Paweł Kowaleczko

Mr. Paweł Kowaleczko


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
7 October 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
MKMichal Kawulok
Michal Kawulok
PKPaweł Kowaleczko
Paweł Kowaleczko
MZMaciej Ziaja
Maciej Ziaja
Jakub NalepaJakub Nalepa
Jakub Nalepa
Daniel KostrzewaDaniel Kostrzewa
Daniel Kostrzewa
Fabio Del FrateFabio Del Frate
Fabio Del Frate
The need for enhancing image spatial resolution has motivated the researchers to propose numerous super-resolution techniques, including those developed specifically for hyperspectral data. Despite significant advancements in this field attributed to deep learning, little attention has been given to evaluating the practical value of super-resolved images in specific applications. Most methods are validated in application-independent scenarios, often using simulated low-resolution images, resulting in overly optimistic conclusions. In this paper, we propose task-based evaluation strategies for hyperspectral image super-resolution and we present results obtained with various approaches that include pansharpening, multispectral–hyperspectral data fusion, and single-image super-resolution. We demonstrate that the proposed framework allows us to highlight both benefits and limitations of each method and can therefore guide the development of super-resolution techniques suitable for real-world applications.

8 February 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
PKPaweł Kowaleczko
Paweł Kowaleczko
TKTomasz Kamiński
Tomasz Kamiński
MRMariusz Rychlicki
Mariusz Rychlicki
ZKZbigniew Kasprzyk
Zbigniew Kasprzyk
MSMarek Stawowy
Marek Stawowy
JTJacek Trzeszkowski
Jacek Trzeszkowski
The paper presents the general characteristics of weighing systems for vehicles in motion. A number of problems and constraints that accompany these systems to ensure adequate accuracy in the operation of these systems are pointed out. The efficient operation of WIM systems is also related to the proper preselection of vehicles for weighing in motion. The next part of the paper presents the basic classification and characteristics of machine learning algorithms, as well as examples of applications and implementations of these algorithms in various industries. The paper presents a model based on the XGBoost algorithm for estimating the weight of vehicles in motion, taking into account key characteristics of vehicles. The model was tested on large datasets from two locations in Poland, achieving high accuracy rates. The results indicate the model’s potential in optimizing preselection systems, allowing for the effective identification of overloaded vehicles. Future work will focus on testing the model at other locations to verify its scalability and operational efficiency.

20 June 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
MZMaciej Ziaja
Maciej Ziaja
PKPaweł Kowaleczko
Paweł Kowaleczko
TTTomasz Tarasiewicz
Tomasz Tarasiewicz
Daniel KostrzewaDaniel Kostrzewa
Daniel Kostrzewa
MKMichal Kawulok
Michal Kawulok
Hyperspectral imagery provides rich spectral information, but commonly suffers from low spatial resolution. This problem can be addressed with hyperspectral pansharpening which benefits from a high-resolution panchromatic image to enhance the resolution of spectral bands. Another possibility of improving spatial resolution, commonly exploited for remotely-sensed images, benefits from multitemporal fusion of images acquired at different revisits of a satellite. However, such a process, termed multi-image super-resolution, has not been applied to hyperspectral imagery due to the excessive size of hyperspectral cubes. In this paper, we propose a new processing pipeline that combines these two approaches. A multitemporal series of panchromatic images is super-resolved to reconstruct a high-resolution panchromatic image which is subsequently used during pansharpening. We demonstrate the benefits of the proposed pipeline for PRISMA imagery, whose hyperspectral cubes (30 m ground sampling distance) are associated with panchromatic images (5 m ground sampling distance). The latter are upsampled by a factor of 3× relying on multi-image super-resolution, which allows our pansharpening to achieve the upsampling ratio of 18${\times }$ for PRISMA images. We report and discuss the results of our extensive experiments which indicate that the proposed approach offers substantial quantitative and qualitative improvement, confirmed by a mean opinion score survey.

