열화상 카메라를 이용한 전통시장 화재 감지에서 YOLOv8 객체 탐지 모델의 성능 비교 분석
Comparative Analysis of YOLOv8 Object Detection Model Performance in Fire Detection in Traditional Markets Using Thermal Cameras
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Traditional markets, formed naturally, often feature aged buildings and facilities that are susceptible to fire. However, the lack of adequate fire detection systems in these markets can easily lead to large-scale fires upon ignition. Therefore, this study was conducted with the aim of detecting fires in traditional markets, utilizing thermal imaging cameras for data collection and the YOLOv8 model for object detection experiments. Data were collected in the night markets within traditional markets of xx city and by simulating fire scenarios. A comparative analysis of the Nano and XL models of YOLOv8 revealed that the XL model is more effective in detecting fires. The XL model not only demonstrated higher accuracy in correctly identifying flames but also tended to miss fewer fires compared to the Nano model. In the case of objects other than flames, the XL model showed superior performance over the Nano model. Taking all these factors into account, it is anticipated that with further data collection and improvement in model performance, a suitable fire detection system for traditional markets can be developed.
Abstract
Traditional markets, formed naturally, often feature aged buildings and facilities that are susceptible to fire. However, the lack of adequate fire detection systems in these markets can easily lead to large-scale fires upon ignition. Therefore, this study was conducted with the aim of detecting fires in traditional markets, utilizing thermal imaging cameras for data collection and the YOLOv8 model for object detection experiments. Data were collected in the night markets within traditional markets of xx city and by simulating fire scenarios. A comparative analysis of the Nano and XL models of YOLOv8 revealed that the XL model is more effective in detecting fires. The XL model not only demonstrated higher accuracy in correctly identifying flames but also tended to miss fewer fires compared to the Nano model. In the case of objects other than flames, the XL model showed superior performance over the Nano model. Taking all these factors into account, it is anticipated that with further data collection and improvement in model performance, a suitable fire detection system for traditional markets can be developed.
참고문헌 (24)
- 함형우, "전통시장 화재 피해 최소화 방안연구", 한국화재소방학회 학술대회 논문집, pp.175~ (2023), 한국화재소방학회
- 박정화, "전통시장 훈소 화재 위험성 및 화재진압 방법에 관한 연구", 한국화재소방학회 학술대회 논문집, pp.98~ (2022), 한국화재소방학회
- "전통시장 및 상점가 육성을 위한 특별법(약칭: 전통시장법)" (2023)[URL]
- "통계청"[URL]
- 김정곤, "전통시장 화재 발생 및 확대 위험요인에 관한 연구", 한국재난정보학회 논문집, 17(1), pp.60~67 (2021), 한국재난정보학회
- "국가화재정보시스템 화재통계"[URL]
- 소윤범, "전통시장 외부공간의 화재 대응을 위한 시스템 개발에 관한 연구", 한국방재학회논문집, 20(5), pp.105~112 (2020), 한국방재학회[DOI]
- "전통시장 화재 절반, 영업 끝난 야간에발생... 전기적 요인 최다" (2019), 권수현[URL]
- 유시영, "비디오 기반 딥러닝 융합 알고리즘에 의한 화재 감지 시스템에 관한 연구", 한국통신학회논문지, 46(9), pp.1487~1496 (2021), 한국통신학회[DOI]
- S. T. Seydi, "Fire-Net: A Deep Learning Framework for Active Forest Fire Detection", Journal of Sensors, 2022, pp.1~14 (2022)
- J. Balen, "FireBot - An Autonomous Surveillance Robot for Fire Prevention, Early Detection and Extinguishing", 2023 15th International Conference on Computer and Automation Engineering (2023)
- S. Li, "An Early Forest Fire Detection System Based on DJI M300Drone and H20T Camera", 2022 International Conference on Unmanned Aircraft Systems (2022)
- K. L. B. L. Xavier, "Development of an Early Fire Detection Technique Using a Passive Infrared Sensor and Deep Neural Networks", Fire Technology, 58(6), pp.3529~3552 (2022)[DOI]
- 김윤지, "딥러닝을 이용한 영상 기반의 화재 위치 감지", 전기학회논문지, 69(3), pp.474~479 (2020), 대한전기학회
- A. Abdusalomov, "An Improvement of the Fire Detection and Classification Method Using YOLOv3 for Surveillance Systems", Sensors, 21(19), pp.6519~ (2021)
- 이평화, "딥러닝 기반 알고리즘을 활용한 산불 객체 탐지", 디지털콘텐츠학회논문지, 23(9), pp.1869~1877 (2022), 한국디지털콘텐츠학회
- K. Avazov, "Forest Fire Detection and Notification Method Based on AI and IoT Approaches", Future Internet, 15(2) (2023)[DOI]
- 박소민, "컬러 정보와 YOLOv4를이용한 불꽃 검출 연구", Proceedings of KIIT Conference, 2022(12), pp.404~407 (2022), 한국정보기술학회
- 김치용, "데이터 증강 학습 이용한 딥러닝 기반 실시간 화재경보시스템 구현", 전기전자학회논문지, 26(3), pp.468~474 (2022), 한국전기전자학회
- Y. Ahn, "Development of early fire detection model for buildings using computer vision-based CCTV", Journal of Building Engineering, 65 (2023)[DOI]
- J. Pincott, "Indoor fire detection utilizing computer vision-based strategies", Journal of Building Engineering, 61 (2022)[DOI]
- J. Redmon, "You only look once: Unified, real-time object detection", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.779~788 (2016)
- "GitHub - ultralytics/ultralytics: NEW - YOLOv8? in PyTorch > ONNX > OpenVINO > CoreML > TFLite"[URL]
- "What is YOLOv8? The Ultimate Guide" (2023)[URL]