高分辨率遥感影像多特征灌丛提取方法研究

Research on Multi-feature Shrub Extraction Method Based on GF-1 Remote Sensing Images

采用GF-1 PMS影像Level 2级影像产品,以云贵高原喀斯特地貌中的灌丛为研究对象,通过提出FSSDM(Forest and Shrub Spectrum Discrimination Model)模型,并将该模型与专题指数特征、纹理特征进行特征组合,采用SVM分类器进行自动解译,以解决实际生产中灌丛与背景植被易混淆、识别正确率不高的问题。研究发现,FSSDM模型能够有效区分灌丛与林地、阴影,结合指数特征和纹理特征,可快速、高效地将灌丛从复杂背景中提取出来,且精度优于传统提取方法。

This paper adopts GF-1 PMS image Level 2 image product, takes shrubs in the Yunnan-Guizhou Plateau karst landform as the research object, and proposes the FSSDM(Forest and Shrub Spectrum Discrimination Model) model, and combines the model with thematic index features and texture features. The feature combination is automatically interpreted by the SVM classifier to solve the problem that the shrub and the background vegetation are easy to be confused in actual production, and the recognition rate is low. The study found that combining with exponential features and texture features, the FSSDM model can effectively distinguish between shrubs and woodlands, shadows, can quickly and efficiently extract shrubs from complex backgrounds, and the accuracy is better than traditional extraction methods.