显著度模型的地标提取方法综述
发布时间：2018-12-29 07:19
【摘要】：针对地标显著度模型的构成、计算方法及存在的突出问题,该文在对国内外大量文献进行分析研究的基础上,系统综述了基于显著度模型提取地标的方法。指出了现有研究中存在的主要问题和不足,围绕感知显著度、认知显著度、上下文显著度、总体显著度的计算方法,进行了较为深入的研究,并针对性地提出了解决方案。
[Abstract]:Aiming at the constitution, calculation method and existing problems of landmark saliency model, this paper systematically summarizes the methods of extracting landmarks based on saliency model based on the analysis and study of a large number of literatures at home and abroad. This paper points out the main problems and shortcomings of the existing research, and makes a more in-depth study on the calculation methods of perceptual significance, cognitive significance, contextual significance and total salience, and puts forward a solution.
【作者单位】： 信息工程大学;
【基金】：国家“863”计划项目(2013AA12A202) 国家自然科学基金项目(41371382)
【分类号】：TN96
本文编号：2394477
[Abstract]:Aiming at the constitution, calculation method and existing problems of landmark saliency model, this paper systematically summarizes the methods of extracting landmarks based on saliency model based on the analysis and study of a large number of literatures at home and abroad. This paper points out the main problems and shortcomings of the existing research, and makes a more in-depth study on the calculation methods of perceptual significance, cognitive significance, contextual significance and total salience, and puts forward a solution.
【作者单位】： 信息工程大学;
【基金】：国家“863”计划项目(2013AA12A202) 国家自然科学基金项目(41371382)
【分类号】：TN96
【相似文献】
相关期刊论文 前1条
1 曾鹏;许平;;基于视觉显著度的H.264冗余片编码技术[J];江汉大学学报(自然科学版);2013年01期
相关博士学位论文 前1条
1 赖重远;形状部分的视觉显著度与形状编码[D];华中科技大学;2013年
，本文编号：2394477
本文链接：https://www.wllwen.com/kejilunwen/xinxigongchenglunwen/2394477.html
