Analyzing fine-scale wetland composition using high resolution imagery and texture features
Analyzing fine-scale wetland composition using high resolution imagery and texture features
复制标题
DOI：
10.1016/j.jag.2013.01.003
复制
发表时间：
2013-08
期刊：
影响因子：
--
通讯作者：
Z. Szantoi;F. Escobedo;A. Abd-Elrahman;Scot E. Smith;L. Pearlstine
中科院分区：
文献类型：
--
作者：
Z. Szantoi;F. Escobedo;A. Abd-Elrahman;Scot E. Smith;L. Pearlstine
为了监测自然和人为干扰对湿地生态系统的影响，有必要采用湿禾本科/莎草群落的准确和快速的映射。因此，期望利用自动分类算法，使得可以定期地并且以有效的方式进行监测。本研究开发了一种分类和精度评估方法湿地制图的风险植物群落在沼泽地国家公园的泥灰岩草原和沼泽地区。最大似然（ML）和支持向量机（SVM）分类器进行了测试，使用30.5厘米航空影像，归一化差异植被指数（NDVI），一阶和二阶纹理特征和辅助数据。此外，适当的窗口大小为不同的纹理特征估计使用半变异函数分析。研究结果表明，增加的NDVI和纹理特征的分类精度从66.2%使用ML分类器（光谱波段）的83.71%使用SVM分类器（光谱波段，NDVI和一阶纹理特征）。
In order to monitor natural and anthropogenic disturbance effects to wetland ecosystems, it is necessary to employ both accurate and rapid mapping of wet graminoid/sedge communities. Thus, it is desirable to utilize automated classification algorithms so that the monitoring can be done regularly and in an efficient manner. This study developed a classification and accuracy assessment method for wetland mapping of at-risk plant communities in marl prairie and marsh areas of the Everglades National Park. Maximum likelihood (ML) and Support Vector Machine (SVM) classifiers were tested using 30.5cm aerial imagery, the normalized difference vegetation index (NDVI), first and second order texture features and ancillary data. Additionally, appropriate window sizes for different texture features were estimated using semivariogram analysis. Findings show that the addition of NDVI and texture features increased classification accuracy from 66.2% using the ML classifier (spectral bands only) to 83.71% using the SVM classifier (spectral bands, NDVI and first order texture features).