Aprendizado Ativo com dados de Ciência Cidadã para o monitoramento de florestas tropicais
Abstract
In April 2019 the Citizen Science project ForestEyes was launched, which uses non-specialized volunteers classifying remote sensing segments searching for deforested areas. In this work, these volunteers’ contributions build a small but efficient training set through an Active Learning procedure. This training set is built iteratively based on different strategies that choose samples that will bring more representativeness. The results showed the importance of a correct initial training set and the balancing of the samples in the classification accuracy.References
Fernanda B. J. R. Dallaqua, Álvaro L. Fazenda, and Fabio A. Faria. ForestEyes project: In IEEE 15th International Conference on Can citizen scientists help rainforests? eScience, pages 18–27. IEEE, 9 2019.
François Grey. Viewpoint: The age of citizen cyberscience. Cern Courier, 29, 2009.
Robert M. Haralick, Karthikeyan Shanmugam, et al. Textural features for image classication. IEEE Transactions on systems, man, and cybernetics, (6):610–621, 1973.
Trupti M. Kodinariya and Prashant R. Makwana. Review on determining number of cluster in k-means clustering. International Journal, 1(6):90–95, 2013.
Donald T. Lauer, Stanley A. Morain, and Vincent V. Salomonson. The landsat program: Its origins, evolution, and impacts. Photogrammetric Engineering and Remote Sensing, 63(7):831–838, 1997.
Eduardo F. P. Luz, Felipe R. S. Correa, Daniel L. González, François Grey, and Fernando M. Ramos. The forestwatchers: a citizen cyberscience project for deforestation monitoring in the tropics. Human Computation, 1(2):137–145, 2014.
Greg Schohn and David Cohn. Less is more: Active learning with support vector machi- nes. In ICML, volume 2, page 6. Citeseer, 2000.
Arfon M. Smith, Stuart Lynn, and Chris J. Lintott. An introduction to the zooniverse. In First AAAI conference on human computation and crowdsourcing, 2013.
Devis Tuia, Michele Volpi, Loris Copa, Mikhail Kanevski, and Jordi Munoz-Mari. A survey of active learning algorithms for supervised remote sensing image classication. IEEE Journal of Selected Topics in Signal Processing, 5(3):606–617, 2011.
Dalton M. Valeriano, Eliana M. K. Mello, José Carlos Moreira, Yosio E. Shimabukuro, Valdete Duarte, I. M. Souza, J. R. Santos, Claudio C. F. Barbosa, and R. C. M. Souza. Monitoring tropical forest from space: the prodes digital project. International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences, 35:272–274, 2004.
François Grey. Viewpoint: The age of citizen cyberscience. Cern Courier, 29, 2009.
Robert M. Haralick, Karthikeyan Shanmugam, et al. Textural features for image classication. IEEE Transactions on systems, man, and cybernetics, (6):610–621, 1973.
Trupti M. Kodinariya and Prashant R. Makwana. Review on determining number of cluster in k-means clustering. International Journal, 1(6):90–95, 2013.
Donald T. Lauer, Stanley A. Morain, and Vincent V. Salomonson. The landsat program: Its origins, evolution, and impacts. Photogrammetric Engineering and Remote Sensing, 63(7):831–838, 1997.
Eduardo F. P. Luz, Felipe R. S. Correa, Daniel L. González, François Grey, and Fernando M. Ramos. The forestwatchers: a citizen cyberscience project for deforestation monitoring in the tropics. Human Computation, 1(2):137–145, 2014.
Greg Schohn and David Cohn. Less is more: Active learning with support vector machi- nes. In ICML, volume 2, page 6. Citeseer, 2000.
Arfon M. Smith, Stuart Lynn, and Chris J. Lintott. An introduction to the zooniverse. In First AAAI conference on human computation and crowdsourcing, 2013.
Devis Tuia, Michele Volpi, Loris Copa, Mikhail Kanevski, and Jordi Munoz-Mari. A survey of active learning algorithms for supervised remote sensing image classication. IEEE Journal of Selected Topics in Signal Processing, 5(3):606–617, 2011.
Dalton M. Valeriano, Eliana M. K. Mello, José Carlos Moreira, Yosio E. Shimabukuro, Valdete Duarte, I. M. Souza, J. R. Santos, Claudio C. F. Barbosa, and R. C. M. Souza. Monitoring tropical forest from space: the prodes digital project. International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences, 35:272–274, 2004.
Published
2020-08-19
How to Cite
DALLAQUA, Fernanda; FAZENDA, Álvaro; FARIA, Fabio.
Aprendizado Ativo com dados de Ciência Cidadã para o monitoramento de florestas tropicais. In: REGIONAL SCHOOL OF ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING, 1. , 2020, São Paulo.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 30-33.
