A contextual classification approach for forest land cover mapping using high spatial resolution multispectral satellite imagery – a case study in Lake Tahoe, California
High spatial resolution imagery;Contextual classification;Forest classification;Remote sensing;Lifeforms
Maps of classified surface features are a key output from remote sensing. Conventional methods of pixel-based classification label each pixel independently by considering only a pixel’s spectral properties. While these purely spectral-based techniques may be applicable to many medium and coarse-scale remote sensing analyses, they may become less accurate when applied to high spatial resolution imagery in which the pixels are smaller than the objects to be classified. At this scale, there is a higher intra-class spectral heterogeneity. Detailed forest and vegetation classification is extremely challenging at this scale with both high intra-class spectral heterogeneity and inter-class spectral homogeneity. A solution to these issues is to take into account not only a pixel’s spectral characteristics but also its spatial characteristics into classification. In this study, we develop a generalizable contextualized classification approach for high spatial resolution image classification. We apply the proposed approach to map vegetation growth forms such as trees, shrubs, and herbs in a forested ecosystem in the Sierra Nevada Mountains.
【 预 览 】
附件列表
Files
Size
Format
View
A contextual classification approach for forest land cover mapping using high spatial resolution multispectral satellite imagery – a case study in Lake Tahoe, California