This study explores the impact of video resolution on the performance of machine learning-based traffic monitoring systems. Using a combination of empirical analysis and theoretical modeling, we assess how different resolutions affect detection accuracy, resource consumption, and computational efficiency. While other factors such as noise level, or compression artifacts also influence performance, resolution was chosen as a primary variable due to its critical role in balancing detail capture and computational cost. Higher resolutions can enhance object detection accuracy but also significantly increase data processing demands, making resolution a key trade-off in designing efficient surveillance systems. Findings of this study show significant insights into these trade-offs, guiding transportation authorities and system developers in making informed decisions to design scalable traffic monitoring solutions that meet the demands of modern urban environments.

Nowadays, traffic congestion and air pollution in urban areas become huge challenges to transportation engineering. On the other hand, technologies have evolved, and simulation and artificial intelligence have become important tools to face these challenges. In this paper, a review of this research field is done, and a possible combination of simulation and machine learning to mitigate traffic emissions is proposed. The long-term goal of the research is to establish an effective emission mitigation model for some specific crossings.

The intersection area between two arbitrarily rotated ellipses is a recurring geometric primitive in imaging, computer vision, and robotics. In the general case, its evaluation is often associated with intersection-point recovery, topology-dependent case handling, adaptive refinement, or dense boundary approximation. This study presents a fixed-cost computational framework for ellipse–ellipse intersection based on a rotated-frame slice formulation. A coordinate-frame rotation expresses one ellipse in axis-aligned form while representing the second as a general conic. This yields a hybrid formulation that reduces the intersection area to a one-dimensional overlap integral of vertical slice height over the admissible horizontal interval. The integral is evaluated using fixed-order quadrature, with optional sine mapping to improve conditioning near grazing configurations. Numerical evaluation on 100,000 synthetic ellipse pairs shows that the proposed formulation reaches a low-error regime earlier than polygonal approximation while remaining substantially faster across the tested range. The formulation is further examined through a tree-crown delineation case study on the BAMFORESTS dataset, a benchmark forest dataset of very-high-resolution UAV imagery. In this case study, ellipse proxies derived from axis-aligned and oriented bounding box detections are used for overlap computation during non-maximum suppression (NMS). Using ellipse-proxy overlap during NMS preserves nearly the same peak F1 score of 0.785 while modestly shifting NMS behavior toward lower thresholds and producing slightly broader near-peak intervals.