文章基本信息

标题：Real Time Video Segmentation in Cluttered Environment using Graph Cut Approach
本地全文：下载
作者：Karthik S ; Dr. Jharna Majumdar
期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2018
卷号：7
期号：1
页码：121
DOI：10.15680/IJIRSET.2018.0701022
出版社：S&S Publications
摘要：In this paper we extend the work done in [1] in which graph based approach is described. The algorithmdefines a predicate used for segmenting images. In this paper we show the analysis of the defined predicate and varythe threshold K of the predicate and examine the regions generated and determine the best predicate for segmentingimages and we further extend this work by implementing segmentation in a video on cluttered environment on 3different categories of video such as entertainment, sports and nature. For a real life application, video sequence can beof much longer duration. In order to handle the seamless video sequence efficiently, we have proposed one of the waysof handling the memory. Multithreading and Process Concurrency is the underlying principle employed in the model.
关键词：Segmentation; Graph-cut; Graph-weights; Memory model; Multi-threading.