Success Stories

Improvement of shrub detection map using Deep Learning

Back to article

Title: Improvement of shrub detection map using Deep Learning

Description: Comparison of the maps and accuracies of the shrub detection maps obtained with an OBIA-based model and a CNN-based model. The symbols (+), (-) and (Fn) stand for true positive, false positive, and false negative, respectively.

The white values on the top of the bounding boxes in the right panel show the probabilities, calculated by ResNet-detector, of having a Ziziphus lotus shrub. Precision represents how many detected Ziziphus lotus were true, recall or sensitivity represents how many actual Ziziphus lotus were detected, and balanced score (F1 measure) evaluates the balance between precision and recall.

Copyright: Map data: Google, DigitalGlobe. Guirado et al., 2017. MDPI/processed by Universities of Almería and Granada

Initial Floating Portlet

See messages from the community

Sentiboard is an open digital platform facilitating sharing of information related to the users and usage of Copernicus Sentinel data
Go to sentiboard