Edges are a basic and fundamental feature in image processing that is used directly or indirectly in huge number of applications. Inspired by the expansion of image resolution and processing power, dilated-convolution techniques appeared. Dilated convolutions have impressive results in machine learning, so naturally we discuss the idea of dilating the standard filters from several edge-detection algorithms. In this work, we investigated the research hypothesis that use dilated filters, rather than the extended or classical ones, and obtained better edge map results. To demonstrate this hypothesis, we compared the results of the edge-detection algorithms using the proposed dilation filters with original filters or custom variants. Experimental results confirm our statement that the dilation of filters have a positive impact for edge-detection algorithms from simple to rather complex algorithms.

Monitoring air quality is critical for understanding pollution impacts on public health. The Copernicus Atmosphere Monitoring Service (CAMS) provides estimates of nitrogen oxides (NO_x), nitrogen dioxide (NO₂), fine particulate matter (PM_2.5) and inhalable coarse particles (PM₁₀), but its spatial resolution may limit accuracy at individual urban stations. This study introduces a graph centrality-based framework for station-level correction of CAMS European reanalysis data using in situ observations from ARPA Lombardia (2018 to 2021). Stations are modelled as nodes in a multiplex graph, with spatial influence quantified through six centrality measures including topology-based and context-aware variants such as the Adapted PageRank Algorithm (APA) and Eigendata. The centrality features are integrated with Geo-Temporally Weighted Regression (GTWR), Extreme Gradient Boosting (XGBoost) and Random Forest with Spatio-Temporal Kriging (RF-STK), evaluated under station, temporal and combined holdout strategies. Under station holdout, XGBoost achieves an $R^2$ of up to 0.66 for NO₂, while RF-STK can exceed this when residual spatial kriging is active. Adding OpenStreetMap (OSM)-context APA centrality yields pollutant-dependent changes: gains for NO_x and PM_2.5, mixed results for NO₂, and a temporal improvement for PM₁₀ with RF-STK. Results confirm that graph-theoretic structural context complements station-level CAMS correction but is not a general surrogate for pollutant dispersion.