传统光谱分类法的局限性促使了遥感“图谱耦合”认知理论的发展, 使其更加注重了空间信息的应用。 然而, 已有的分类方法虽也融入了空间形态、空间关系的应用, 在精度上有一定的提高, 但在空间规律定量描述、 地物实际分布边界跟踪等方面仍存在不足。本文发展了一种空间邻接支持下的遥感影像分类方法: 通过基准地物的 精确提取进而搜索与其邻接的目标地物, 对邻接范围内的地类混淆以及非邻接范围内的目标类误分一并进行修正, 并以近海地物分类为例进行试验, 获得了更为精确、合理的分类结果, 也为后续逐步精确地提取各地物提供了一种 便捷有效的途径。

The image classification is a key step for remote sensing data transforming into practical information and knowledge, which has always been the core problem in the remote sensing field. The limitations in traditional spectral classification method otherwise promotes the theory development on the spatial-spectral coupled information cognition of remote sensing, which focuses more on the spatial relationship. However, the current classification revision methods have configured the spatial forms and relationship while, going further, but there still exist some deficiencies in spatial distribution theorem about quantitative description, objects’ actual distribution, and so on. Thus, the paper proposes a spatial-adjacencysupported classification revision method inclusive of reference object extraction, target object pixels searching and reference adjacent objects distinguishing which detailed steps are: (1) marking the objects out and getting their distribution rangepicking up the other objects in the range, (2) selecting them as the target object, picking out the unavailable target object in the range and selecting them as a certain objectwhich also provides a convenient and effective way for stepwise and accurate extraction of other objects subsequently. We also carried out an experiment on offshore area classification revision, and the result proved to be more accurate and reasonable.