Abstract
Abstract: For a long time, in many countries, questions involving disputes about land ownership has generated demand for geoinformation and documentation. In most cases, access for researchers is restricted or humanely impossible by eminence of conflicts, even armed. In these cases, researchers use Remote Sensing and Photogrammetry to enable their studies. However, the dynamics of the phenomenon being studied often requires approaches that traditional techniques become unviable or unable to fulfil. This work shows the results of an approach that used a photogrammetric UAV platform to take pictures of an invaded rural area in Brazil and estimate its expansion over two years. From the taken images, mosaics were generated and then classified using Decision Tree to identify tents. Then it was developed a Matlab algorithm, to detect and quantify the tents on the classified Images. It was possible to infer that there was an expansion of 7.3% between the two analyzed dates and probably more than three thousand people occupied the invasion site.
Highlights
Land conflicts have always been part of the Brazilian countrys history and often motivated by disputes over property and land use (Brumer and Santos, 2006)
Teixeira (2015) presented an analysis of land conflicts arising from the illegal occupation on protected areas at the vicinity of a pilot area of colonization in Rondônia (Brazil)
In order to obtain some kind of ground truth and allow an evaluation of the proposed approach a manual vectorization of all tents found in the scenes was done
Summary
Land conflicts have always been part of the Brazilian countrys history and often motivated by disputes over property and land use (Brumer and Santos, 2006). A common case in Brazil for this scenario is the land invasion areas with eminent armed conflicts For this example, the photogrammetric approach based on Unmanned Aerial Vehicles - UAV's platform is a good option to acquire geoinformation. The authors highlighted that the use of UAVs equipped with "off the shelf" instruments (digital cameras and position and orientation sensors) combined with Computer Vision and Geomatics knowledge, allowed semi-automatic generation of horizontal and vertical spatial information with positional quality at the centimeter level For this scenario, the Structure From Motion – SFM, has been wildly used as a modern tool for UAV's images processing (Westoby et al, 2012).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
