The Amazon region is constantly targeted by illegal activities, with one of the most prevalent being illegal mining. Due to the dense forest, the use of clandestine aviation becomes an alternative for supplying illicit activities in the region. This paper proposes a multi-stage algorithm based on convolutional neural networks to find the geographical location of landing strips in the proposed biome. Numerous band compositions were tested, with images in multiple radiometric resolutions, investigating how data transformation affects the technique. In this context, the developed algorithm has more than 90% recall rate in preliminary tests. For the test across the entire biome, the algorithm detected 93.30% of the already mapped landing strips and also identified new ones. Additionally, the entire activation took 43 hours, demonstrating a promising result for the rapid mapping of the biome. We verified that the integration of two sources of different sensors requires preprocessing, as the sensor responses to the same scene can be different, which complicates the neural network training stage. In this sense, artificially reducing the radiometric resolution of both sensors to a lower resolution proved to be a simple way to integrate different remote sensing data sources.
1 January 2025 in Journal of Aerospace Technology and Management
The use of unmanned aerial platforms has increasingly been demanded in various applications. Among these, in-flight inspection stands out, traditionally conducted by aircraft equipped with various sensors to verify the performance requirements of ground-installed navigation aids, as well as air navigation procedures for operational and airworthiness purposes. In-flight inspection is costly in terms of time, qualified personnel, necessary equipment, flight hours, and operational impact on the inspected aerodrome. In this context, the use of unmanned aerial systems (UAS) emerges as a potentially cost-effective alternative, with the potential to significantly reduce the costs associated with the in-flight inspection of navigation aids. This work presents the methodology and results of in-flight inspection of the precision approach path indicator (PAPI) using UAS. The results presented are selected from over a dozen field campaigns, wherein inspection procedures were adapted to replace conventional aircraft with UAS. The results were compared to traditional inspections performed by the conventional aircraft crewed with professional flight inspectors. The findings indicate a strong similarity between the UAS methodology and conventional inspection, suggesting that UAS could partially or completely replace conventional inspections, significantly reducing the time, costs, and impact of inspections carried out by conventional aircraft.
16 December 2025 in Revista Brasileira de Cartografia
Typically, the modernization of Land Administration Systems (LAS) concentrates on overarching aspects and seldom investigates the spatial infrastructure that underpins it, thereby presenting challenges for the integration of geospatial data. For this purpose, Discrete Global Grid Systems (DGGS), characterized by its "congruent cartography", offer a promising solution within a multi-scale reference framework. Moreover, a significant gap exists in the absence of a DGGS designed to address the cartographic focus and usability requirements for land administration, such as equal-area sizing and geodetic precision. Developed at the Aeronautics Institute of Technology (ITA), the ITA Cadastral Ellipsoidal Reference Tessellation (ITACaRT) was introduced as an innovative DGGS to bridge this gap. The development of ITACaRT was guided by several key criteria, including its suitability for cadastral purposes at appropriate scales, compatibility with the WGS84 ellipsoid and Global Navigation Satellite Systems (GNSS), utilization of simple parallelogram-shaped equal-area cells, a direct tessellation adhering to Cartesian geometry for usability by geoinformation professionals, and decimal convergence to facilitate blockchain tokenization. Complementary to these criteria, a Compositional Hierarchical Indexing system was devised to represent cadastral vector features more efficiently than the atomic identifiers typical of conventional DGGS. ITACaRT thus establishes a solid foundation for contemporary LAS, providing a viable spatial infrastructure that supports emerging technologies such as blockchain.