Результаты поиска по 'object detection':
Найдено статей: 16
  1. Bazhenov S.A., Khodyrev R.R., Kabanova T.V., Shipilov S.E., Vrazhnov D.A., Kistenev Y.V.
    Small object detection in aerial images using convolutional neural networks
    Computer Research and Modeling, 2026, v. 18, no. 4, pp. 855-870

    This paper addresses the problem of detecting small objects in visible-spectrum aerial imagery. High background variability and weak feature saliency make small object detection a non-trivial task. Under such conditions, classical computer vision algorithms based on hand-crafted descriptors exhibit low efficiency, prompting a shift towards deep neural network architectures, which demonstrate superior generalization capability and robustness to false positives. We selected a one-stage approach based on a neural network predictive model as the primary object detection method. Also, several neural network architectures belonging to this class were analyzed, outlining their advantages and disadvantages. As the baseline detector, we adopted YOLO version 11 and incorporated a multi-scale feature aggregation module (which combines information from neural network layers operating at different scales) and a dimension-aware selective integration module (which automatically determines the dimension (channel, height, or width) along which to process features and fuses them selectively). These modifications aim to both enhance computational efficiency, enabling deployment of neural network models onboard aerial vehicles for real-time image analysis, and improve small object detection accuracy. Given the complexity of image annotation, we used an open synthetic image database containing approximately 4 000 images for training and testing (with a 90/10 split, respectively). We extend the training set using various random augmentation techniques. To evaluate the performance of the resulting predictive models, we employed mean Average Precision across all classes, using both a fixed 50% intersectionover- union threshold and a varying threshold from 50% to 95%. Overfitting was monitored by analyzing loss curves during training process. The proposed modifications to the YOLO architecture reduced image processing time by a factor of two while maintaining detection accuracy.

  2. Shleymovich M.P., Dagaeva M.V., Katasev A.S., Lyasheva S.A., Medvedev M.V.
    The analysis of images in control systems of unmanned automobiles on the base of energy features model
    Computer Research and Modeling, 2018, v. 10, no. 3, pp. 369-376

    The article shows the relevance of research work in the field of creating control systems for unmanned vehicles based on computer vision technologies. Computer vision tools are used to solve a large number of different tasks, including to determine the location of the car, detect obstacles, determine a suitable parking space. These tasks are resource intensive and have to be performed in real time. Therefore, it is important to develop effective models, methods and tools that ensure the achievement of the required time and accuracy for use in unmanned vehicle control systems. In this case, the choice of the image representation model is important. In this paper, we consider a model based on the wavelet transform, which makes it possible to form features characterizing the energy estimates of the image points and reflecting their significance from the point of view of the contribution to the overall image energy. To form a model of energy characteristics, a procedure is performed based on taking into account the dependencies between the wavelet coefficients of various levels and the application of heuristic adjustment factors for strengthening or weakening the influence of boundary and interior points. On the basis of the proposed model, it is possible to construct descriptions of images their characteristic features for isolating and analyzing, including for isolating contours, regions, and singular points. The effectiveness of the proposed approach to image analysis is due to the fact that the objects in question, such as road signs, road markings or car numbers that need to be detected and identified, are characterized by the relevant features. In addition, the use of wavelet transforms allows to perform the same basic operations to solve a set of tasks in onboard unmanned vehicle systems, including for tasks of primary processing, segmentation, description, recognition and compression of images. The such unified approach application will allow to reduce the time for performing all procedures and to reduce the requirements for computing resources of the on-board system of an unmanned vehicle.

    Views (last year): 31. Citations: 1 (RSCI).
  3. Weber V.I., Ivanod D.D., Kuprits V.Y., Svetlichny Y.A.
    Small object detection in radar images
    Computer Research and Modeling, 2026, v. 18, no. 5, pp. 1249-1268

    This study examines how object annotation format and input image resolution jointly affect the quality of binary detection of small objects in radar images. The study aims to compare YOLO family models, including YOLOv5, YOLOv8, YOLOv11, and YOLOv26, with specialized oriented object detection architectures such as Rotated RetinaNet, R3Det, ROI Transformer, Gliding Vertex, and related models in the task of binary detection of small ground objects in radar imagery. The study also aims to identify data preparation parameters that improve object localization accuracy.

    For the experimental analysis, we formed a new binMSTAR dataset from the open mixMSTAR database. The dataset contains annotations in horizontal bounding box (HBB) and oriented bounding box (OBB) formats for nine input frame resolutions ranging from 640 × 640 to 1408 × 1408 pixels. We assessed the statistical significance of the observed differences using the nonparametric Mann – Whitney U test. The results show that OBB annotation provides a statistically significant advantage in terms of mAP50–95, with an average improvement of 6.5%, because it reduces the influence of redundant background noise. The experiments also reveal an optimal input frame size range of 896–1024 pixels. Further resolution growth decreases localization accuracy, since excessive background content weakens the object-related feature representation. YOLO models demonstrate the best overall balance of detection quality, with YOLOv11(m) reaching a peak mAP50–95 of 0.87 at a resolution of 960 pixels. At the same time, specialized OBB detectors at a resolution of 1024 pixels achieve comparable recall values, reaching up to 0.997. These results support the use of oriented bounding boxes and input resolutions within the 896–1024 pixel range for binary detection tasks in radar imagery.

