Recreating a road traffic accident scheme is a task of current importance. There are several main problems when drawing up a plan of accident: a long-term collection of all information about an accident, inaccuracies, and errors during manual data fixation. All these disadvantages affect further decision-making during a detailed analysis of an accident. The purpose of this work is to automate the entire process of operational reconstruction of an accident site to ensure high accuracy of measuring the distances of the relative location of objects on the sites. First the operator marks the area of a road accident and the UAV scans and collects data on this area. We constructed a three-dimensional scene of an accident. Then, on the three-dimensional scene, objects of interest are segmented using a deep learning model SWideRNet with Axial Attention. Based on the marked-up data and image Transformation method, a two-dimensional road accident scheme is constructed. The scheme contains the relative location of segmented objects between which the distance is calculated. We used the Intersection over Union (IoU) metric to assess the accuracy of the segmentation of the reconstructed objects. We used the Mean Absolute Error to evaluate the accuracy of automatic distance measurement. The obtained distance error values are small (0.142 ± 0.023 m), with relatively high results for the reconstructed objects’ segmentation (IoU = 0.771 in average). Therefore, it makes it possible to judge the effectiveness of the proposed approach.

The paper considers the problem of constructing safe routes for a group of unmanned aerial vehicles in a limited airspace over an agricultural area. The relevance of the study is due to the growing use of UAV groups in the agro-industrial complex for monitoring, mapping, and processing fields, which requires ensuring flight safety in conditions of high air traffic density, limited communication, and exposure to external factors. A particular challenge is the need for autonomous missions in the presence of navigation errors and natural impacts. A route planning method is proposed based on representing the trajectory of each device as a capsule air corridor – a three-dimensional volume of a fixed radius formed along the trajectory segments. Spatial redundancy ensures safe spacing of trajectories at the planning stage, eliminating conflicts during subsequent autonomous flight operations without the need for continuous coordination between agents. The capsule radius includes a reserve for possible deviations from the planned trajectory, which ensures resistance to navigation errors. The method is based on the sequential formation of routes for each device according to a four-phase scheme, including a vertical ascent from the starting point to the operating altitude, a horizontal transition to the entrance to the processing zone, a return from the exit from the zone to the starting point of the descent, and a vertical descent to the initial position. Each new route is built considering the already reserved air corridors through an analytical check of geometric intersections between the capsules of different trajectories and convex polyhedrons of the processing zones. To improve computational efficiency, hierarchical spatial filtering is used based on bounding parallelepipeds, which allows for the rapid cutting off of obviously non-intersecting objects at the preliminary stage and performing an accurate geometric check only for potentially conflicting route segments. Numerical experiments were carried out for groups of 2 to 32 devices on a typical agricultural plot of one square kilometer. A nonlinear increase in the planning time and the number of iterations with an increase in the number of agents was found, which is due to the need to build each subsequent route in an already partially occupied space with an increasing number of spatial constraints. The length of routes shows a tendency to increase, especially pronounced at the initial stages of scaling, which is associated with the need to bypass already reserved air corridors.