Vladimir Alexandrovich Knyaz

Teeth are one of the most frequently studied objects in anthropology and some other scientific disciplines. Our recent works on development of automated measurement techniques for incisors evoked interest to studies of non-metric morphological traits. Such assessments are traditionally made by means of visual analysis in dental anthropological research, including the trait chosen for testing automated algorithms in the current research – incisor labial convexity. 3D models of incisors of Sunghirian adolescents (Sunghir 2 and Sunghir 3) were generated after micro-focus tomographic scanning; teeth with complete morphology included in the study. On the basis of the proposed technique the developed software performs orientation of models, their sectioning, surface and contour analysis, measurements. As a result, two indicators were proposed for digital assessment of incisor labial convexity. Their combined usage showed interesting results for studying the non-metric trait on seven teeth, as well as for morphological studies beyond classical approaches, e.g. when used on lower incisors.

This paper presents a UAV course correction algorithm leveraging a neural network and the analysis of a video stream from the onboard camera. The algorithm is designed to identify key landmarks efficiently and requires only a limited set of training images. Significantly, it demonstrates operational capabilities at viewing angles and altitudes that differ from those used during training. Experimental results indicate that the algorithm achieves satisfactory landmark recognition accuracy even with substantial perspective deviations, thus enhancing the robustness and effectiveness of UAV operations.

This paper presents a novel reinforcement learning (RL) framework for automated vectorization of high-resolution aerial imagery, addressing key challenges in geospatial analysis through adaptive feature extraction and sequential decision-making. Our hybrid architecture combines a modified ResNet-50 backbone with atrous spatial pyramid pooling (ASPP) for multi-scale feature extraction and bidirectional GRUs for spatial context modeling, integrated with a dueling double DQN agent that optimizes vectorization through reward-driven policy learning. The proposed method demonstrates significant improvements over conventional approaches, achieving about 10% increase in mean Intersection-over-Union (mIoU) on the CrowdAI Mapping Challenge dataset while reducing processing time by 29% through optimized RL-based decision sequences. A multi-component reward system balances geometric accuracy (boundary F1-score: 0.79), topological correctness (94.1% Cycle Consistency and 93.4% Junction Accuracy), and computational efficiency, enabling robust performance across diverse urban and rural landscapes. This work establishes a new paradigm for adaptive geospatial vectorization that combines deep learning’s representational power with RL’s sequential optimization capabilities.

The article discusses some issues of modeling and digitalization of real-time systems using Petri nets (Petrosyan et al., 2025). The identification and secret key generation system is modeled using the Colored Petri net, which is a modern extension of the classical Petri net. The main goal of modeling the identification and secret key generation system using the Colored Petri net is to identify the presence of errors and randomness, the behaviour of the functioning, in the efficiency of the model. The Colored Petri net (CPN) graph of the identification and secret key generation system describes the workflow, logical actions much more simply, since Petri nets are convenient mechanisms for modeling, checking, validating complex systems. The article discusses some issues of modeling and digitalization of real-time systems using Petri nets. The identification and secret key generation system is modeled using the Colored Petri net, which is a modern extension of the classical Petri net (Petrosyan et al., 2025). The main goal of modeling the identification and secret key generation system using the Colored Petri net is to identify the presence of errors and randomness, the behavior of the functioning, in the efficiency of the model. The Colored Petri net (CPN) graph of the identification and secret key generation system describes the workflow, logical actions much more simply, since Petri nets are convenient mechanisms for modeling, checking, validating complex systems (Petrosyan et al., 2025).

