Daliana Lobo Torres

Visiting PhD Student
Daliana

daliana0491@gmail.com

Research Interests

Agricultural activities have to be monitored on local to global scales at high temporal frequency due to their dependency on physical landscapes, climatic conditions, and seasonal patterns associated with crops’ biological life cycle. In addition, crop classification is a challenging task due to spatial and temporal changes crops experience within and between seasons. My current research lies in the area of weakly supervised learning to analyze crop dynamics for agricultural land cover mapping.

Education

  • Ph.D., Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Brazil, Aug 2020 - present
  • M.Sc., Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Brazil, Aug 2018 - Aug 2020

Publication

  • Lobo Torres, D., J. N. Turnes, P. J. S. Vega, R. Q. Feitosa, D.E. Silva, J. Marcato Jr, & C. Almeida. 2021. Deforestation detection with fully convolutional networks in the Amazon Forest from Landsat-8 and Sentinel-2 images, Remote Sensing 13(24), 5084.
  • Voelsen, M., Lobo Torres, D., Feitosa, R. Q., Rottensteiner, F., & Heipke, C. 2021. Investigations on feature similarity and the impact of training data for land cover classification. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 3, 181-189.
  • Lobo Torres, D., L.E Cué La Rosa, D. A. B. Oliveira, & R. Q. Feitosa, 2021. Evaluation of unsupervised deep clustering methods for crop classification using SAR image sequences. 2021 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2021). DOI: 10.1109/IGARSS47720.2021.9554548.
  • Turnes, J. N., Castro, J. D. B., Lobo Torres, D., Vega, P. J. S., Feitosa, R. Q., & Happ, P. N. 2020. Atrous cGAN for SAR to optical image translation. IEEE Geoscience and Remote Sensing Letters, DOI: 10.1109/LGRS.2020.3031199.
  • Lobo Torres, D., R. Q. Feitosa, P. N. Happ, L. E. C. La Rosa, J. Marcato Jr., J. Martins, P. O. Bressan, W. N. Gonçalves, & V. Liesenberg.2020. Applying fully convolutional architectures for semantic segmentation of a single tree species in an urban environment on high-resolution UAV optical imagery. Sensors 20(2), 563.