RSOBIA - A new OBIA Toolbar and Toolbox in ArcMap 10.x for Segmentation and Classification
RSOBIA - A new OBIA Toolbar and Toolbox in ArcMap 10.x for Segmentation and Classification
复制标题
RSOBIA - ArcMap 10.x 中用于分割和分类的新 OBIA 工具栏和工具箱
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
T. L. Bas
中科院分区：
文献类型：
--
作者：
T. L. Bas
ArcMap 10.x的一个新工具箱将被呈现，它将数据层分割成一组多边形。该软件可在http://www.codemap.eu/Outputs上获得。每个多边形由K-均值聚类和区域生长算法定义，从而在图像中找到区域、它们的边缘和边界。每个多边形都附有图像的特征，例如多边形内像素值的平均值和标准差。将图像分割成多边形拼图的优点还在于，人类解释者不需要花费数小时将边界数字化。实际的分割过程取自分析和分类例程的RSGIS库（Bunting等人，2014年）。这些例程是免费软件，但已修改为在Windows操作系统下的ESRI ArcGIS软件中可用。分割过程的输入是多层光栅图像，例如，卫星图像或由地形衍生物组成的任何光栅数据集。集群的大小和数量由用户设置，并取决于所使用的图像。在ArcGIS环境中使用OBIA的优势在于它可以成为工作流的一部分，无论是单独的还是在模型中。这种集成加快了分析速度，并允许更容易地操纵数据。使用其数值特征对多边形进行有意义的分类可能非常依赖于数据主题。有许多分类系统可供使用，并根据现有数据加以调整。一个简单的分类工具是作为一个绘制功能提供的，但预计ArcMAP中的功能已经被用于执行复杂的分类规则。
A new toolbox for ArcMap 10.x will be presented that segments the data layers into a set of polygons. The software is available at http://www.codemap.eu/Outputs . Each polygon is defined by a K-means clustering and region growing algorithm, thus finding areas, their edges and boundaries in the imagery. Attached to each polygon are the characteristics of the imagery such as mean and standard deviation of the pixel values, within the polygon. The segmentation of imagery into a jigsaw of polygons also has the advantage that the human interpreter does not need to spend hours digitising the boundaries. The actual segmentation process has been taken from the RSGIS library of analysis and classification routines (Bunting et al., 2014). These routines are freeware but have been modified to be made available in the ESRI ArcGIS software under the Windows operating system. Input to the segmentation process is a multi-layered raster image, for example; satellite imagery, or any set of raster datasets made up from derivatives of topography. The size and number of clusters are set by the user and are dependent on the imagery used. The advantage of having OBIA within the ArcGIS environment is that it can become part of the workflow, either separately or in models. Such integration speeds analysis and allows easier manipulation of data. Meaningful classification of the polygons using their numerical characteristics can be very dependent on the data subject. Many classification systems are available and tailored to the data available. A simple classification tool is provided as a paint function, but it is expected that functionality within ArcMAP is already being used to undertake complex classification rules.