Superpixel Generation by the Iterative Spanning Forest Using Object Information

F. Belém, A. Falcão, S. Guimarães
{"title":"Superpixel Generation by the Iterative Spanning Forest Using Object Information","authors":"F. Belém, A. Falcão, S. Guimarães","doi":"10.5753/SIBGRAPI.EST.2020.12979","DOIUrl":null,"url":null,"abstract":"Superpixel segmentation methods aim to partition the image into homogeneous connected regions of pixels (i.e., superpixels) such that the union of its comprising superpixels precisely defines the objects of interest. However, the homogeneity criterion is often based solely on color, which, in certain conditions, might be insufficient for inferring the extension of the objects (e.g., low gradient regions). In this dissertation, we address such issue by incorporating prior object information — represented as monochromatic object saliency maps — into a state-of-the-art method, the Iterative Spanning Forest (ISF) framework, resulting in a novel framework named Object-based ISF (OISF). For a given saliency map, OISF-based methods are capable of increasing the superpixel resolution within the objects of interest, whilst permitting a higher adherence to the map’s borders, when color is insufficient for delineation. We compared our work with state-of-the-art methods, considering two classic superpixel segmentation metrics, in three datasets. Experimental results show that our approach presents effective object delineation with a significantly lower number of superpixels than the baselines, especially in terms of preventing superpixel leaking.","PeriodicalId":307185,"journal":{"name":"Anais Estendidos da Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2020)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Anais Estendidos da Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2020)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5753/SIBGRAPI.EST.2020.12979","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

Superpixel segmentation methods aim to partition the image into homogeneous connected regions of pixels (i.e., superpixels) such that the union of its comprising superpixels precisely defines the objects of interest. However, the homogeneity criterion is often based solely on color, which, in certain conditions, might be insufficient for inferring the extension of the objects (e.g., low gradient regions). In this dissertation, we address such issue by incorporating prior object information — represented as monochromatic object saliency maps — into a state-of-the-art method, the Iterative Spanning Forest (ISF) framework, resulting in a novel framework named Object-based ISF (OISF). For a given saliency map, OISF-based methods are capable of increasing the superpixel resolution within the objects of interest, whilst permitting a higher adherence to the map’s borders, when color is insufficient for delineation. We compared our work with state-of-the-art methods, considering two classic superpixel segmentation metrics, in three datasets. Experimental results show that our approach presents effective object delineation with a significantly lower number of superpixels than the baselines, especially in terms of preventing superpixel leaking.
基于目标信息的迭代生成森林生成超像素
超像素分割方法旨在将图像划分为像素(即超像素)的均匀连接区域,使得其包含的超像素的并集精确地定义感兴趣的对象。然而,均匀性标准通常仅基于颜色,在某些条件下,可能不足以推断物体的扩展(例如,低梯度区域)。在本文中,我们通过将先验对象信息(表示为单色对象显著性映射)合并到最先进的方法迭代生成森林(ISF)框架中来解决这一问题,从而产生了一个名为基于对象的ISF (OISF)的新框架。对于给定的显著性地图,基于oisf的方法能够增加感兴趣对象内的超像素分辨率,同时在颜色不足以描绘时允许更高的地图边界粘附性。我们将我们的工作与最先进的方法进行了比较,在三个数据集中考虑了两个经典的超像素分割指标。实验结果表明,该方法可以有效地描述目标,并且可以显著减少超像素的数量,特别是在防止超像素泄漏方面。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信