Dymitr PIETROW

Mr. Dymitr PIETROW

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 October 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Maciej KaczyńskiMaciej Kaczyński
Maciej Kaczyński
Zbigniew PiotrowskiZbigniew Piotrowski
Zbigniew Piotrowski
DPDymitr PIETROW
Dymitr PIETROW
This article presents a method for transparent watermarking of high-capacity watermarked video under H.265/HEVC (High-Efficiency Video Coding) compression conditions while maintaining high-quality encoded image. The aim of this paper is to present a method for watermark embedding using neural networks under conditions of subjecting video to lossy compression of the HEVC codec using the YUV420p color model chrominance channel for watermarking. This paper presents a method for training a deep neural network to embed a watermark when a compression channel is present. The discussed method is characterized by high accuracy of the video with an embedded watermark compared to the original. The PSNR (peak signal-to-noise ratio) values obtained are over 44 dB. The watermark capacity is 96 bits for an image with a resolution of 128 × 128. The method enables the complete recovery of a watermark from a single video frame compressed by the HEVC codec within the range of compression values defined by the CRF (constant rate factor) up to 22.

9 December 2021 in Sensors
Verified
Journal Article
Open access
PDF file
JMJan Matuszewski
Jan Matuszewski
DPDymitr PIETROW
Dymitr PIETROW
With the increasing complexity of the electromagnetic environment and continuous development of radar technology we can expect a large number of modern radars using agile waveforms to appear on the battlefield in the near future. Effectively identifying these radar signals in electronic warfare systems only by relying on traditional recognition models poses a serious challenge. In response to the above problem, this paper proposes a recognition method of emitted radar signals with agile waveforms based on the convolutional neural network (CNN). These signals are measured in the electronic recognition receivers and processed into digital data, after which they undergo recognition. The implementation of this system is presented in a simulation environment with the help of a signal generator that has the ability to make changes in signal signatures earlier recognized and written in the emitter database. This article contains a description of the software’s components, learning subsystem and signal generator. The problem of teaching neural networks with the use of the graphics processing units and the way of choosing the learning coefficients are also outlined. The correctness of the CNN operation was tested using a simulation environment that verified the operation’s effectiveness in a noisy environment and in conditions where many radar signals that interfere with each other are present. The effectiveness results of the applied solutions and the possibilities of developing the method of learning and processing algorithms are presented by means of tables and appropriate figures. The experimental results demonstrate that the proposed method can effectively solve the problem of recognizing raw radar signals with agile time waveforms, and achieve correct probability of recognition at the level of 92–99%.

6 November 2025 in IEEE Access
Verified
Journal Article
Open access
Maciej KaczyńskiMaciej Kaczyński
Maciej Kaczyński
Zbigniew PiotrowskiZbigniew Piotrowski
Zbigniew Piotrowski
DPDymitr PIETROW
Dymitr PIETROW
Signal source localization and emitter tracking constitute fundamental functions in communication systems, autonomous navigation, surveillance, and electronic warfare. Conventional approaches based on geometric modeling, including time difference of arrival (TDoA), angle of arrival (AoA), and received signal strength (RSS), often degrade in complex environments characterized by multipath propagation, non-line of sight (NLoS) conditions, and dynamic interference. Recent advances in machine learning (ML) have motivated the development of data-driven frameworks capable of learning nonlinear mappings directly from signal measurements, thereby enhancing adaptability, robustness, and real-time applicability. This review provides a structured survey of ML techniques for source localization and tracking in both radio frequency (RF) and acoustic domains. Structured lists and comparative analyses of simulators, methods, surveys, and datasets for acoustic and RF localization, are presented, alongside a unifying taxonomy. Feature engineering methods, ranging from time-frequency transforms to spatio-temporal encoding and multimodal fusion, are examined in terms of their role in generalization and efficiency. Comparative analyses highlight the relative strengths of shallow models, probabilistic frameworks, and deep neural architectures, as well as the integration of synthetic data and transfer learning. The review concludes with perspectives on next-generation localization systems.

13 January 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Zbigniew PiotrowskiZbigniew Piotrowski
Zbigniew Piotrowski
MBMarta Bistroń
Marta Bistroń
GJGabriel Jekateryńczuk
Gabriel Jekateryńczuk
PKPaweł Kaczmarek
Paweł Kaczmarek
DPDymitr PIETROW
Dymitr PIETROW
This paper presents the design of a system to support the identification of victims of disasters and terrorist attacks. The system, called ID Victim (IDV), is a web application using a mobile app and data server. The DVI (Disaster Victim Identification) procedure, an international standard developed by Interpol, is used. The purpose of the IDV system is to facilitate and expedite the process of determining victims’ identities. A neural identification module was developed and trained on approximately 13,000 images from the LFW dataset and fine-tuned using 400 simulated PostMortem (PM) and AnteMortem (AM) images. Postmortem data include photographs of victims while antemortem data consist of pre-disaster photos of potential victims. The module generates a hypothesis, linking PM to AM, which is then verified. The module achieved test identification accuracy of up to 60% for 25 sample PM and AM sets. The system partially automates photo comparisons by DVI teams, improving efficiency, reducing identification time, and limiting the exposure of operators to graphic images. Implementing the system as a mobile application accelerates the process by enabling direct data entry during victim examinations on-site.

1 February 2020
Verified
Conference Paper
Closed access
MJMatuszewski Jan
Matuszewski Jan
DPDymitr PIETROW
Dymitr PIETROW
The article describes the practical application of artificial neural network in the processing of post-processing radar information, such as echoes filtration from the solid objects, automatic establishment of recognition zones, work with disturbances, tracking of aircraft and testing their flight characteristics, and even an attempt to identify the type of aircraft based on the obtained characteristic of the effective reflection surface of the object. The measurement results have been presented in the form of appropriate tables, charts, screenshots conclusions and implementation possibilities in the current generation of radiolocation devices.

19 November 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
Maciej KaczyńskiMaciej Kaczyński
Maciej Kaczyński
Zbigniew PiotrowskiZbigniew Piotrowski
Zbigniew Piotrowski
DPDymitr PIETROW
Dymitr PIETROW
This paper presents a method for preserving the quality of video compressed with video codecs. The video codecs used in this article are H.264/AVC (Advanced Video Coding) and its successor H.265/HEVC (High Efficiency Video Coding). The aim of the article is to present a method for enhancing the video quality for high compression values by preprocessing video frames using Deep Neural Network (DNN). The proposed method reduces the degree of image quality degradation caused by lossy video compression by improving the detail quality of the output video frames after decompression. The proposed method improves video quality for high QP (Quantization Parameter) values beginning from 25 and above. Compared to the popular trend of improving the video quality of already degraded video, the presented method attempts to improve the quality by modifying the image before the compression process by the video codec. The image is modified by DNN to obtain the lowest possible loss of video quality, represented by quality coefficients, but above all by the visual reception of the video by the viewer, enabling increased perception of more details in conditions of high video compression.