Tropical forest conservation is a current issue of social and ecological relevance, due to their important role in the global ecosystem. Tropical forests have a great diversity of fauna and flora, act in the regulation of climate and rainfall, absorb large amounts of carbon dioxide, and serve as a home for countless indigenous peoples. Unfortunately, for years, thousands of hectares have been deforested and degraded in the Amazon rainforest. Government programs and private initiatives have emerged with the aim of mitigating the effects of the caused damage through monitoring and inspection. Most monitoring programs involve the inspection of remote sensing images by specialists, generally counting on the support of computational resources for automatic detection of patterns. This thesis proposes a novel %deforestation detection system called ForestEyes, which aims to detect deforestation in tropical forests based on Citizen Science and Machine Learning approaches. ForestEyes project uses non-specialist volunteers to inspect images in this target task, interacting with them through an appropriate graphical interface allocated on the well-known Citizen Science platform Zooniverse. In the performed experiments, six official campaigns have been carried out, receiving more than 81,000 contributions from 644 volunteers, the results of which were compared with the official monitoring program for the Brazilian Legal Amazon (PRODES). The volunteers, within the concept of the wisdom of crowds, achieved excellent data labeling when considered an efficient segmentation even for early deforestation detection which is considered a challenge for any similar system. These labeled data were used as a training set for different Machine Learning approaches which results were comparable and many times even better than the achieved by using the official monitoring program as input data. Thus, the volunteers' labeling proved to be reliable and robust, discarding noisy data that could decrease the classification's efficiency.
Two of the published papers are:
https://ieeexplore.ieee.org/document/8614310
https://ieeexplore.ieee.org/document/9041785