Advancements in autonomous driving have seen unprecedented improvement in recent years. This work addresses the challenge of enhancing the navigation of autonomous vehicles in complex urban environments such as intersections and roundabouts through the integration of computer vision and unmanned aerial vehicles (UAVs). UAVs, owing to their aerial perspective, offer a more effective means of detecting vehicles involved in these maneuvers. The primary objective is to develop, evaluate, and compare different computer vision models and reduced-board (and small-power) hardware for optimizing traffic management in these scenarios. A dataset was constructed using two sources, several models (YOLO 5 and 8, DETR, and EfficientDetLite) were selected and trained, four reduced-board computers were chosen (Raspberry Pi 3B+ and 4, Jetson Nano, and Google Coral), and the models were tested on these boards for edge computing in UAVs. The experiments considered training times (with the dataset and its optimized version), model metrics were obtained, inference frames per second (FPS) were measured, and energy consumption was quantified. After the experiments, it was observed that the combination that best suits our use case is the YoloV8 model with the Jetson Nano. On the other hand, a combination with much higher inference speed but lower accuracy involves the EfficientDetLite models with the Google Coral board.

This article presents a remote management architecture of an unmanned aerial vehicles (UAVs) fleet to aid in the management of solar power plants and object tracking. The proposed system is a competitive advantage for sola r energy production plants, due to the reduction in costs for maintenance, surveillance, and security tasks, especially in large solar farms. This new approach consists of creating a hardware and software architecture that allows for performing different tasks automatically, as well as remotely using fleets of UAVs. The entire system, composed of the aircraft, the servers, communication networks, and the processing center, as well as the interfaces for accessing the services via the web, has been designed for this specific purpose. Image processing and automated remote control of the UAV allow generating autonomous missions for the inspection of defects in solar panels, saving costs compared to traditional manual inspection. Another application of this architecture related to security is the detection and tracking of pedestrians and vehicles, both for road safety and for surveillance and security issues of solar plants. The novelty of this system with respect to current systems is summarized in that all the software and hardware elements that allow the inspection of solar panels, surveillance, and people counting, as well as traffic management tasks, have been defined and detailed. The modular system presented allows the exchange of different specific vision modules for each task to be carried out. Finally, unlike other systems, calibrated fixed cameras are used in addition to the cameras embedded in the drones of the fleet, which complement the system with vision algorithms based on deep learning for identification, surveillance, and inspection.

A dataset of Spanish road traffic images taken from unmanned aerial vehicles (UAV) is presented with the purpose of being used to train artificial vision algorithms, among which those based on convolutional neural networks stand out. This article explains the process of creating the complete dataset, which involves the acquisition of the data and images, the labeling of the vehicles, anonymization, data validation by training a simple neural network model, and the description of the structure and contents of the dataset (which amounts to 15,070 images). The images were captured by drones (but would be similar to those that could be obtained by fixed cameras) in the field of intelligent vehicle management. The presented dataset is available and accessible to improve the performance of road traffic vision and management systems since there is a lack of resources in this specific domain.

Rising financial fraud impacts industries, economies, and consumers, creating a need for advanced technological solutions. Compliance frameworks help detect and prevent illicit activities like money laundering, market manipulation, etc. However, with the rise of cryptocurrencies and blockchain, traditional detection methods are ineffective. As a result, Artificial Intelligence (AI) has emerged as a vital tool for combating fraud in the cryptocurrency sector. This systematic review examines the integration of AI in compliance for cryptocurrency fraud detection between 2014 and 2025, analyzing its evolution, methodologies, and emerging trends. Using RStudio (Biblioshiny) and VOSviewer, 353 peer-reviewed studies from leading databases including SciSpace, Elicit, Google Scholar, ScienceDirect, Scopus, and Web of Science were analyzed following the PRISMA methodology. Key trends include the adoption of machine learning, deep learning, natural language processing, and generative AI technologies to improve efficiency and innovation in fraud detection. However, challenges persist, including limited transparency in AI models, regulatory fragmentation, and limited access to quality data, all of which hinder effective fraud detection. The long-term real-world effectiveness of AI tools remains underexplored. This review highlights the trajectory of AI in compliance, identifies areas for further research, and emphasizes bridging theory and practice to strengthen fraud detection in cryptocurrency transactions.

A dataset of aerial urban traffic images and their semantic segmentation is presented to be used to train computer vision algorithms, among which those based on convolutional neural networks stand out. This article explains the process of creating the complete dataset, which includes the acquisition of the images, the labeling of vehicles, pedestrians, and pedestrian crossings as well as a description of the structure and content of the dataset (which amounts to 8694 images including visible images and those corresponding to the semantic segmentation). The images were generated using the CARLA simulator (but were like those that could be obtained with fixed aerial cameras or by using multi-copter drones) in the field of intelligent transportation management. The presented dataset is available and accessible to improve the performance of vision and road traffic management systems, especially for the detection of incorrect or dangerous maneuvers.

The proposed system assists in the automatic creation of three-dimensional (3D) meshes for all types of objects, buildings, or scenarios, using drones with monocular RGB cameras. All these targets are large and located outdoors, which makes the use of drones for their capture possible. There are photogrammetry tools on the market for the creation of 2D and 3D models using drones, but this process is not fully automated, in contrast to the system proposed in this work, and it is performed manually with a previously defined flight plan and after manual processing of the captured images. The proposed system works as follows: after the region to be modeled is indicated, it starts the image capture process. This process takes place automatically, with the device always deciding the optimal route and the framing to be followed to capture all the angles and details. To achieve this, it is trained using the artificial intelligence technique of Double Deep Q-Learning Networks (reinforcement learning) to obtain a complete 3D mesh of the target.