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques", pp.242~264 (2010), IGI global
  63. Toulouse, T., "Computer vision for wildfire research: an evolving image dataset for processing and analysis", Fire Saf. J, 92, pp.188~194 (2017)
  64. Verstockt, S., "Multi-sensor fire detection by fusing visual and non-visual flame features", International Conference on Image and Signal Processing, pp.333~341 (2010), Springer
  65. "GML Cþþ Camera Calibration Toolbox" (2005)[URL]
  66. Wang, K., "Detection of infrared small targets using feature fusion convolutional network", IEEE Access, 7, pp.146081~146092 (2019)
  67. Xu, G., "Video smoke detection based on deep saliency network", Fire Saf. J, 105, pp.277~285 (2019)
  68. Xu, R., "A forest fire detection system based on ensemble learning", Forests, 12, pp.1~17 (2021)[DOI]
  69. Yar, H., "Vision sensorbased real-time fire detection in resource-constrained IoT environments", Comput. Intell. Neurosci, 2021, pp.5195508~ (2021)[DOI]
  70. Yin, Z., "A deep normalization and convolutional neural network for image smoke detection", IEEE Access, 5, pp.18429~18438 (2017)
  71. Outline of video image fire detector and study on the development of performance standard, "Yu, S. H.", 14~19 (2013)
  72. Zervas, E., "Multisensor data fusion for fire detection", Inf. Fusion, 12(3), pp.150~159 (2011)
  73. Zhang, F., "A Dual-Channel convolution neural network for image smoke detection", Multimed. Tool. Appl, 79(45), pp.34587~34603 (2020)
  74. Zhong, B., "A biomimetic model of adaptive contrast vision enhancement from mantis shrimp", Sensors, 20(16), pp.4588~ (2020)

관련 논문AI추천

AI-enhanced fire detection and suppression system for autonomous ships이혁, 정현, 김종환, 유용호, 유원선, 정정훈, Gil Hyuk Lim대한조선학회 · International Journal of Naval Architecture and Ocean Engineering2024 · 제16권 Fire Detection Based on Image Learning by Collaborating CNN-SVM with Enhanced Recall도용태한국센서학회 · 센서학회지2024 · 제33권 제3호Development of a Multimodal Fire Detection Framework최신형중소기업융합학회 · 산업과 과학2025 · 제4권 제6호Computer Vision-based Method to Detect Fire Using Color Variation in Temporal Domain김성환, 김지연, 정제창, 조준상, Ung Hwang자연과학연구소 · Quantitative Bio-Science2018 · 제37권 제2호Fire Detection Using Multi-Channel Information and Gray Level Co-occurrence Matrix Image Features김민준, 김승호, 장영숙, 전재현한국정보처리학회 · JIPS(Journal of Information Processing Systems)2017 · 제13권 제3호Real-time Smoke Detection Research with False Positive Reduction using Spatial and Temporal Features based on Faster R-CNN이상훈, 이영학한국전기전자학회 · 전기전자학회논문지2020 · 제24권 제4호

이 간행물의 다른 논문 (70건)

Interference intention classification of moving obstacles used for USV collision avoidanceSong Lifei, Sun Hao, Xu Kaikai, Huang Liang, Chen Houjingpp. 1-16Fatigue damage assessment of offshore riser subjected to vortex-induced vibrations by SHEAR7김도균, Lekkala Malakonda Reddy, Latheef Mohamed, Jung Jae Hwan, Kim Young Taepp. 1-17Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning이상현, 김기수, 노명일, 오민재, 남정우, 여인창, 김진혁, Jang Young-Hunpp. 1-15Fender segmentation in unmanned aerial vehicle images based on densely connected receptive field block방현태, 전해민, Yu Byeongjun, Yi Sang Soo, Min Jiyoungpp. 1-9Collision avoidance based on predictive probability using Kalman filter이성욱, Kim Jae Hyun, Jin Eun Seokpp. 1-23
원문 보기