CASIA OpenIR  > 毕业生  > 硕士学位论文
基于S/T Graph Cuts的目标分割方法研究
Alternative TitleObject Segmentation based on S/T Graph Cuts
Thesis Advisor卢汉清 ; 程健
Degree Grantor中国科学院研究生院
Place of Conferral中国科学院自动化研究所
Degree Discipline模式识别与智能系统
Keyword目标分割 S/t Graph Cuts 感兴趣区域提取 Object Segmentation S/t Graph Cuts Attention Extraction
Abstract目标分割是计算机视觉领域的经典难题之一,是图像分类、视觉监控、目标识别等问题中的关键技术。因此,研究目标分割问题具有十分重要的意义。近年来,随着图理论的引入和研究的深入,基于S/T Graph Cuts的目标分割方法因其充实的理论基础和良好的性能成为了新的研究热点。 本文主要研究基于S/T Graph Cuts的目标分割方法。在传统S/T Graph Cuts分割方法的基础上,将人类视觉感知信息引入到分割框架中辅助先验模型的获取,减少甚至避免大量的用户的交互,从而提高算法的实用性和易用性。此外,本文对感兴趣区域的提取进行了一些有意义的尝试。本文的主要工作和创新如下: 1.对目标分割的方法进行了全面的综述,对各种方法的优缺点进行了分析和评价。重点对基于S/T Graph Cuts的目标分割方法进行了深入了研究,并通过大量的实验对交互式 S/T Graph Cuts及相关方法进行了分析和评价。 2.针对显著性区域分布复杂的图像,提出一种结合显著区域检测和S/T Graph Cuts的多分辨率自动分割框架:Saliency Cuts。借助感兴趣区域检测自动获取有效的目标和背景标注,能够完全避免用户交互并得到完整而高效的分割结果。 3.针对具有多个分散显著性区域的图像,提出了一种Local Saliency Cuts的框架,允许用户进行少量的操作即可实现指定目标的分割,同时也减少了全局计算的消耗时间。 4.针对移动设备上的图片浏览,提出一种基于不对称S/T Graph Cuts的感兴趣区域提取方法,能够有效而鲁棒地从图像中提取用户感兴趣的区域,也是目标分割的一个变形和应用上的扩展。
Other AbstractObject segmentation has been a challenging problem in computer vision and also plays an important role in many applications, such as image classification, object recognition, video surveillance, etc. In recent years, graph-theoretic segmentation methods have attracted much attention due to their solid theories and good performances. This thesis mainly emphasizes on object segmentation based on S/T Graph Cuts. We make some contributions on reducing user interactions and improving the practicability by introducing human vision related salient information into our framework. Besides that, we design a robust and effective attention extraction approach also based on S/T Graph Cuts. The contents and contributions of this thesis mainly include: 1.A comprehensive review for object segmentation and especially for segmentation based on S/T Graph Cuts is presented. The advantages and disadvantages of two typical S/T Graph Cuts methods are discussed through extensive experiments. 2.An automatic object segmentation framework, i.e. Saliency Cuts, is proposed for images with single salient objects. The proposed method integrates saliency detection and S/T Graph cuts which can supply efficient object and background labels and obtain complete and accurate segmentations automatically. 3.A "Local Saliency Cuts" framework is presented for segmentation of images with multi-salient regions or objects. Only a few interactions are involved to get satisfactory results, and the computing time is also reduced for the local manner. 4.An Asymmetrical Graph Cuts model is designed to extract the interesting attention regions for personalized image browsing in mobile devices. As a deformation and extend of object segmentation, the proposed model can supply robust and effective attention extraction compared to previous approaches.
Other Identifier200628014628029
Document Type学位论文
Recommended Citation
GB/T 7714
傅玉. 基于S/T Graph Cuts的目标分割方法研究[D]. 中国科学院自动化研究所. 中国科学院研究生院,2009.
Files in This Item:
File Name/Size DocType Version Access License
CASIA_20062801462802(2232KB) 暂不开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[傅玉]'s Articles
Baidu academic
Similar articles in Baidu academic
[傅玉]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[傅玉]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.