Building Data Sets for Rainforest Deforestation Detection Through a Citizen Science Project

  • Fernanda Jordan Rojas Dallaqua Unifesp
  • Fabio Augusto Faria Unifesp
  • Álvaro Luis Fazenda Unifesp

Resumo


Originally, the ForestEyes project aims to detect deforestation in tropical forests based on citizen science (CS) and machine learning (ML) approaches, in which the volunteers analyze and label segments of remote sensing images to build new training sets for creating different classification models. In previous work, only three modules related to CS have been proposed. In this letter, two new modules are created: 1) organization and selection and 2) ML. Therefore, these modules turn the ForestEyes project a more robust system in the deforestation detection task, building high-confidence labeled collections, increasing the monitoring coverage, and decreasing volunteer dependence. Performed experiments show that volunteers create better data sets than those based on automatic PRODES-based approaches, selecting the most relevant samples and discarding noisy segments that might disrupt ML techniques. Finally, the results showed the feasibility of allying CS with ML for rainforest deforestation detection task.
Palavras-chave: Active learning (AL), image classification, machine learning (ML), supervised learning.
Publicado
07/11/2020
DALLAQUA, Fernanda Jordan Rojas; FARIA, Fabio Augusto; FAZENDA, Álvaro Luis. Building Data Sets for Rainforest Deforestation Detection Through a Citizen Science Project. In: CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 33. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 483-487.