8795

8156

كارشناسي ارشد

هوش مصنوعي و رباتيك

اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر

1392

نه،73ص.: مصور،جدول،نمودار(رنگي)

ص.ع.به فارسي و انگليسي

مازيار پالهنگ

13/2/93

بهزاد نظري

مهندسي برق و كامپيوتر

ID8156

A Region Based CAMShift Tracking with a Moving Camera Mohammad Mahdi Kaseer m kaseer@ec iut ac ir Date of Submission 2013 09 15 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisor Dr Maziar Palhang palhang@cc iut ac irAbstractVisual tracking algorithms have important applications in machine vision Visual tracking algorithms with a movingcamera must be robust to camera motion CAMShift algorithm is a fast and simple color based tracking algorithm but itis not robust to camera motion because it faces with a problem when the tracked object moves across regions ofbackground with similar colors with tracked object Some algorithms have been proposed to reduce this problem majority of these algorithms try to reduce the problem by adding more limitations to object model such as addingsaturation and value information in addition to hue By imposing these limitations parts of color similarity problemssolved except regions which their colors are similar by hue saturation and value Another approach is ABCShiftalgorithm that tries to reduce this problem by adaptive learning of background All proposed methods assign aprobability of belonging a pixel to the object In this thesis we assign a probability to regions instead of pixels Assigning probability to regions leads to more accurate algorithm because we can add some regions information such asarea of regions and we can add some information about relation between these regions We first demonstrate theproblems of CAMShift and then we show how this approach can improve CAMShift algorithm especially in situationsthat there are similar colors in background Keywords CAMShift Region Based CAMShift RCAMShift tracking with moving camera

مازيار پالهنگ

بهزاد نظري