In this work, the developed system for detecting areas with defects in the development of corn crops was investigated from a photograph taken by an unmanned aerial vehicle (UAV) using computer vision. To solve the problem of detecting such sites, the structures of the YOLOv5 and YOLOv8 neural networks were considered. The use of the developed software will reduce labor and time costs for image analysis, which in turn will reduce the response time when problem areas are detected in agricultural fields to achieve higher yields.

Keywords: instance segmentation, YOLOv5, YOLOv8

This article describes the results of research on the possibility of detecting sunflower plants from photographs taken by a UAV. The solution to this problem will allow automated control of an important agricultural parameter - seedling density. The problem is complicated by the limited amount of training sample and "disturbances" associated with field weeding. As the result we obtain that the YOLOv5m neural network is capable on a sample of 122 pictures to qualitatively detect plants with an error of 0.077% of training. Artificially increasing the sample to 363 pictures reduces the learning error to 0.063%. Disturbances reduce the detection efficiency of sunflower plants in the test images. It is possible to increase the detection efficiency either by adding original images to the training sample or by artificially enlarging the sample.

Keywords: detection, YOLOv5, sunflower, seedling density, neural network

The construction industry at all times was one of the most popular, as it is closely connected with the life of people. The stronger the population of our planet grows, the more it becomes necessary to erect an ever larger number of be it industrial or residential buildings and structures. This article discusses the problems of technical expertise in determining the volume and cost of actually high-quality work performed. The main problem is that most of the works carried out during construction (repair) are hidden and it is not possible to verify them, therefore, the expert in this examination is forced to be guided by the acts of examination of hidden works and the journal of the work. One of the main causes of disputes between the customer and the contractor is the overestimated volume of work performed, as well as poorly executed work.

Keywords: Problem, expertise, covert operation, hidden work, construction, repairs, cause, dishonesty, conclusion, expert, quality

The paper is focused on research of an access control system based on the analysis of the thermal radiation of the user's palms using common components, it is shown that the use of multifactor biometric authentication based on the thermal image of the palms and infrared images of the user's veins allows to reduce the errors of the first and second kind during biometric authentication.

Keywords: biometric authentication, thermal palm print, access control system, infrared vein imaging

Detection and identification of features on television images is one of the important problems in technical vision systems. The effectiveness of the vision systems directly depends on the performance of the feature detection stage. An important step in image processing is the steady detection and identification of features of the image (landmarks) as the observation conditions change.

Keywords: image processing, technical vision, robust detector, detection efficiency

In this paper, the effectiveness of implementing DSP algorithms necessary to realize the fact of glass breaking in a controlled room is considered. In the course of the research, existing schemes for constructing glassbreak detectors used in existing fire and security alarm systems are analyzed. The possibility of constructing digital filtering algorithms on microcontrollers STM32F4XX of medium degree of integration is investigated. Studies have shown the fundamental possibility of implementing DSP algorithms necessary to detect the fact of glass breaking on STM32F4XX microcontrollers in real time.

Keywords: digital signal processing, burglar alarm system, glass break detector, digital filter, finite impulse response, microcontroller performance.

The simulation of two-dimensional spherical crystals consisting of a large number of particles is carried out. These shells were analyzed based on their geometric structure and energy distribution. Various types of defects formed in a state of equilibrium  is considered. Being shown the ambiguity of the existing method of their interpretation. A new way of describing such defects in the close-packed two-dimensional crystals with different topology is suggested.  

Keywords: topological defects, two-dimensional materials, spherical crystals, topological charge

  In this work researches of structural and electrophysical properties of ferroelectric films of lead zirconate titanate (PZT) which afterwards is planned to apply in hybrid sensor systems are done. Values of capacities of the received samples are in the range from 200 to 1100 pF, the range of thickness of the received films is 300-1000 nanometers. X-ray analysis showed direct dependence of the quantitative maintenance of crystalline PZT in film structure from partial pressure of oxygen in the camera. By results of research the range of polarization of samples are in the range 0,06 – 2,2 µC/cm2, and values of calculated piezoelectric modules are in the range 0,04*10-12 – 13,3*10-12 C/N.

Keywords: sensors, segnetoelektric films, touch systems, piezoelectric modules.

`

Keywords: