Fire Detection Algorithms Using Multimodal ... - Bilkent University
Fire Detection Algorithms Using Multimodal ... - Bilkent University Fire Detection Algorithms Using Multimodal ... - Bilkent University
CHAPTER 1. INTRODUCTION 7security guard of the forest look-out tower.The contribution of this work is twofold; a novel video based wildfire detectionmethod and a novel active learning framework based on the LMS algorithm. Theproposed adaptive fusion strategy can be used in many supervised learning basedcomputer vision applications comprising of several sub-algorithms.1.2 Thesis OutlineThe outline of the thesis is as follows. In Chapters 2 and 3, wavelet and HMMbased methods for flame detection in visible and IR range video are presented,respectively. The short-range smoke detection algorithm is presented in Chapter4. Detection of flames using PIR sensors is discussed in Chapter 5. In Chapter6, wildfire (long-range smoke) detection with active learning based on the LMSalgorithm is described. Finally Chapter 7 concludes this thesis by providing anoverall summary of the results. Possible research areas in the future are provided,as well.The organization of this thesis is presented in Table 1.1. Note that, smokedetection methods could only be developed for visible range cameras due to thefact that smoke cannot be visualized with PIR sensors and LWIR cameras.Table 1.1: Organization of this thesis.Sensor type Flame Short-range (< 30m) Long distance (> 100m)SmokeSmokeVisible Range Camera Chapter 2 Chapter 4 Chapter 6LWIR Camera Chapter 3 N/A N/APIR Sensor Chapter 5 N/A N/A
Chapter 2Flame Detection in VisibleRange VideoIn this chapter, the previous work in the literature on video based fire detection issummarized, first. Then, the proposed wavelet analysis and Markov model baseddetection method characterizing the flame flicker process is described. Markovmodel based approach reduces the number of false alarms issued to ordinaryfire-colored moving objects as compared to the methods using only motion andcolor clues. Experimental results show that the proposed method is successful indetecting flames.2.1 Related WorkVideo based fire detection systems can be useful for detecting fire in covered areasincluding auditoriums, tunnels, atriums, etc., in which conventional chemicalfire sensors cannot provide quick responses to fire. Furthermore, closed circuittelevision (CCTV) surveillance systems are currently installed in various publicplaces monitoring indoors and outdoors. Such systems may gain an early fire detectioncapability with the use of a fire detection software processing the outputsof CCTV cameras in real time.8
- Page 3 and 4: I certify that I have read this the
- Page 7 and 8: viiiçin de işaret işleme yöntem
- Page 9: ixThis work was supported in part b
- Page 14 and 15: LIST OF FIGURESxiv2.6 Three-state M
- Page 16 and 17: LIST OF FIGURESxvi4.4 Two moving ob
- Page 18 and 19: List of Tables1.1 Organization of t
- Page 20 and 21: Chapter 1IntroductionDynamic textur
- Page 22: CHAPTER 1. INTRODUCTION 3No fire de
- Page 29 and 30: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 31 and 32: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 33 and 34: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 35 and 36: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 37 and 38: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 39 and 40: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 41 and 42: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 43 and 44: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 45 and 46: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 47 and 48: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 49 and 50: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 51 and 52: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 53 and 54: CHAPTER 2. FLAME DETECTION IN VISIB
- Page 55 and 56: CHAPTER 3. FLAME DETECTION IN INFRA
- Page 57 and 58: CHAPTER 3. FLAME DETECTION IN INFRA
- Page 59 and 60: CHAPTER 3. FLAME DETECTION IN INFRA
- Page 61 and 62: CHAPTER 3. FLAME DETECTION IN INFRA
- Page 63 and 64: CHAPTER 3. FLAME DETECTION IN INFRA
- Page 65 and 66: CHAPTER 3. FLAME DETECTION IN INFRA
- Page 67 and 68: CHAPTER 3. FLAME DETECTION IN INFRA
- Page 69 and 70: CHAPTER 3. FLAME DETECTION IN INFRA
- Page 71 and 72: CHAPTER 3. FLAME DETECTION IN INFRA
Chapter 2Flame <strong>Detection</strong> in VisibleRange VideoIn this chapter, the previous work in the literature on video based fire detection issummarized, first. Then, the proposed wavelet analysis and Markov model baseddetection method characterizing the flame flicker process is described. Markovmodel based approach reduces the number of false alarms issued to ordinaryfire-colored moving objects as compared to the methods using only motion andcolor clues. Experimental results show that the proposed method is successful indetecting flames.2.1 Related WorkVideo based fire detection systems can be useful for detecting fire in covered areasincluding auditoriums, tunnels, atriums, etc., in which conventional chemicalfire sensors cannot provide quick responses to fire. Furthermore, closed circuittelevision (CCTV) surveillance systems are currently installed in various publicplaces monitoring indoors and outdoors. Such systems may gain an early fire detectioncapability with the use of a fire detection software processing the outputsof CCTV cameras in real time.8