Roan Grandfather LongHope

<div>Source Data</div><div><p><a href='https://nrcs.app.box.com/v/naip/folder/59364119980' rel='nofollow ugc'><span style='font-size:12.0pt; font-family:&quot;Segoe UI&quot;,sans-serif;'>The
National Agriculture Imagery Program (NAIP) Color Infrared Imagery, captured in
2018</span></a><span style='font-size:12.0pt; font-family:&quot;Segoe UI&quot;,sans-serif;'> </span></p></div><div><br /></div><div>Processing Methods</div><div><ol><li>downloaded NAIP imagery tiles for all Southern Appalachian sky islands with spruce forest type present.  </li><li>Mosaiced individual imagery tiles by sky island.  This step resulted in a single, seamless imagery raster dataset for each sky island.</li><li>Changed the raster band combination of the mosaiced sky island imagery to visually enhance the spruce forest type from the other forest types.  Typically, the band combination was Band 2 for Red, Band 3 for Green, and Band 1 for Blue. </li><li>Utilizing the ArcGIS Pro Image Analyst extension, performed an image segmentation of the mosaiced sky island imagery.  Segmentation is a process in which adjacent pixels with similar multispectral or spatial characteristics are grouped together. These objects represent partial or complete features on the landscape.  In this case, it simplified the imagery to be more uniform by forest type present in the imagery, especially for the spruce forest type.</li><li>Utilizing the segmented mosaiced sky island imagery, training samples were digitized.  Training samples are areas in the imagery that contain representative sites of a classification type that are used to train the imagery classification.  Adequate training samples were digitized for every classification type required for the imagery classification.  The spruce forest type was included for every sky island.  </li><li>Classified the segmented mosaiced sky island imagery utilizing a Support Vector Machine (SVM) classifier.  The SVM provides a powerful, supervised classification method that is less susceptible to noise, correlated bands, and an unbalanced number or size of training sites within each class and is widely used among researchers.  This step took the segmented mosaiced sky island imagery and created a classified raster dataset based on the training sample classification scheme.  </li><li>Reclassified the classified dataset only retaining the spruce forest type and shadows class.</li><li>Converted the spruce and shadows raster dataset to polygon.</li></ol></div><div><br /></div>

<div>源数据</div><div><p><a href='https://nrcs.app.box.com/v/naip/folder/59364119980' rel='nofollow ugc'><span style='font-size:12.0pt; font-family:&quot;Segoe UI&quot;,sans-serif;'>2018年采集的国家农业影像计划（National Agriculture Imagery Program, NAIP）彩色红外影像</span><span style='font-size:12.0pt; font-family:&quot;Segoe UI&quot;,sans-serif;'> </span></p></div><div><br /></div><div>处理流程</div><div><ol><li>下载所有分布有云杉林的阿巴拉契亚南部天空岛的NAIP影像瓦片。</li><li>按每个天空岛拼接单幅影像瓦片，最终得到每个天空岛对应的单张无缝影像栅格数据集。</li><li>调整拼接后天空岛影像的波段组合，以强化云杉林与其他林型的视觉差异。常规波段组合为：红通道对应波段2，绿通道对应波段3，蓝通道对应波段1。</li><li>借助ArcGIS Pro影像分析（Image Analyst）扩展模块，对拼接后的天空岛影像执行图像分割。图像分割是将具有相似多光谱或空间特征的相邻像素聚合为地物对象的过程，这些对象可代表地表上的部分或完整地物。本步骤中，分割操作可根据影像中的林型（尤其云杉林）将影像简化为更均质的单元。</li><li>基于分割后的拼接影像，数字化训练样本。训练样本指影像中包含待分类类型代表性区域的样本，用于训练影像分类模型。本数据集为所有影像分类所需的林型均采集了足量的训练样本，且每个天空岛均包含云杉林类型的训练样本。</li><li>采用支持向量机（Support Vector Machine, SVM）分类器对分割后的拼接影像进行分类。支持向量机是一种鲁棒性强的监督分类方法，不易受噪声、波段相关性及各类别训练样本数量/规模不均衡的影响，被研究者广泛使用。本步骤通过分割后的拼接影像，基于训练样本的分类体系生成分类后的栅格数据集。</li><li>对分类后的数据集进行重分类，仅保留云杉林与阴影两类。</li><li>将包含云杉林与阴影的栅格数据集转换为多边形矢量格式。</li></ol></div><div><br /></div>