پديد آورنده :
عليداري، حمزه
عنوان :
افزايش سرعت و كيفيت آشكارسازي اشياء متحرك مبتني بر تخمين چگالي كرنل
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
مخابرات ﴿سيستم﴾
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
صفحه شمار :
دوازده، 93ص.: مصور جدول، نمودار
استاد راهنما :
محمدرضا احمدزاده
توصيفگر ها :
اختلاف گيري زماني , ميدان تصادفي ماركوف
تاريخ نمايه سازي :
1394/05/19
استاد داور :
بهزاد نظري، مازيار پالهنگ
تاريخ ورود اطلاعات :
1396/10/04
رشته تحصيلي :
برق و كامپيوتر
دانشكده :
مهندسي برق و كامپيوتر
چكيده فارسي :
به فارسي و انگليسي
چكيده انگليسي :
Speeding Up and Quality Enhancement of Moving Object Detection Based on Kernel Density Estimation Hamzeh Alidadi h alidadi@ec iut ac ir Data of Submission 2015 05 30 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran 84156 83111Degree Master of Science Language PersianSupervisors name Dr Mohammad Reza Ahmadzadeh ahmadzadeh@cc iut ac irAbstract Nowadays machine vision systems have been developed in different sectors of life including industry commerce transportation etc Moving objects detection is the first andmost basic step in some areas of machine vision The important approaches used in thedetection of moving objects include Background subtraction temporal differencing and theoptical flow Background subtraction approach is the most efficient approach and is widelyused to detect moving objects in the fixed cameras In recent years some techniques havebeen proposed for performing background subtraction approach One of the efficientapproach is the kernel density estimation approach In this approach the probability of eachpixels is calculated and then the probabilities are compared with a threshold value and thenthe moving area is detect In this thesis we present a fast and robust background subtractionmethod based on kernel density estimation The background is modeled using spatial temporal data and in order to improve the detection accuracy foreground is modeled onsmall spatio neighbors High computation complexity is one problem of the kernel densityestimation method To overcome this problem and also to enhance the detection rate thedifference between consecutive frames is used so that if only the difference is more than athreshold value the proposed method will model the background and foreground and willdetect the moving object To improve and enhance the spatial correlation in the detection Markov model is used Simulation results show that the proposed method outperforms otherrecent methods Keywords moving object detection kernel density estimation temporal differencing markov random field
استاد راهنما :
محمدرضا احمدزاده
استاد داور :
بهزاد نظري، مازيار پالهنگ
