Dmitry Sidorchuk

Dr. Dmitry Sidorchuk


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
1 December 2022 in Journal of Communications Technology and Electronics
Verified
Journal Article
Closed access
PDF file
MPM. A. Pavlova
M. A. Pavlova
DSDmitry Sidorchuk
Dmitry Sidorchuk
DKD. O. Kushchev
D. O. Kushchev
DBDmitry Bocharov
Dmitry Bocharov
Dmitry NikolaevDmitry Nikolaev
Dmitry Nikolaev
Unmanned aerial vehicles (UAVs) are widely used as data sources for monitoring of farm lands. As distinct from satellite imagery, in which satellites often have a sun-synchronous trajectory, UAV data can be characterized by significant variability of shooting conditions, which complicates data analytics. We consider the problem of equalization of the shooting conditions for a hyperspectral image using specific spatial image zones (clues), for which the values obtained under the target conditions are known. It is shown that the affine model of the irradiance incoming to a sensor on the test dataset is more accurate than the linear one. For analytical calculation of the parameters of the affine model, the presence of instability in the spectral regions, in which the images of clue regions have close values, is shown. A regularized numerical method that is free of such a disadvantage is proposed for estimation of the parameters of the affine model. The affine model is used to propose a new equalization method that makes it possible to bring images obtained under original conditions closer to images obtained under target conditions, reducing the error by a factor of 4.6. For the experimental study of the models and the equalization method, we use a specific dataset consisting of the AVIRIS hyperspectral images obtained for a single area under significantly different conditions for illumination.

1 December 2022 in Journal of Communications Technology and Electronics
Verified
Journal Article
Closed access
PDF file
ANAlmir Nurmukhametov
Almir Nurmukhametov
DSDmitry Sidorchuk
Dmitry Sidorchuk
IKIvan Konovalenko
Ivan Konovalenko
Artem NikonorovArtem Nikonorov
Artem Nikonorov
MGM. A. Gracheva
M. A. Gracheva
In precision agriculture, remote sensing using unmanned aerial vehicles (UAVs) can well complement and, in several cases, even completely replace satellite imagery. However, it is important to harmonize their signals for consistent use. In this work, the problem of spectral harmonization is considered. We propose two new methods of spectral harmonization: method of root-polynomial correction (RPC) and model-based spectral harmonization (MBSH). The methods are evaluated on a synthetic dataset that is generated using AVIRIS hyperspectral data and known spectral sensitivities of two sensors: Sentinel-2A (satellite) and Parrot Sequoia+ (UAV). The RPC has outperformed all state-of-the-art methods in most bands. The MBSH method, despite of moderate result, has an important advantage: it does not require retraining for sensors with different spectral sensitivities.

7 July 2025 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
DSDmitry Sidorchuk
Dmitry Sidorchuk
ANAlmir Nurmukhametov
Almir Nurmukhametov
PMPaul Maximov
Paul Maximov
VBValentina Bozhkova
Valentina Bozhkova
ASAnastasia Sarycheva
Anastasia Sarycheva
Dmitry NikolaevDmitry Nikolaev
Dmitry Nikolaev
Color vision deficiency (CVD) affects around 300 million people globally due to issues with cone cells, highlighting the need for effective daltonization methods. These methods modify color palettes to enhance detail visibility for individuals with CVD. However, they can also distort the natural appearance of images. This study presents a novel daltonization method that focuses on preserving image naturalness for both normal trichromats and individuals with CVD. Our approach modifies only the achromatic component while enhancing detail visibility for individuals with CVD. To compare our approach with the previously known anisotropic daltonization method, we utilize objective and subjective evaluations that separately assess visibility enhancement and naturalness preservation. Our findings indicate that the proposed method outperforms the anisotropic method in naturalness by over 10 times according to objective criteria. Subjective evaluations revealed that more than 90% of CVD individuals and 95% of trichromats preferred our method for its natural appearance. Although objective contrast metrics suggest inferior visibility enhancement, subjective evaluation indicates comparable performance: contrast improvement was observed in 65% of protan cases for our method versus 70% for the anisotropic method, with contrast deterioration in 18% versus 7%, respectively. Overall, our method offers superior naturalness while maintaining comparable detail discrimination.

