Area 3 — UAV and Multimodal Remote Sensing

Our remote sensing work applies UAV-based platforms and multimodal AI frameworks to monitor forest ecosystems from the air. Key capabilities include: flower color indices for detecting phenological events from remote sensing imagery; vision-language learning models for species classification; and deep learning models for segmenting and mapping forest boundaries at regional scales across diverse landscapes.

We also work on super-resolution methods that transform low-resolution inputs — whether satellite imagery or sparse LiDAR point clouds — into high-fidelity outputs suitable for individual-tree detection and measurement.

Three images showing a plot of land. Image A shows an aerial view of a forest. B shows an aerial view of a small plot of trees within the larger forest. Image C shows a variety of yellow squares detecting where the trees are located in the image.

Publications

  1. Huang, Y., Ou, B., Meng, K., Yang, B., Carpenter, J., Jung, J., & Fei, S. (2024). Tree species classification from UAV canopy images with deep learning models. Remote Sensing, 16(20), 3836. https://doi.org/10.3390/rs16203836
  2. Thapa, B., Darling, L., Choi, D., Ardohain, C.M., Firoze, A., Aliaga, D.G., Hardiman, B.S., & Fei, S. (2024). Application of multi-temporal satellite imagery for urban tree species identification. Urban Forestry & Urban Greening, 98, 128409. https://doi.org/10.1016/j.ufug.2024.128409
  3. Thapa, B., Hardiman, B., & Fei, S. (2025). Flower color index for detecting and monitoring warm-colored flowering across scales. International Journal of Applied Earth Observation and Geoinformation, 145, 104978. https://doi.org/10.1016/j.jag.2025.104978
  4. Ou, B., Shao, G., Yang, B., & Fei, S. (2025). FocalSR: Revisiting image super-resolution transformers with Fourier-transform cross attention layers for remote sensing image enhancement. Geomatica, 77, 100042. https://doi.org/10.1016/j.geomat.2024.100042
  5. Ardohain, C., & Fei, S. (2025). The impacts of training data spatial resolution on deep learning in remote sensing. Science of Remote Sensing, 11, 100185. https://doi.org/10.1016/j.srs.2024.100185