The objective of this work was to detect land use and land cover changes in the municipality of Rondon do Pará, in the Brazilian Legal Amazon, through the Geographic Object-based Image Analysis (GEOBIA), aiming to identify whether its inclusion in the list of priority municipalities for actions to prevent, monitor and control deforestation in the Amazon (Decree 6.321/2007), has inhibited this process. The methodological procedure involved the calculation of vegetation indices to highlight interest classes, the segmentation of the images into geo-objects and the classification using Support Vector Machine (SVM) algorithm. Also, we evaluated the relationship between annual rates of particulate material with a diameter of fewer than 2.5 micrometers (PM2.5) emitted from fires and deforestation in Rondon do Pará. The results show the reduction of deforestation rates but the conversion, in absolute values, of 984,47 km² of natural vegetation to anthropized areas along the 2006-2017 period, and the reduction of the average PM2.5 fire emissions from 31,107 tons year-1 between 2002 and 2007 to 10,394 ton year-1 in the post-inclusion period (2008-2019). This represents that the inclusion of Rondon do Pará in this list was beneficial, but the suppression of natural vegetation was not totally curbed, reinforcing that changes from environmental policies are gradual. Activities that do not use fire to suppress natural vegetation, such as selective logging, common in Rondon do Pará, had impact. This makes it necessary to intensify inspections and the development of sustainable actions in the region.