TRABALHOS DE FIM DE CURSO @PUC-Rio
| Título: | SEMANTIC SEGMENTATION IN DEFORESTATION AREAS | ||||||||||||
| Autor(es): |
THIAGO MATHEUS BRUNO DA SILVA |
||||||||||||
| Colaborador(es): |
RAUL QUEIROZ FEITOSA - Orientador MABEL XIMENA ORTEGA ADARME - Coorientador |
||||||||||||
| Catalogação: | 13/DEZ/2021 | Língua(s): | PORTUGUESE - BRAZIL |
||||||||||
| Tipo: | TEXT | Subtipo: | SENIOR PROJECT | ||||||||||
| Notas: |
[pt] Todos os dados constantes dos documentos são de inteira responsabilidade de seus autores. Os dados utilizados nas descrições dos documentos estão em conformidade com os sistemas da administração da PUC-Rio. [en] All data contained in the documents are the sole responsibility of the authors. The data used in the descriptions of the documents are in conformity with the systems of the administration of PUC-Rio. |
||||||||||||
| Referência(s): |
[pt] https://www.maxwell.vrac.puc-rio.br/projetosEspeciais/TFCs/consultas/conteudo.php?strSecao=resultado&nrSeq=56551@1 [en] https://www.maxwell.vrac.puc-rio.br/projetosEspeciais/TFCs/consultas/conteudo.php?strSecao=resultado&nrSeq=56551@2 |
||||||||||||
| DOI: | https://doi.org/10.17771/PUCRio.acad.56551 | ||||||||||||
| Resumo: | |||||||||||||
|
Deforestation is of no doubt an hugely important problem, which affects directly some destructive
phenomena such as biodiversity reduction, climate change among other destructive phenomena.
Therefore, is of tremendously importance to detect early deforestation. Motivated by this
problem, this work proposes an new method for automatic deforestation detection, based on semantic
segmentation, using ResUnet-a multitasking with a new Semi-Supervised Change vector analysis
(CVA) task. The objective of this work is to study the contribution of CVA to our change detection
problem and compare its relevance with the other tasks. Besides, we want observe the different
choices of threshold used on the whole training and its impact on final main segmentation task. The
method was evaluated in a region of the Brazilian Legal Amazon. In our experiments were used two
images of Landsat 8 acquired in 2018 and 2019 which were concatenated on the input.
|
|||||||||||||
|
|||||||||||||