The paper is focused on the development of the experimental web-based solution for image processing from the perspective of an Unmanned Aerial Vehicle (UAV). Specifically, the research is carried out as part of the broader study on drone utilization in traffic at the Technical University of Kosice. This contribution explores the possibility of using the UAV as a tool to detect the temporal state of the traffic in multiple locations. Road traffic analysis is enabled through the detection of vehicles from the user-defined region of interest (ROI). Its content then serves as the input for motion detection, followed by the detection of vehicles using the YOLOv4 model. Detection of other types of objects is possible, thus making the system more universal. The vehicle is tracked after recognition in two consecutive frames. The tracking algorithm is based on the calculation of the Euclidean distance and the intersection of the rectangles. The experimental verification yields lower hardware requirements for CPU and GPU by about two FPS when using optimization techniques, such as ROI or reference dimensions of objects. The accuracy of detection and the subsequent tracking of cars reaches almost 100% while providing accurate trajectory determination.

This research describes an experimental solution used for estimating the positions of pedestrians from video recordings. Additionally, clustering algorithms were utilized to interpret the data. The system employs the You Only Look Once (YOLO) algorithm for object detection. The detection algorithm is applied to video recordings provided by an unmanned aerial vehicle (UAV). An experimental method for calculating the pedestrian’s geolocation is proposed. The output of the calculation, i.e., the data file, can be visualized on a map and analyzed using cluster analyses, including K-means, DBSCAN, and OPTICS algorithms. The experimental software solution can be deployed on a UAV or other computing devices. Further testing was performed to evaluate the suitability of the selected algorithms and to identify optimal use cases. This solution can successfully detect groups of pedestrians from video recordings and it provides tools for subsequent cluster analyses.

The broad goal of this study is the estimation of dimensions of real-world multidimensional objects. The focus is on the human being and its dimensional parameters, primarily the height. The approach to the estimation of the height in a single camera environment is presented and is experimentally verified. The proposed method presumes that the distance from the optical device to the human body and its Vertical Field of View (VFOV) are known. The VFOV has to be calculated or acquired only once for a specific device. The accuracy of the proposed method is validated by a series of test scenarios including, e.g., statistical height measurements.