Hierarchical Segmentation Evaluation of Region-Based Image Hierarchy

Hierarchical Segmentation Evaluation of Region-Based Image Hierarchy
复制标题

基于区域的图像层次结构的层次分割评估

DOI:
10.1109/jstars.2019.2926425
复制
发表时间:
2019-08
影响因子:
5.5
通讯作者:
Wu Guofeng
Wu Guofeng
中科院分区:
工程技术3区
文献类型:
--
作者:
Wu Zhaocong;He Lin;Hu Zhongwen;Zhang Yi;Wu Guofeng

文献摘要

参考文献

相似文献

多尺度图像分割在基于对象的图像分析(OBIA)应用中占有重要地位,分割质量的评价是OBIA研究的热点。近年来,随着多尺度和层次化策略在OBIA中的应用,基于区域的图像层次结构得到了越来越多的关注。基于区域的图像层次(即,二叉划分树和尺度集层次)是一种树状结构,它可以用来记录多尺度分割结果。虽然许多方法已被用来评估多尺度分割,他们不能直接应用于评估基于区域的图像层次。在这项研究中,提出了一种分层分割评估方法来评估基于区域的图像层次的上限精度。在我们的研究中,实现了一个图像层次结构,使用区域合并过程,并组织成一个规模索引的二进制分区树;每个参考多边形的最佳匹配段,然后通过扫描整个层次结构中选择;最后,参考多边形和相应的最佳匹配段之间的相似性被用来评估层次结构的整体性能。采用高分辨率遥感影像(GaoFen-2和QuickBird)和三种区域合并准则对该方法的有效性进行了验证。此外,该方法与传统的多尺度评价策略进行了比较。实验结果证明了该方法的有效性,以及与现有方法相比的优势。
Multiscale image segmentation plays an important role in object-based image analysis (OBIA) applications, and the evaluation of segmentation quality is a hot topic for OBIA community. Recently, with the increasing use of multiscale and hierarchical strategy in OBIA works, region-based image hierarchies have attracted increasing attentions. A region-based image hierarchy (i.e., binary partition tree and scale-sets hierarchy) is a tree-like structure, and it can be used to record multiscale segmentation results. Although many methods have been employed to evaluate multiscale segmentation, they cannot be applied to evaluate a region-based image hierarchy directly. In this study, a hierarchical segmentation evaluation approach was proposed to evaluate the upper-bound accuracy of a region-based image hierarchy. In our study, an image hierarchy is implemented using a region merging process, and organized as a scale-indexed binary partition tree; the best matching segment of each reference polygon is then selected by scanning whole hierarchy; and finally, the similarity between reference polygons and corresponding best matching segments are used to evaluate the overall performance of the hierarchy. Two high spatial resolution images (GaoFen-2 and QuickBird) and three region merging criteria were used to evaluate the effectiveness of the proposed approach. Moreover, the proposed method was compared with traditional multiscale evaluation strategies. The experimental results have demonstrated the effectiveness of the proposed approach, as well as the advantages compared to existing approaches.
DOI: 10.1016/j.patrec.2014.04.019
发表时间: 2014-10
期刊: Pattern Recognit. Lett.
影响因子: --
作者:
B. R. Kiran;J. Serra
通讯作者: B. R. Kiran;J. Serra
考虑分段内和分段间异质性的区域合并:一种改进的混合遥感图像分割方法
DOI: 10.3390/rs10050781
发表时间: 2018-05
期刊: Remote Sensing
影响因子: 5
作者:
Wang Yongji;Qi Qingwen;Meng Qingyan;Yang Jian;Liu Ying
通讯作者: Liu Ying
用于监督和无监督图像分割评估的基于学习的框架
DOI: 10.1142/s0219467814500144
发表时间: 2014-08
影响因子: 1.6
作者:
Jian Lin;Bo Peng;Tianrui Li
通讯作者: Tianrui Li
DOI: 10.1016/j.rse.2014.12.020
发表时间: 2015-03
影响因子: 13.5
作者:
G. Tochon;J. Féret;S. Valero;R. Martin;D. Knapp;P. Salembier;J. Chanussot;G. Asner
通讯作者: G. Tochon;J. Féret;S. Valero;R. Martin;D. Knapp;P. Salembier;J. Chanussot;G. Asner
DOI: 10.1016/j.ejrs.2017.03.001
发表时间: 2017-06
期刊: The Egyptian Journal of Remote Sensing and Space Science
影响因子: --
作者:
H. Bakhtiari;A. Abdollahi;Hani Rezaeian
通讯作者: H. Bakhtiari;A. Abdollahi;Hani Rezaeian