  4. Syzranova N.G., Andruschenko V.A.
    Numerical modeling of physical processes leading to the destruction of meteoroids in the Earth’s atmosphere
    Computer Research and Modeling, 2022, v. 14, no. 4, pp. 835-851

    Within the framework of the actual problem of comet-asteroid danger, the physical processes causing the destruction and fragmentation of meteor bodies in the Earth’s atmosphere are numerically investigated. Based on the developed physicalmathematical models that determines the movements of space objects of natural origin in the atmosphere and their interaction with it, the fall of three, one of the largest and by some parameters unusual bolides in the history of meteoritics, are considered: Tunguska, Vitim and Chelyabinsk. Their singularity lies in the absence of any material meteorite remains and craters in the area of the alleged crash site for the first two bodies and the non-detection, as it is assumed, of the main mother body for the third body (due to the too small amount of mass of the fallen fragments compared to the estimated mass). The effect of aerodynamic loads and heat flows on these bodies are studied, which leads to intensive surface mass loss and possible mechanical destruction. The velocities of the studied celestial bodies and the change in their masses are determined from the modernized system of equations of the theory of meteoric physics. An important factor that is taken into account here is the variability of the meteorite mass entrainment parameter under the action of heat fluxes (radiation and convective) along the flight path. The process of fragmentation of meteoroids in this paper is considered within the framework of a progressive crushing model based on the statistical theory of strength, taking into account the influence of the scale factor on the ultimate strength of objects. The phenomena and effects arising at various kinematic and physical parameters of each of these bodies are revealed. In particular, the change in the ballistics of their flight in the denser layers of the atmosphere, consisting in the transition from the fall mode to the ascent mode. At the same time, the following scenarios of the event can be realized: 1) the return of the body back to outer space at its residual velocity greater than the second cosmic one; 2) the transition of the body to the orbit of the Earth satellite at a residual velocity greater than the first cosmic one; 3) at lower values of the residual velocity of the body, its return after some time to the fall mode and falling out at a considerable distance from the intended crash site. It is the implementation of one of these three scenarios of the event that explains, for example, the absence of material traces, including craters, in the case of the Tunguska bolide in the vicinity of the forest collapse. Assumptions about the possibility of such scenarios have been made earlier by other authors, and in this paper their implementation is confirmed by the results of numerical calculations.

  5. Elaraby A.E., Nechaevskiy A.V.
    An effective segmentation approach for liver computed tomography scans using fuzzy exponential entropy
    Computer Research and Modeling, 2021, v. 13, no. 1, pp. 195-202

    Accurate segmentation of liver plays important in contouring during diagnosis and the planning of treatment. Imaging technology analysis and processing are wide usage in medical diagnostics, and therapeutic applications. Liver segmentation referring to the process of automatic or semi-automatic detection of liver image boundaries. A major difficulty in segmentation of liver image is the high variability as; the human anatomy itself shows major variation modes. In this paper, a proposed approach for computed tomography (CT) liver segmentation is presented by combining exponential entropy and fuzzy c-partition. Entropy concept has been utilized in various applications in imaging computing domain. Threshold techniques based on entropy have attracted a considerable attention over the last years in image analysis and processing literatures and it is among the most powerful techniques in image segmentation. In the proposed approach, the computed tomography (CT) of liver is transformed into fuzzy domain and fuzzy entropies are defined for liver image object and background. In threshold selection procedure, the proposed approach considers not only the information of liver image background and object, but also interactions between them as the selection of threshold is done by find a proper parameter combination of membership function such that the total fuzzy exponential entropy is maximized. Differential Evolution (DE) algorithm is utilizing to optimize the exponential entropy measure to obtain image thresholds. Experimental results in different CT livers scan are done and the results demonstrate the efficient of the proposed approach. Based on the visual clarity of segmented images with varied threshold values using the proposed approach, it was observed that liver segmented image visual quality is better with the results higher level of threshold.

  6. Moiseev N.A., Nazarova D.I., Semina N.S., Maksimov D.A.
    Changepoint detection on financial data using deep learning approach
    Computer Research and Modeling, 2024, v. 16, no. 2, pp. 555-575

    The purpose of this study is to develop a methodology for change points detection in time series, including financial data. The theoretical basis of the study is based on the pieces of research devoted to the analysis of structural changes in financial markets, description of the proposed algorithms for detecting change points and peculiarities of building classical and deep machine learning models for solving this type of problems. The development of such tools is of interest to investors and other stakeholders, providing them with additional approaches to the effective analysis of financial markets and interpretation of available data.

    To address the research objective, a neural network was trained. In the course of the study several ways of training sample formation were considered, differing in the nature of statistical parameters. In order to improve the quality of training and obtain more accurate results, a methodology for feature generation was developed for the formation of features that serve as input data for the neural network. These features, in turn, were derived from an analysis of mathematical expectations and standard deviations of time series data over specific intervals. The potential for combining these features to achieve more stable results is also under investigation.

    The results of model experiments were analyzed to compare the effectiveness of the proposed model with other existing changepoint detection algorithms that have gained widespread usage in practical applications. A specially generated dataset, developed using proprietary methods, was utilized as both training and testing data. Furthermore, the model, trained on various features, was tested on daily data from the S&P 500 index to assess its effectiveness in a real financial context.

    As the principles of the model’s operation are described, possibilities for its further improvement are considered, including the modernization of the proposed model’s structure, optimization of training data generation, and feature formation. Additionally, the authors are tasked with advancing existing concepts for real-time changepoint detection.

Pages: previous

Indexed in Scopus

Full-text version of the journal is also available on the web site of the scientific electronic library eLIBRARY.RU

The journal is included in the Russian Science Citation Index

The journal is included in the RSCI

International Interdisciplinary Conference "Mathematics. Computing. Education"