تشخيص آتش در محيط هاي باز با استفاده از دنباله هاي ويدئويي

چكيده انگليسي :

Fire Detection for Outdoor Applications using Video Sequences Maedeh Jamali m jamali@ec iut ac ir Date of Submission Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Farsi Supervisor Dr Shadrokh Samavi samavi96@cc iut ac irAbstract Due to industrial deployment and expansion of urban zones early warning systems play critical role ingiving emergency response to unexpected events Fire detection systems are very important in comparisonwith other warning systems due to fire huge damage and its destructive power Nowadays many companiestry to present efficient methods for early fire detection which prevents further disasters Usually manpoweris used for monitoring in traditional methods of fire detection but they are costly and do not have suitableefficiency in some applications Fire sensors are modern methods which are used in fire and smokedetection These methods cannot be used in outdoor applications since an enormous number of sensors areneeded in order to have an adequate density and completely cover the area Hence an important disadvantageof point detectors is that they are distance limited and produce high rate of false alarms in outdoorenvironments Due to rapid developments in digital camera technology and improvement in computingpower and memory there is a major trend to replace conventional fire detection methods with vision basedsystems These systems can solve the shortcomings of previous methods Modern methods try toautomatically distinguish fire in their coverage area These methods are economical and reduce humanerrors Camera is an important part in such systems which covers vast areas and collects suitable informationabout size expansion velocity and fire locality In order to distinguish fire using a camera we need toprocess video sequences to find out the presence or absence of fire in them The main goal in fire detectionsystems is designing the systems with high detection rate low error rate and reasonable detection time Oneof the main requirements of vision based fire detection systems is features extraction with high separationcapability Therefore different methods are presented for extracting vision based information and fire regiondetection The goal of this thesis is to introduce an efficient method for fire detection in outdoor applicationusing video sequences We propose two models In the first one we use motion and color features due todynamism and color range of fire A more general method is proposed in second model which can be used inboth fixed and moving camera scenarios We use saliency map as a new feature for fire detection in this latermethod which distinguishes important regions in an image Texture descriptor in time domain for fire textureextraction provides another feature for this method which improves accuracy Keywords Video fire detection vision base information color space motion detection saliencydetection 3D texture descriptor

جمالي، مائده

تشخيص آتش در محيط هاي باز با استفاده از دنباله هاي ويدئويي

اطلاعات بصري , فضاي رنگ , تشخيص حركت , تشخيص برجستگي , توصيفگر بافت سه بعدي