Traffic has a direct impact on local and regional economies, on pollution levels and is also a major source of discomfort and frustration for the public who have to deal with congestion, accidents or detours due to road works or accidents. Congestion in urban areas is a common phenomenon nowadays, as the main arteries of cities become congested during peak hours or when there are additional constraints such as traffic accidents and road works that slow down traffic on road sections. When traffic increases, it is observed that some roads are predisposed to congestion, while others are not. It is evident that both congestion and urban traffic itself are influenced by several factors represented by complex geospatial data and the spatial relationships between them. In this paper were integrated mathematical models, real time traffic data with network analysis and simulation procedures in order to analyze the public transportation in Oradea and the impact on urban traffic. A mathematical model was also adapted to simulate the travel choices of the population of the city and of the surrounding villages. Based on the network analysis, traffic analysis and on the traveling simulation, the elements generating traffic congestion in the inner city can be easily determined. The results of the case study are emphasizing that diminishing the traffic and its effects can be obtained by improving either the public transport density or its accessibility.

Popular geo-computer vision works make use of aerial imagery, with sizes ranging from 64 × 64 to 1024 × 1024 pixels without any overlap, although the learning process of deep learning models can be affected by the reduced semantic context or the lack of information near the image boundaries. In this work, the impact of three tile sizes (256 × 256, 512 × 512, and 1024 × 1024 pixels) and two overlap levels (no overlap and 12.5% overlap) on the performance of road classification models was statistically evaluated. For this, two convolutional neural networks used in various tasks of geospatial object extraction were trained (using the same hyperparameters) on a large dataset (containing aerial image data covering 8650 km² of the Spanish territory that was labelled with binary road information) under twelve different scenarios, with each scenario featuring a different combination of tile size and overlap. To assess their generalisation capacity, the performance of all resulting models was evaluated on data from novel areas covering approximately 825 km². The performance metrics obtained were analysed using appropriate descriptive and inferential statistical techniques to evaluate the impact of distinct levels of the fixed factors (tile size, tile overlap, and neural network architecture) on them. Statistical tests were applied to study the main and interaction effects of the fixed factors on the performance. A significance level of 0.05 was applied to all the null hypothesis tests. The results were highly significant for the main effects (p-values lower than 0.001), while the two-way and three-way interaction effects among them had different levels of significance. The results indicate that the training of road classification models on images with a higher tile size (more semantic context) and a higher amount of tile overlap (additional border context and continuity) significantly impacts their performance. The best model was trained on a dataset featuring tiles with a size of 1024 × 1024 pixels and a 12.5% overlap, and achieved a loss value of 0.0984, an F1 score of 0.8728, and an ROC-AUC score of 0.9766, together with an error rate of 3.5% on the test set.

Urban areas have developed organically over time, driven by the economic success of cities. However, this development has usually been accompanied by the side effects of urbanization, such as increased traffic and its associated problems: traffic congestion, increased accident rates and pollution. As urban populations grow and expand, the importance of GIS lies in its ability to collect a large amount of geospatial data, including human-generated data. This data is necessary to understand the complexity of the city, set priorities, solve complicated planning problems and perform a variety of spatial analysis, which shows not only the feasibility but also the consistency of the proposed infrastructure with the requirements of a sustainable city. In this paper, we demonstrate the benefits of integrating real-time traffic data with GIS technology and remote sensing data for analyzing the impact of infrastructure works and COVID-19 on traffic in Oradea, Romania. The case study was focused on the historical center of Oradea and was based on remote sensing data collected before, during, and after traffic restrictions. The study also shows the need for using GIS and crowdsourcing-based applications in traffic analysis and planning.