EUVIMEDEUVIMED entdecken
Crossref

SOFTWARE TOOL FOR IMPROVING THE INFORMATIONAL CONTENT OF VISUAL PARAMETERS OF IMAGES OF IR-RADIATION

V. S. Matnenko, I. O. Prots'ko

Ukrainian Journal of Information Technology · 2026 · 8 (1) · 115-126

DOI: 10.23939/ujit2026.01.115 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ukrainian Journal of Information Technology, 2026. Verfasst von V. S. Matnenko und 1 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Night vision devices (NVD) and thermal imaging cameras are widely used in the fields of surveillance, security and monitoring, search and rescue, emergency response, industrial control and maintenance, ground operations and unmanned aerial vehicles. Night vision devices operate on the principle of amplifying residual light (starlight, moonlight, city lighting) in the visible and near-infrared ranges (0.4–0.9 μm). Thermal imaging devices record thermal radiation of objects in the medium (3–5 μm) or far (8–14 μm) infrared range. The problem with these hardware tools is the low contrast of scenes, low resolution, which leads to pixelation and blurred contours. To improve the informativeness of visual parameters of images in the infrared and visible spectra of low intensity, purposeful software tools are used. A software tool has been developed that allows you to automate the process of improving the quality of images from NVD and thermal imagers by classifying the sensor type and using adaptive filters. The software tool is based on common methods of digital image processing, the selection of which is carried out on the basis of neural network classification. The objects of the processing software tool are digital images obtained from various optoelectronic devices. The structure with a description of the functions of the blocks of the developed software complex is considered. The neural network classifier, based on the trained model, determines the type of source (thermal imager, NVD, day optics) and the level of noise. The obtained performance metrics are: Overall Accuracy: 97%, Precision avg: 97%, Recall: 95.1%. Automatic processing after image classification by the MobileNetV2 neural network occurs sequentially. First, local contrast is improved, which allows you to "pull out" details from the shadows. Next, noise reduction is applied to remove graininess. After that, sharpness is increased to restore edges. One of the important capabilities of the software tool is pseudocolorization of thermal imaging data. The software complex uses a flexible user interface that provides input of control commands, selection of operating modes (automatic/manual) and adjustment of filtering coefficients. Using the software complex provides the ability to quickly select feature extractors in the image, which will help to avoid obstacles in understanding the situation based on the received video data image.

Zitieren

APA

Matnenko, V. S., & Prots'ko, I. O. (2026). SOFTWARE TOOL FOR IMPROVING THE INFORMATIONAL CONTENT OF VISUAL PARAMETERS OF IMAGES OF IR-RADIATION. Ukrainian Journal of Information Technology, 8(1), 115-126. https://doi.org/10.23939/ujit2026.01.115

Vancouver

Matnenko VS, Prots'ko IO. SOFTWARE TOOL FOR IMPROVING THE INFORMATIONAL CONTENT OF VISUAL PARAMETERS OF IMAGES OF IR-RADIATION. Ukrainian Journal of Information Technology. 2026;8(1):115-126. doi:10.23939/ujit2026.01.115

BibTeX
@article{Matnenko2026,
  author = {Matnenko, V. S. and Prots'ko, I. O.},
  title = {SOFTWARE TOOL FOR IMPROVING THE INFORMATIONAL CONTENT OF VISUAL PARAMETERS OF IMAGES OF IR-RADIATION},
  journal = {Ukrainian Journal of Information Technology},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {115--126},
  doi = {10.23939/ujit2026.01.115}
}
Kostenlos starten →