Currently, remote sensing research is focused on developing an automated algorithm that can compete with empirical methods for mapping the contours of individual buildings. Despite facing numerous challenges related to suboptimal imaging conditions, diverse building architecture, and complex backgrounds, creating such an algorithm is essential for monitoring urban and natural areas, generating 3D city models, managing disasters, and estimating population density. Obtaining the polygonal boundary of a building and extracting a vectorized building mask as output for direct use is one of the current challenges in drawing building outlines. This work provides a comprehensive workflow for building extraction and improves their predicted area by regularization the boundaries of buildings. First, a convolutional neural network is used to train the binary semantic segmentation model and then regularization and vectorization processes are performed. The main difference from existing methods is a new regularization method based on compiling a neighborhood matrix for each point belonging to the “building” class. According to the experimental results, the algorithm shows high efficiency: IOU (intersection over union) = 91.2%, AP (average precision) = 64.1% and AR (average recall) = 75.1%, comparable to leading building boundary extraction methods such as PolyWorld.

Orthodox churches and their paintings are an important part of the historical heritage. Along with well-preserved and maintained churches, there are a large number of dilapidated buildings included in the list of cultural heritage sites, which are in a deplorable state due to lack of funds for restoration. The expanding possibilities of collecting diverse information on cultural heritage make it possible to accumulate and systematize information about sites in order to be able to document their reconstruction and restoration in the future. This study addresses the problem of analyzing changes in the wall paintings of Orthodox churches based on remote-sensing data using multi-temporal interior images, including amateur photography.

One of the urgent and constantly in demand problems is updating maps. Maps, representing geo-information in vector form, have undoubted advantages in compactness and ”readability” compared to aerial photographs. The issue of maps actuality is critically important for rational urban planning, precision farming, the relevance of the cadastre and other geospatial applications. Various sources of data are used for maps updating, with aerial imagery being the main and rich source of information. Automatic processing of aerial photographs makes it possible to efficiently extract vector information, providing operational monitoring and accounting for changes that have appeared. The presented study addresses the problem of multi sensor information fusion in order to obtain accurate vector information. We use aerial images as a main data source and additionally the data of laser scanning and ground survey to increase performance of automatic image semantic segmentation and vectorization. The proposed framework is demonstrated on the task of forest monitoring.

Among different study techniques, which are used in dental research, measurements of teeth play one of the most important roles. However classical measurement techniques usually show consistent results on morphologically complete objects, while teeth can be found in different conditions, depending, for instance, on the natural wear degree. In order to increase the sample, which is especially important when findings are not abundant, and to improve the analytical part, alternative techniques have been proposed, among which cervical measurements are considered to be informative, especially taking into consideration morphological and methodological importance of the cervical area. Algorithms of automated digital measurement techniques also use the cervical area for providing stability of results. Visualisation of the tooth cervical margin and reconstruction of its projections can be achieved by two conventional imaging techniques, which are tomography (preferably high-resolution) and intra-oral confocal optical scanning. They both were used for obtaining 3D reconstruction of upper premolar taken from palaeoanthropological materials. In line with applying the same automated coordinate system setting algorithm to both types of reconstructions, contours of their enamel cervical margins were defined and their projections to horizontal plane were obtained and measured. Despite the fact that 3D reconstructions from different imaging sources technically can serve for running automated odontometry, measurement results, especially in comparative studies, should be handled with attention.

For years, researchers have been developing an automated method that can replace humans by drawing the outlines of individual buildings in a vector format, which plays an important role in GIS creation, environmental monitoring, urban planning, population density estimation, and energy supply. There is no doubt that this is an extremely difficult task, not only because of the labor required to develop such a highly intelligent algorithm, but also because of the challenges posed by imperfect imaging conditions, different building structures, and the complexity of the background. One of the current challenges in extracting building outlines is to accurately recreate the polygonal boundaries of the building while extracting vectorized building masks as output for direct use in various applications. This work provides a comprehensive workflow for building extraction and improves the predicted area of buildings through boundary regularization. First, a convolutional neural network is used to train instance segmentation model, then regularization and vectorization processes are performed. The main difference from existing methods is a new regularization method based on the concepts of linear connectivity and convexity of a set of points. This approach can effectively identify and remove points that do not belong to the detected building but were incorrectly segmented by the algorithm. Based on the results of experiments, the algorithm showed a high level of efficiency, comparable to leading methods for extracting building boundaries as PolyWorld.