Unmanned Aerial Vehicles (UAVs) represent easy, affordable, and simple solutions for many tasks, including the collection of traffic data. The main aim of this study is to propose a new, low-cost framework for the determination of highly accurate traffic flow parameters. The proposed framework consists of four segments: terrain survey, image processing, vehicle detection, and collection of traffic flow parameters. The testing phase of the framework was done on the Zagreb bypass motorway. A significant part of this study is the integration of the state-of-the-art pre-trained Faster Region-based Convolutional Neural Network (Faster R-CNN) for vehicle detection. Moreover, the study includes detailed explanations about vehicle speed estimation based on the calculation of the Mean Absolute Percentage Error (MAPE). Faster R-CNN was pre-trained on Common Objects in COntext (COCO) images dataset, fine-tuned on 160 images, and tested on 40 images. A dual-frequency Global Navigation Satellite System (GNSS) receiver was used for the determination of spatial resolution. This approach to data collection enables extraction of trajectories for an individual vehicle, which consequently provides a method for microscopic traffic flow parameters in detail analysis. As an example, the trajectories of two vehicles were extracted and the comparison of the driver’s behavior was given by speed—time, speed—space, and space—time diagrams.

The United Nations (UN) stated that all new roads and 75% of travel time on roads must be 3+ star standard by 2030. The number of stars is determined by the International Road Assessment Program (iRAP) star rating module. It is based on 64 attributes for each road. In this paper, a framework for highly accurate and fully automatic determination of two attributes is proposed: roadside severity-object and roadside severity-distance. The framework integrates mobile Lidar point clouds with deep learning-based object detection on road cross-section images. The You Only Look Once (YOLO) network was used for object detection. Lidar data were collected by vehicle-mounted mobile Lidar for all Croatian highways. Point clouds were collected in .las format and cropped to 10 m-long segments align vehicle path. To determine both attributes, it was necessary to detect the road with high accuracy, then roadside severity-distance was determined with respect to the edge of the detected road. Each segment is finally classified into one of 13 roadside severity object classes and one of four roadside severity-distance classes. The overall accuracy of the roadside severity-object classification is 85.1%, while for the distance attribute it is 85.6%. The best average precision is achieved for safety barrier concrete class (0.98), while the worst AP is achieved for rockface class (0.72).

Understanding how built structures and urban vegetation jointly relate to population patterns is increasingly important for sustainable urban planning. This study used airborne LiDAR data to analyze three-dimensional urban morphology across Zagreb, Croatia, at neighborhood and district scales. A 1 m nDSM and classified rasters were used to derive canopy, building, height, volumetric, and built–vegetation balance metrics. Spatial clustering was assessed using Moran’s I, LISA, and Getis–Ord Gi*, while relationships with population density were evaluated using correlation and spatial regression models. At the neighborhood level, canopy cover ranged from 4.5% to 84.7%, while UMI ranged from 0.002 to 10.368. UMI showed significant spatial clustering (Moran’s I = 0.457, p = 0.001), with 24 high–high and 64 low–low clusters. Composite balance metrics outperformed individual vegetation or building indicators; logUMI provided the strongest performance for log-transformed population-density models, with SLM pseudo-R² = 0.903. Agreement assessment showed high consistency for canopy cover (R² = 0.997), while building height agreement was weaker for global datasets. Results indicate that transformed built–vegetation balance metrics provide useful complementary indicators for describing urban morphology and population density patterns.

Accurate information on intra-urban population distribution is essential for urban planning, infrastructure management, exposure assessment, and evidence-based decision-making. However, census data are usually available only for predefined administrative units and often lack the spatial detail required for fine-scale urban analyses. This study evaluates a top-down approach for estimating population distribution within the city of Zagreb, Croatia, using building footprints, three-dimensional building characteristics, OpenStreetMap (OSM) semantic information, and census population counts. The citywide population total was redistributed to LiDAR-derived roof and WSF-derived settlement polygons and aggregated to 17 city districts for validation. Two built-environment datasets were tested: locally derived LiDAR roof polygons and WSF-derived settlement polygons. Area-based scenarios were implemented for both datasets, while height-enhanced scenarios incorporated LiDAR-derived nDSM information. The WSF height-enhanced scenario therefore combined globally available WSF geometry with locally derived LiDAR height information and is referred to as WSF + nDSM. Results show that 3D models consistently outperformed 2D models. Total relative error (TRE) decreased from 15.5% to 11.8% for LiDAR and from 19.6% to 11.4% for WSF. OSM-based refinement further improved all scenarios, with the LiDAR 3D + OSM and WSF + nDSM + OSM scenarios achieving comparable overall performance (TRE = 9.0% for both at the city-district validation level). These findings demonstrate the value of combining vertical and semantic building information for more accurate urban population disaggregation.

The physicochemical composition of honey reflects its botanical origin, environmental conditions, and post-harvest handling; however, studies that combine long-term monitoring data with multivariate and spatial analyses at a metropolitan scale remain limited. This study analyzed acacia, chestnut, flower, and meadow honeys from the Zagreb metropolitan region, Croatia, using a long-term physicochemical quality dataset from the Zzzagimed International Honey Quality Competition collected between 2007 and 2019. From a total database of 351 samples, 82 georeferenced samples from the City of Zagreb and Zagreb County were selected and evaluated for moisture, electrical conductivity, free acidity, and hydroxymethylfurfural (HMF). Most samples met general honey quality requirements: only three samples exceeded the moisture threshold of 20%, and no samples exceeded the limits for HMF or free acidity. Electrical conductivity and free acidity provided the clearest differentiation among honey types, ranging from 0.22 to 1.47 mS/cm and from 9.77 to 27.38 meq/kg, respectively. Multivariate analysis showed that physicochemical variability was structured primarily by honey type, with the first two principal components explaining 62.8% of the total variance. Spatial analyses revealed weak to moderate spatial structure, with residual autocorrelation retained only for free acidity. Honeys from the Zagreb region showed good physicochemical quality, and their variability was driven mainly by declared botanical origin rather than by broad City–County differences.