15 October 2025 in Annals of Computer Science and Information Systems
Verified
Conference Paper
Closed access
JSJakub Sadel
Jakub Sadel
TTTomasz Tarasiewicz
Tomasz Tarasiewicz
PKPaweł Kowaleczko
Paweł Kowaleczko
MZMaciej Ziaja
Maciej Ziaja
Daniel KostrzewaDaniel Kostrzewa
Daniel Kostrzewa
MKMichal Kawulok
Michal Kawulok

30 December 2018 in Problems of Mechatronics Armament Aviation Safety Engineering
Verified
Journal Article
Open access
PKPaweł Kowaleczko
Paweł Kowaleczko
APAndrzej Panas
Andrzej Panas
MNMirosław NOWAKOWSKI
Mirosław NOWAKOWSKI
The results of numerical simulations performed for Dynamic Mechanical Analysis (DMA) measurements of thermal and mechanical (or thermomechanical) properties performed on a model composite structure are presented herein. The simulated elastic response of an epoxy-carbon fibre composite specimen was analysed for a case by which the model specimen was subjected to three-point bending with a free support. The epoxy-carbon fibre composite studied as explained herein exhibited extreme differences between the resilient properties of the epoxy resin matrix and the carbon fibre reinforcement. In addition, the carbon fibre reinforcement was both internally and structurally anisotropic. The numerical simulations were performed to demonstrate a qualitative dependence of the DMA measurement results on a certain structure of the investigated specimen and to determine if the DMA results could be qualified as effective or apparent. A macro-mechanical model of the specimen was developed and had the numerical calculations run with COMSOL/M, a FEM modelling software suite. The carbon fibre reinforcement was modelled with an orthotropic structure of laminar or circular inclusions with different characteristic dimensions. Representative material properties were assumed from the results of proprietary experimental investigations and certain reference literature data. The effect of the composite layers’ configuration and their characteristic dimensions on the evaluated model’s elastic modulus value was also studied. The results presented herein suggested a qualitative agreement with the results of the DMA investigations performed on real-life composite structures. They also proved the effectiveness of the developed numerical simulation methodology, shown herein, in the DMA of micro- and macromechanical phenomena

4 September 2026 in Electronics
Verified
Journal Article
Open access
PDF file
JSJakub Sadel
Jakub Sadel
TTTomasz Tarasiewicz
Tomasz Tarasiewicz
PKPaweł Kowaleczko
Paweł Kowaleczko
MZMaciej Ziaja
Maciej Ziaja
Daniel KostrzewaDaniel Kostrzewa
Daniel Kostrzewa
MKMichal Kawulok
Michal Kawulok
Assessing the quality of super-resolved images is important for comparing reconstruction algorithms, but pixel fidelity, perceptual appearance, and structural preservation do not always agree. We investigate whether keypoint detector response maps and detected keypoints can act as trainable structural indicators for aligned full-reference super-resolution image quality assessment (SR-IQA). A contrastive Multi-Scale Index Proposal (MSIP) objective specializes Key.Net toward SR-like resolution loss, candidate checkpoints are screened without subjective labels, and six response- and keypoint-based measures are evaluated on four subjective benchmarks. The results show a redistribution rather than a uniform improvement: MSIP correlations increase on three of the four benchmarks, both repeatability variants decrease for every trained family on SISAR and RealSRQ, and general keypoint performance on HPatches decreases for trained checkpoints. At the benchmark level, established comparators such as TOPIQ-FR, RQI, and DISQ remain stronger, and on three of the four datasets the best keypoint-based result is still obtained with the pretrained detector. The measures nevertheless retain quality-related variation after conditioning on ten IQA controls in 88 of 120 tested hypotheses, with markedly weaker evidence on RealSRQ. Their practical value is therefore diagnostic: the response maps localize the structures behind an HR–SR discrepancy, complementing rather than replacing established SR-IQA metrics.