Sizhuo Li
Postdoc
Geografi 2
Øster Voldgade 10
1350 København K
Primære forskningsområder
I work in the interdisciplinary field of deep learning and remote sensing and I am interested in applying advanced neural networks to popular remote sensing problems, including intelligent forest management and carbon stock estimation. Development and adaptation of deep learning methods are the main focuses of my studies.
Aktuel forskning
An automatic and scalable tree inventory framework based on UNet, enabling individual crown segmentation, tree counting, and tree height estimation at the country scale.
Interesseområder
Deep learning, remote sensing
ID: 226574618
Flest downloads
-
118
downloads
Deep learning enables image-based tree counting, crown segmentation and height prediction at national scale
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Udgivet -
71
downloads
Nation-wide mapping of tree-level aboveground carbon stocks in Rwanda
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Udgivet -
40
downloads
More than one quarter of Africa's tree cover is found outside areas previously classified as forest
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Udgivet