Earticle

초록

영어

In this paper, we propose a novel, fast model for detecting fire flame and smoke using object detection and 3D classification, referred to as FastFireDet3D. This model uses NanoDet to quickly identify potential areas representing fire and smoke, followed by a novel 3D classification model based on a spatio-temporal convolutional neural network (STCNN). This two-step process allows for efficient and accurate detection. The average processing time for FastFireDet3D is approximately 40-90ms when run on a CPU, and it achieves an accuracy improvement of 3.45% over traditional Convolutional 3D (C3D) models.

목차

Abstract
1. Introduction
2. Fire detection using object detection and temporal region classification
3. Experimental results
3.1 STCNN vs. C3D: PCA Performance
3.2 STCNN vs. C3D: t-SNE Performance
3.3 t-SNE Fire/Smoke Distribution: STCNN vs. C3D
3.4 Model Performance
4. Conclusion
Acknowledgement
References

키워드

저자

• Kigon Park [ Assistant Professor, Dept. of AI Meta Convergence, Graduate School, Namseoul Univ., Korea/Ph.D. Course, Kyung Hee Univ., Korea ]
• Minjun Oh [ M.S. Course, Kyung Hee Univ., Korea ]
• Daeho Lee [ Professor, Dept. of Software Convergence, Graduate School, Kyung Hee Univ., Korea ]
• Kiseo Park [ Professor, Dept. of Electronics & Information Engineering, Kyung Hee Cyber Univ., Korea ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Internet, Broadcasting and Communication

• 간기

  계간

• pISSN

  2288-4920

• eISSN

  2288-4939

• 수록기간

  2009~2025

• 십진분류

  KDC 326 DDC 380