26 November 2025 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
Artem NikonorovArtem Nikonorov
Artem Nikonorov
DSDmitry Sidorchuk
Dmitry Sidorchuk
NONikita Odinets
Nikita Odinets
VVVladislav Volkov
Vladislav Volkov
ASAnastasia Sarycheva
Anastasia Sarycheva
Dmitry NikolaevDmitry Nikolaev
Dmitry Nikolaev
Hyperspectral remote sensing images (HSIs) provide invaluable information for environmental and agricultural monitoring, yet they are often degraded by atmospheric haze, which distorts spatial and spectral content and hinders downstream analysis. Progress in hyperspectral dehazing has been limited by the absence of paired real-haze benchmarks; most prior studies rely on synthetic haze or unpaired data, restricting fair evaluation and generalization. We present HyperHazeOff, the first comprehensive benchmark for hyperspectral dehazing that unifies data, tasks, and evaluation protocols. It comprises (i) RRealHyperPDID, 110 scenes with paired real-haze and haze-free HSIs (plus RGB images), and (ii) RSyntHyperPDID, 2616 paired samples generated using a physically grounded haze formation model. The benchmark also provides agricultural field delineation and land classification annotations for downstream task quality assessment, standardized train/validation/test splits, preprocessing pipelines, baseline implementations, pretrained weights, and evaluation tools. Across six state-of-the-art methods (three RGB-based and three HSI-specific), we find that hyperspectral models trained on the widely used HyperDehazing dataset fail to generalize to real haze, while training on RSyntHyperPDID enables significant real-haze restoration by AACNet. HyperHazeOff establishes reproducible baselines and is openly available to advance research in hyperspectral dehazing.

20 October 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Artem NikonorovArtem Nikonorov
Artem Nikonorov
DSDmitry Sidorchuk
Dmitry Sidorchuk
NONikita Odinets
Nikita Odinets
VVVladislav Volkov
Vladislav Volkov
ASAnastasia Sarycheva
Anastasia Sarycheva
Dmitry NikolaevDmitry Nikolaev
Dmitry Nikolaev
Hyperspectral remote sensing imagery provides invaluable information for environmental and agricultural monitoring but remains highly susceptible to atmospheric haze. We introduce the first comprehensive benchmark for hyperspectral image dehazing featuring paired real-world hazy and haze-free remote sensing data. The Remote sensing Real-world Hyperspectral Paired Dehazing Image Dataset (RRealHyperPDID) includes 110 scenes with naturally occurring haze and corresponding clear references, enabling reliable evaluation of dehazing algorithms across both hyperspectral and RGB domains. To support model training and ablation studies, we present the Remote Sensing Synthetic Hyperspectral Paired Dehazing Image Dataset (RSyntHyperPDID), comprising 2,616 synthetically generated hazy-clear pairs. The benchmark also provides agricultural field delineation annotations, allowing assessment of dehazing effects on downstream remote sensing tasks. Extensive experiments with six state-of-the-art methods reveal fundamental limitations of existing hyperspectral dehazing approaches and highlight the need for realistic, domain-consistent data. Models trained on RSyntHyperPDID demonstrate better generalization to real hazy data, establishing a new baseline for hyperspectral dehazing.

22 June 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
NFNikita Firsov
Nikita Firsov
OTOlga Terekhova
Olga Terekhova
NONikita Odinets
Nikita Odinets
AFAlexey Fedotov
Alexey Fedotov
AMArtem Muzyka
Artem Muzyka
DSDmitry Sidorchuk
Dmitry Sidorchuk
Vision-language models (VLMs) are increasingly used in remote sensing (RS), yet their ability to perform abstract visual reasoning remains poorly understood. Existing RS benchmarks primarily evaluate perception-oriented capabilities, such as scene classification, object detection, image captioning, and visual question answering, providing limited insight into higher-level reasoning. To address this gap, we introduce BMRS, the first remote-sensing benchmark based on the Bongard problem paradigm. The benchmark comprises 122 problems constructed from satellite and aerial imagery and organized into seven categories: Shape, Semantic, Presence, Spatial, Size, Number, and Same. Unlike conventional perception benchmarks, BMRS requires models to infer abstract concepts from multiple images, thereby evaluating few-shot learning, concept induction, analogy making, and relational reasoning. To establish a human baseline, we conducted a study involving 113 participants, who achieved an average accuracy of 74.5%. We then evaluated three groups of models: proprietary large-scale VLMs, open-source general-purpose VLMs, and remote sensing vision-language models (RSVLMs). The strongest proprietary models, ChatGPT and Gemini, achieved accuracies of 89.3% and 86.9%, respectively, surpassing human performance. In contrast, the best open-source general-purpose model achieved 42.6% accuracy, while the strongest RSVLM reached only 20.5%. Analysis across problem categories revealed that Semantic problems were the easiest for both humans and models, indicating that object-level semantic understanding transfers effectively to the remote-sensing domain: several RSVLMs achieved performance comparable to substantially larger general-purpose models. Conversely, Spatial problems proved the most challenging, highlighting spatial-relational reasoning as a key limitation of current RSVLMs. BMRS provides a challenging benchmark for measuring progress toward reasoning-capable RSVLMs and offers new insights into the strengths and limitations of current model adaptation strategies.