English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The inherent fuzziness of wetland ecosystems largely accounts for the spectral variability of wetland ecosystems in remote sensing images. In addition, a limited spatial resolution leads to the presence of many mixed pixels in middle-resolution multispectral remote sensing images. Existing methods that use a single center or a limited number of endmembers to represent land cover types cannot fully account for the spectral variability of land cover types; moreover, these methods use these limited representations to calculate the membership function (MF), leading to limited classification and mapping performance. To address spectral variability and mixed pixels, this study proposes a novel MF generation method, in which mixed pixels are treated as an auxiliary type, and the clustering and spectral characteristics are integrated to detect the cores of land cover types in spectral space. Then, the spectral diversity can be fully expressed by the core components of the land cover types. The membership values of mixed pixels are calculated from the core components via the sparse reconstruction method. The experiment shows that the proposed method has a substantial increase in classification accuracy over existing methods.

Generating Fuzzy Membership Functions for Modeling Wetland Ecosystems from Multispectral Remote Sensing Images