Unmanned aerial vehicles (UAVs) have become important components of modern systems for monitoring, inspection, mapping, and autonomous intervention. Their performance directly depends on the efficiency of the control systems and the architecture used for data processing, decision-making, and mission coordination. The paper presents a comparative analysis of the main control architectures used in UAV platforms: control with on-board processing (On-Board Control), hierarchical Master-Swarm architecture, and centralized systems based on a Ground Control System (GCS). It describes the operating principles of each architecture, the hardware and software components involved, advantages, limitations, and specific areas of application. The analysis highlights the impact of each solution on autonomy, scalability, resilience to communication loss, and real-time control performance. The results obtained show that On-Board Control systems offer superior autonomy and robustness, Master-Swarm architectures are intended particularly for the collaborative coordination of drone swarms, and GCS systems provide advanced capabilities for monitoring and centralized processing. Furthermore, current trends oriented towards hybrid architectures are highlighted, which combine the advantages of the three models to increase the level of autonomy, safety, and operational efficiency of modern UAV systems.
Near-infrared imagery is essential for vegetation monitoring, precision agriculture, and environmental remote sensing, but multispectral UAV systems remain significantly more expensive and less accessible than conventional RGB imaging platforms. This study presents a lightweight artificial intelligence framework for reconstructing the NIR spectral band exclusively from the red spectral band acquired by a UAV. The proposed methodology formulates the reconstruction task as a pixel-wise nonlinear regression problem and employs a compact multilayer perceptron (MLP) containing only 609 trainable parameters, without exploiting spatial neighborhood information. The framework was developed and evaluated using 280 synchronized multispectral UAV image sets acquired with a DJI Phantom 4 Multispectral platform over a heterogeneous agricultural landscape in the Republic of Moldova. Of these, 252 image sets were used for model development, and 28 were reserved as a held-out within-mission test subset. Quantitative evaluation on a held-out test dataset from the same acquisition mission yielded a mean squared error of 0.010329, a root mean squared error of 0.101632, a mean absolute error of 0.079883, a coefficient of determination of 0.253383, and a Pearson correlation coefficient of 0.683637 between measured and reconstructed normalized NIR digital intensities. The results indicate that the model captures part of the red–NIR relationship under the evaluated acquisition conditions; however, the moderate coefficient of determination suggests that the reconstructed values are an approximation rather than a replacement for measured NIR observations. An illustrative NDVI-based assessment showed that broad spatial vegetation patterns remained identifiable. Rather than introducing a new neural network architecture, this work establishes a compact empirical baseline to investigate the practical performance and limitations of pixel-wise NIR reconstruction from a single red-band value with minimal model complexity.