딥런닝 기반의 프레임 유사성을 이용한화재 오탐 검출 개선 연구
Fase Positive Fire Detection Improvement Research using the Frame Similarity Principal based on Deep Learning
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
화염 및 연기 감지 알고리즘 연구는 다양한 모양, 빠른 확산 및 색상으로 인해 컴퓨터 비전에서 어려운 과제이다. 일반적인센서 기반 화재 감지 시스템의 성능은 환경 요인 (실내 및 화재발생 위치)에 따라 크게 제한된다. 이러한 문제를 해결하기위해 딥러닝 방법을 적용하였으며, 이것은 물체의 형상을 특징으로 추출하므로 비슷한 형상이 프레임내에 존재하면 오탐으로검출 될 수 있다. 본 연구는 화재 오탐 검출 개선을 위해 딥런닝 사용 전과 후에 프레임 유사성을 이용하여 오탐을 줄이는새로운 알고리즘을 제안한다. 실험결과 제안된 방법을 적용하여 화재 검출 성능은 유지를 하면서 오탐 부분이 최소 30% 까지 감소하는 결과를 얻을 수 있었다. 제안된 방법의 오탐 검출 성능이 뛰어나다는 것을 확인하였다.
Abstract
Fire flame and smoke detection algorithm studies are challenging task in computer vision due to the variety of shapes,rapid spread and colors. The performance of a typical sensor based fire detection system is largely limited byenvironmental factors (indoor and fire locations). To solve this problem, a deep learning method is applied. Because itextracts the feature of the object using several methods, so that if a similar shape exists in the frame, it can be detectedas false postive. This study proposes a new algorithm to reduce false positives by using frame similarity before usingdeep learning to decrease the false detection rate. Experimental results show that the fire detection performance ismaintained and the false positives are reduced by applying the proposed method. It is confirmed that the proposed methodhas excellent false detection performance
참고문헌 (15)
- Byoung Chul Ko, "Modeling and Formalization of Fuzzy Finite Automata for Detection of Irregular Fire Flames", IEEE Transactions on Circuits and Systems for Video Technology, 21(12), pp.1903~1912 (2011), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- H. Yamagishi, "A Contour Fluctuation data Processing Method for Fire Flame Detection using a Color Camera", IEEE 26th Annual Conference on IECON of the Industrial Electronics Society, pp.824~ (2000)
- T. Celik, "Automatic Fire Detection in Video Sequences", Proceeding of European Signal Processing Conference (2016)
- T. Chen, "An Early Fire-Detection Method Based on Image processing", 2004 International Conference on Image Processing, pp.1707~1707 (2004)
- C. B. Liu, "Vision Based Fire Detection", 2004 International Conference on Pattern Recognition, pp.34~ (2004)
- F. N. Yuan, "Feature Extraction for Computer Vision Based Fire Detection", Journal of University Science and Technology of China, pp.39~43 (2006)
- B. Uğur Töreyin, "Computer vision based method for real-time fire and flame detection", Pattern Recognition Letters, 27(1), pp.49~58 (2006), Elsevier BV[DOI]
- N. Dedeoglu, "Real-time Fire and Flame Detection in Video", ICASSP’05, pp.669~672 (2005)
- T. B. CelikT, "Wavelet Based Real-time Smoke Detection in Video", EUSIPO 2005 (2005)
- Chunyu Yu, "A Real-time Video Fire Flame and Smoke Detection Algorithm", Procedia Engineering, 62, pp.891~898 (2013), Elsevier BV[DOI]
- S. Frizzi, "Convolutional Neural Network for Video Fire and Smoke Detection", IECON 2016 (2016)
- Y. Lecun, "Gradient-based learning applied to document recognition", Proceedings of the IEEE, 86(11), pp.2278~2324 (1998), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- A. Krizhevsky, "ImageNet Classification with Deep convolutional neural Network : Advanced in Neural Information Processing System 25", 26th Annual Conference on Neural Information Processing Systems, pp.1106~1114 (2012)
- G. E. Hinton, "Improving neural networks by preventing co-adaptation of feature detectors", Clinical Orthopedics and Related Research 2012 (2012)
- 김형석, "가변 비트레이트 스트리밍을 위한 명암도 기반의 효율적인 비디오 화질측정 기법", 한국차세대컴퓨팅학회 논문지, 11(5), pp.63~71 (2015), 한국차세대컴퓨팅학회