Fire Detection Algorithms Using Multimodal ... - Bilkent University

More documents

Recommendations

Info

CHAPTER 2. FLAME DETECTION IN VISIBLE RANGE VIDEO 27Both the 1-D temporal wavelet analysis described in Subsection 2.2.3 andthe 2-D spatial wavelet analysis are computationally efficient schemes because amultiplierless filter bank is used for both 1-D and 2-D wavelet transform computation[34], [45]. Lowpass and highpass filters have weights { 1, 1, 1 −1} and { , 1, −1},4 2 4 4 2 4respectively. They can be implemented by register shifts without performing anymultiplications.The wavelet analysis based steps of the algorithm are very important in fireand flame detection because they distinguish ordinary motion in the video frommotion due to turbulent flames and fire.2.3 Decision FusionIn this section, we describe a voting based decision fusion strategy. However,other data fusion methods can be also used to combine the decision of four stagesof the flame and fire detection algorithm.Voting schemes include unanimity voting, majority voting, and m-out-of-nvoting. In m-out-of-n voting scheme, an output choice is accepted if at leastm votes agree with the decisions of n sensors [60]. We use a variant of m-outof-nvoting, the so-called T -out-of-v voting in which the output is accepted ifH = ∑ i w iv i > T where the w i ’s are user-defined weights, the v i ’s are decisionsof the four stages of the algorithm, and T is a user-defined threshold. Decisionparameter v i can take binary values 0 and 1, corresponding to normal case andthe existence of fire, respectively. The decision parameter v 1 is 1 if the pixel isa moving pixel, and 0 if it is stationary. The decision parameter v 2 is taken as1 if the pixel is fire-colored, and 0 otherwise. The decision parameter v 3 is 1 ifthe probability value of flame model is larger than that of non-flame model. Thedecision parameter v 4 is defined in Equation (2.12).In uncontrolled fire, it is expected that the fire region should have a nonconvexboundary. To gain a further robustness to false alarms, another stepchecking the convexity of the fire region is also added to the proposed algorithm.
CHAPTER 2. FLAME DETECTION IN VISIBLE RANGE VIDEO 28Convexity of regions is verified in a heuristic manner. Boundaries of the regionsin the <strong>Fire</strong> mask are checked for their convexity along equally spaced five verticaland five horizontal lines using a 5 × 5 grid. The analysis simply consists ofchecking whether the pixels on each line belong to the region or not. If at leastthree consecutive pixels belong to the background, then this region violates theconvexity condition. A <strong>Fire</strong> mask region which has background pixels on theintersecting vertical and/or horizontal lines, is assumed to have a non-convexboundary. This eliminates false alarms due to match light sources, sun, etc.2.4 Experimental ResultsThe proposed method, Method-2.1, is implemented on a PC with an Intel Pentium4, 2.40 GHz processor. It is tested for a large variety of conditions incomparison with the method utilizing only the color and temporal variation information,which we call Method-2.2, described in [64]. The scheme describedin [17] is also implemented for comparison and it is called as Method 3 in therest of the article. The results for some of the test sequences are presented inTable 2.2.(a)(b)Figure 2.9: (a) With the method using color and temporal variation only(Method-2.2) [64], false alarms are issued for the fire colored line on the movingtruck and the ground, (b) our method (Method-2.1) does not produce anyfalse alarms.
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 27 and 28: Chapter 2Flame Detection in Visible
Page 29 and 30: CHAPTER 2. FLAME DETECTION IN VISIB
Page 45: CHAPTER 2. FLAME DETECTION IN VISIB
Page 55 and 56: CHAPTER 3. FLAME DETECTION IN INFRA
Page 73 and 74: Chapter 4Short Range Smoke Detectio
Page 75 and 76: CHAPTER 4. SHORT RANGE SMOKE DETECT
Page 87 and 88: Chapter 5Flame Detection Using PIRS
Page 89 and 90: CHAPTER 5. FLAME DETECTION USING PI
Page 97 and 98:
CHAPTER 5. FLAME DETECTION USING PI
Page 99 and 100:
CHAPTER 5. FLAME DETECTION USING PI
Page 101 and 102:
CHAPTER 6. WILDFIRE DETECTION 82In
Page 103 and 104:
CHAPTER 6. WILDFIRE DETECTION 84are
Page 105 and 106:
CHAPTER 6. WILDFIRE DETECTION 86D 1
Page 107 and 108:
CHAPTER 6. WILDFIRE DETECTION 88tha
Page 109 and 110:
CHAPTER 6. WILDFIRE DETECTION 90The
Page 111 and 112:
CHAPTER 6. WILDFIRE DETECTION 92D 1
Page 113 and 114:
CHAPTER 6. WILDFIRE DETECTION 94as
Page 115 and 116:
CHAPTER 6. WILDFIRE DETECTION 96Sol
Page 117 and 118:
CHAPTER 6. WILDFIRE DETECTION 98as
Page 119 and 120:
CHAPTER 6. WILDFIRE DETECTION 100Un
Page 121 and 122:
CHAPTER 6. WILDFIRE DETECTION 102is
Page 123 and 124:
CHAPTER 6. WILDFIRE DETECTION 104Ta
Page 125 and 126:
Chapter 7Conclusion and Future Work
Page 127 and 128:
CHAPTER 7. CONCLUSION AND FUTURE WO
Page 129 and 130:
Bibliography[1] B. Albers and A. Ag
Page 131 and 132:
BIBLIOGRAPHY 112[18] D. Chetverikov
Page 133 and 134:
BIBLIOGRAPHY 114[38] G. Healey, D.
Page 135 and 136:
BIBLIOGRAPHY 116[56] U. Niesen, D.
Page 137 and 138:
BIBLIOGRAPHY 118[77] C. Stauffer an
show all

Fire Detection Algorithms Using Multimodal ... - Bilkent University

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?