CIVILICA We Respect the Science
(ناشر تخصصی کنفرانسهای کشور / شماره مجوز انتشارات از وزارت فرهنگ و ارشاد اسلامی: ۸۹۷۱)

Analysis and Study of Visual Tracking Algorithms

عنوان مقاله: Analysis and Study of Visual Tracking Algorithms
شناسه ملی مقاله: ICESCON02_147
منتشر شده در دومین کنفرانس بین المللی علوم و مهندسی در سال 1394
مشخصات نویسندگان مقاله:

Mahdi Tanbakuchi - StudentDepartment of Electrical and Computer EngineeringSouth Tehran BranchIslamic Azad UniversityTehran, Iran
Mojtaba Lotfizad - Department of Electrical and Computer EngineeringTarbiat Modares UniversityTehran, Iran

خلاصه مقاله:
In this paper, we analyze the most recent visual tracking algorithms. By studying the building blocks of such algorithms, we realize that these algorithms are based on either detection or stochastic filtering. Both methods need a way of modelling the target so that it can be recognized in subsequent frames; therefore, having algorithms that can describe the targets is crucial. Since the accuracy of the tracking algorithm relies on the descriptor, some competent descriptors are introduced here. To better understand the details of each type of algorithms, some of the most recent visual trackers are studied and their performances are compared

کلمات کلیدی:
feature extraction; descriptor; visual tracking; classification; particle

صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/490555/