All issues

When recognizing workers on images of a construction site obtained from surveillance cameras, a situation is typical in which the objects of detection have a very different spatial scale relative to each other and other objects. An increase in the accuracy of detection of small objects can be achieved by using the Feature-Fused modification of the SSD detector. Together with the use of overlapping image slicing on the inference, this model copes well with the detection of small objects. However, the practical use of this approach requires manual adjustment of the slicing parameters. This reduces the accuracy of object detection on scenes that differ from the scenes used in training, as well as large objects. In this paper, we propose an algorithm for automatic selection of image slicing parameters depending on the ratio of the characteristic geometric dimensions of objects in the image. We have developed a two-pass version of the Feature-Fused SSD detector for automatic determination of optimal image slicing parameters. On the first pass, a fast truncated version of the detector is used, which makes it possible to determine the characteristic sizes of objects of interest. On the second pass, the final detection of objects with slicing parameters selected after the first pass is performed. A dataset was collected with images of workers on a construction site. The dataset includes large, small and diverse images of workers. To compare the detection results for a one-pass algorithm without splitting the input image, a one-pass algorithm with uniform splitting, and a two-pass algorithm with the selection of the optimal splitting, we considered tests for the detection of separately large objects, very small objects, with a high density of objects both in the foreground and in the background, only in the background. In the range of cases we have considered, our approach is superior to the approaches taken in comparison, allows us to deal well with the problem of double detections and demonstrates a quality of 0.82–0.91 according to the mAP (mean Average Precision) metric.

This paper considers the inverse problem of seismic exploration — determining the structure of the media based on the recorded wave response from it. Large cracks are considered as target objects, whose size and position are to be determined.

he direct problem is solved using the grid-characteristic method. The method allows using physically based algorithms for calculating outer boundaries of the region and contact boundaries inside the region. The crack is assumed to be thin, a special condition on the crack borders is used to describe the crack.

The inverse problem is solved using convolutional neural networks. The input data of the neural network are seismograms interpreted as images. The output data are masks describing the medium on a structured grid. Each element of such a grid belongs to one of two classes — either an element of a continuous geological massif, or an element through which a crack passes. This approach allows us to consider a medium with an unknown number of cracks.

The neural network is trained using only samples with one crack. The final testing of the trained network is performed using additional samples with several cracks. These samples are not involved in the training process. The purpose of testing under such conditions is to verify that the trained network has sufficient generality, recognizes signs of a crack in the signal, and does not suffer from overtraining on samples with a single crack in the media.

The paper shows that a convolutional network trained on samples with a single crack can be used to process data with multiple cracks. The networks detects fairly small cracks at great depths if they are sufficiently spatially separated from each other. In this case their wave responses are clearly distinguishable on the seismogram and can be interpreted by the neural network. If the cracks are close to each other, artifacts and interpretation errors may occur. This is due to the fact that on the seismogram the wave responses of close cracks merge. This cause the network to interpret several cracks located nearby as one. It should be noted that a similar error would most likely be made by a human during manual interpretation of the data. The paper provides examples of some such artifacts, distortions and recognition errors.

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.

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.