摘要
针对常见植被指数不能很好地降低非植被地物对植被分类提取的影响，设计了一种基于植被光谱特征的加权高光谱植被指数，并提出了一种基于加权高光谱植被指数的植被分类提取方案。先利用加权高光谱植被指数对植被信息进行提取，得到较为完整的植被分布信息，再利用典型分类算法进行植被分类，实验结果表明，本文提出的方案能够有效降低非植被地物的影响，提高植被分类提取的精度。
As the common vegetation index is not effective in reducing the impact of non - vegetation feature on vegetation classification and extraction, a weighted hyperspeetral vegetation index is designed based on vegetation spectral characteristics. A vegetation classification and extraction method based on weighted hyperspeetral vegetation index is proposed to reduce the impact of non - vegetation in the processing of vegetation classification. With this method, the index is used to extract vegetation from hy- perspectral image at first, and then SVM classification algorithm is employed to classify vegetation. The results show that the method can effectively reduce the impact of non - vegetation on vegetation classification, and improve the overall classification and extraction accuracy.
出处
《测绘科学与工程》
2015年第5期15-20,共6页
Geomatics Science and Engineering
关键词
高光谱影像
光谱特征
加权高光谱植被指数
植被分类提取
hyperspectral image
spectral characteristic
weighted hyperspectral vegetation index （ WHVI }
vegetation classi-fication and extraction
