In the field of smart mobility, Artificial Intelligence (AI) approaches are influential and can make a highly beneficial contribution. Our project aims to develop a real-time ecological map of road traffic. This map will allow electric vehicles (EVs) and thermal vehicles (TVs) to display the cost of energy consumption and CO${}_2$ emissions on different road sections. In urban environments, road traffic emissions are a significant contributor to environmental pollution, with vehicle emissions being a major component. Addressing these impacts requires a thorough understanding of the operational behavior of vehicles on different road infrastructures within the region. This paper presents a novel, comprehensive dataset, the Vehicle Activity Dataset (VAD), designed to assess the emissions and fuel consumption characteristics of vehicles about their actual operating environment. Constructed from a large number of real-world driving scenarios, VAD incorporates emission data collected by an industrial Portable Emission Measurement System (PEMS), road scenes captured by an RGB camera, and the detection of different object classes within these images. The primary objective of VAD is to provide a comprehensive understanding of the relationship between vehicle emissions and the diverse range of objects present on the road. Experimental results in real road traffic environments through different studies demonstrate the robustness of the developed dataset.

Traffic-related pollution significantly contributes to environmental degradation. The escalating demand for vehicles, coupled with consumer preferences for larger utility vehicles, poses a challenge to achieving targeted carbon emission reductions in common fleet vehicles. To address the inefficiencies in existing route planning methods, this paper introduces a novel eco-routing approach known as Visual Eco-Routing (VER). VER is designed to understand the non-linear relationships between captured road scenes and emissions data across various road links, providing a comprehensive insight into the real-time dynamics of roads and their influence on vehicle performance characteristics. On-road experimental cycles are conducted to gather data, creating a new dataset called the Vehicle Activity Dataset (VAD). To assess the viability of the VER approach, a model named VER-XGB based on eXtreme Gradient Boosting (XGBoost) is proposed. Performance comparisons are made by individual training and benchmarking three selected models, both without VER association and separately with VER association. The comparison reveals significantly lower prediction errors in models with VER, with VER-XGB exhibiting enhanced reliability, yielding MAPE of 4.83% with VAD. Additionally, an aggregate factor termed the emission factor is introduced to explore the correlation between emission gases and distinct groups of visual features defined in the study. The analysis indicates a high correlation between infrastructure features such as traffic signals and stop signs on the road and vehicle emission values. Concluding the study, a qualitative examination is undertaken to evaluate the real-world applicability of the model by predicting an eco-route for a given source and destination pair. The MAPE for this route for predictions from VER-XGB is found to be 6.21%, affirming the practical utility of the proposed VER-XGB model in real-world scenarios.

Monocular 3D object detection (Mono3D) is essential for autonomous driving and augmented reality, yet its performance degrades significantly at night due to the scarcity of annotated nighttime data. In this paper, we investigate the use of style transfer for nighttime data augmentation and evaluate its effect on individual components of 3D detection. Using CycleGAN, we generated synthetic night images from daytime scenes in the nuScenes dataset and trained a modular Mono3D detector under different configurations. Our results show that training solely on style-transferred images improves certain metrics, such as AP@0.95 (from 0.0299 to 0.0778, a 160% increase) and depth error (11% reduction), compared to daytime-only baselines. However, performance on orientation and dimension estimation deteriorates. When real nighttime data is included, style transfer provides complementary benefits: for cars, depth error decreases from 0.0414 to 0.021, and AP@0.95 remains stable at 0.66; for pedestrians, AP@0.95 improves by 13% (0.297 to 0.336) with a 35% reduction in depth error. Cyclist detection remains unreliable due to limited samples. We conclude that style transfer cannot replace authentic nighttime data, but when combined with it, it reduces false positives and improves depth estimation, leading to more robust detection under low-light conditions. This study highlights both the potential and the limitations of style transfer for augmenting Mono3D training, and it points to future research on more advanced generative models and broader object categories.