面向灾害应急土地覆被分类的样本自动选择方法研究

Automatically Samples Selection in Disaster Emergency Oriented Land-Cover Classification

通过对自动化样本选择方法进行研究,实现了局部区域内面向对象的土地覆被自动分类。首先通过模糊聚类获得影像中的候选对象样本,分别提取影像特征和先验知识中的地类特征,通过预设阈值完成样本初步筛选,然后根据先验知识进行半监督距离度量学习,完成样本的自动选择,并为最终的监督分类提供度量依据。应用舟曲泥石流灾区影像进行了实验,结果表明,本文方法与基于人工选择样本的分类结果精度非常接近,同时在多次实验中表现出较高的稳定性,相对人工方法更加客观,适合批量自动化处理。

The automation level of classification for remote sensing image need to be improved to satisfy the timeliness and high-precision requirements in disaster emergency monitoring and assessment. But, the artificial selection of typical samples restricts the automatic inter- pretation of disaster information, a problem particularly acute for the development of busi- ness operation systems. This paper implements a totally automatic object-oriented land cover classification system based on automatic sample selection. First, the candidate object sam- ples are acquired by fuzzy clustering. Second, image features and land type features are ex- tracted from imagery and prior knowledge, respectively. Afterward, samples can be selected by applying preset thresholds on these features. Distance metric learning is then used not on- ly for further sample selection, but also for more accurate supervised classification. Zhouqu Debris flow disaster images are computed by this method. Results show that the classifica- tion outcomes with samples selected automatically are very close to those samples selected by hand. Our results are more stable and objective than those produced manually. Moreover, it is more convenient to batch process images automatically.