خط مشی دسترسیدرباره ما
ثبت نامثبت نام
راهنماراهنما
فارسی
ورودورود
صفحه اصلیصفحه اصلی
جستجوی مدارک
تمام متن
منابع دیجیتالی
رکورد قبلیرکورد بعدی
Document Type : Latin Dissertation
Language of Document : English
Record Number : 149667
Doc. No : ET21459
Main Entry : NWMANIA PETROVIC
Title Proper : CAL MODELS FOR V ERSTANDING
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : With the growing proliferation of cameras and sensors, video and multimedia are becoming an indispensable part ofour daily lives. The unprecedented production and consumption of visual information are making autonomous videoanalysis one of the most active and challenging research areas.In this work I will focus on building a bridge between video data understanding and machine learning methods,which is a promising, but still not fully explored direction. I will specifically focus on model-based video analysisutilizing statistical graphical models. The core of our work is the investigation and design of clustering, inference, andlearning algorithms applied to the video data. I will show how the inference in these models can be used to answer anumber of queries useful for video analysis and processing.Having the applications as the ultimate goal, I will demonstrate the algorithmic techniques for speeding up thenaYve learning in the graphical models by orders of magnitude.tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject : Electericl tess
: برق
electronic file name : TL44626.pdf
Title and statement of responsibility and : CAL MODELS FOR V ERSTANDING [Thesis]
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)