基于光谱相似尺度的SVM荔枝信息提取——以增城市中新镇为例

Extracting lichi information based on support vector machines and spectral similarity scale

运用基于光谱相似尺度(SSS)的支持向量机(SVM)新方法提取荔枝信息。选取广东增城市中新镇作为典型研究区,通过运用光谱相似尺度方法提取荔枝样本,运用SVM提取研究区的荔枝信息。通过实地调查与面积估算,结果表明该方法是基于遥感图像提取荔枝信息的一种切实可行的方法。

Lichi information was extracted based on support vector machines and spectral similarity scale in the paper Support Vector Machine（SVM） is a new prospecting technique in remote sensing. But the selection of object sample is always a difficult problem. Zhongxin town in Zengcheng city is taken as a typical region. Lichi samples are extracted by the means of Spectral Similarity Scale and lichi information is further extracted by the means of SVM. We find that the lichi information is nearly in accordance with the known lichi planting areas by on the spot investigation and area estimate. The experiment shows that it is an effective lichi information extraction approach.