Computer Vision Systems Group
Info
The Computer Vision Systems Group focuses its activities on advanced methods in computer vision and multimodal data analysis, developing algorithms that enable semantic image interpretation, integration of heterogeneous data sources (including satellite data, LiDAR, 3D imaging, and temporal data), as well as their processing and visualization in 2D and 3D environments. The research includes, among others, object detection and segmentation, registration of visual data, and the development of scalable machine learning models and decision support systems, supported by optimization methods and physics-inspired approaches. Particular emphasis is placed on applications in complex systems with high structural uncertainty, such as transport, environmental, and diagnostic systems (including biomedical applications).
An important element of the group’s activity is international collaboration. The team works with researchers from Halmstad University on AI models inspired by brain neuroplasticity, developed for continual and lifelong learning. Collaboration is also being developed with the University of Žilina, focusing on applications of optimization and machine learning methods (including computer vision) in real-world transport systems. Team members also collaborate with the Wigner Research Centre for Physics in Budapest in the field of advanced physics-inspired computational methods and optimization.
Among the group’s key achievements are the development of novel methods for multimodal data integration and analysis, as well as tools for 3D visualization. The team actively participates in international research projects, including the European Q-Fence project funded under the Horizon Europe program, within which post-quantum cryptographic methods are being developed to ensure secure processing and transmission of sensitive data (including medical, financial, and satellite data). The conducted work combines fundamental research with practical applications, particularly in the areas of data security, environmental analysis, and modern transport systems.
The Computer Vision Systems Group has existed since 1987. The group’s co-founder and long-time head was Dr. Eng. Ryszard Winiarczyk. The Computer Vision Systems Group is now led by Associate Professor Krzysztof Domino.
Publications
2024
- Bełdowski P.; Weber P.; Gadomski A.; Sionkowski P.; Kruszewska N.; Domino K.; Studies of the Interaction Dynamics in Albumin–Chondroitin Sulfate Systems by Recurrence Method; The 16th International Conference "Dynamical Systems – Theory and Applications" (DSTA 2021); 2024
- Śmierzchalski T.; Pawłowski J.; Przybysz A.; Pawela Ł.; Puchała Z.; Koniorczyk M.; Gardas B.; Deffner S.; Domino K.; Hybrid quantum-classical computation for automatic guided vehicles scheduling; Scientific Reports; 2024
- Weber P.; Bełdowski P.; Gadomski A.; Domino K.; Sionkowski P.; Ledziński D.; Statistical method for analysis of interactions between chosen protein and chondroitin sulfate in an aqueous environment; The 16th International Conference "Dynamical Systems – Theory and Applications" (DSTA 2021); 2024
2023
- Ostrowski M.; Blachowski B.; Wójcik B.; Żarski M.; Tauzowski P.; Jankowski Ł.; A framework for computer vision-based health monitoring of a truss structure subjected to unknown excitations; Earthquake Engineering and Engineering Vibration; 2023
- Kessler S.; Ostaszewski M.; Bortkiewicz M.; Żarski M.; Wołczyk M.; Parker-Holder J.; Roberts S.; Miłoś P.; The Effectiveness of World Models for Continual Reinforcement Learning; Conference on Lifelong Learning Agents; 2023
- Wójcik B.; Żarski M.; Książek K.; Miszczak J.; Skibniewski M.; A deep learning method for hard-hat-wearing detection based on head center localization; Bulletin of the Polish Academy of Sciences Technical Sciences; 2023
2022
- Blachowski B.; Ostrowski M.; Żarski M.; Wójcik B.; Tauzowski P.; Jankowski L.; An Efficient Computer Vision-Based Method for Estimation of Dynamic Displacements in Spatial Truss Structures; Workshop on Structural Health Monitoring; 2022
- Krawiec K.; Koniorczyk M.; Domino K.; Możliwość zastosowania obliczeń kwantowych w modelowaniu systemów i procesów transportowych; Transport Miejski i Regionalny; 2022
- Domino K.; Miszczak J.; Will you infect me with your opinion?; Physica A: Statistical Mechanics and its Applications; 2022
- Domino K.; Koniorczyk M.; Puchała Z.; Statistical quality assessment of Ising-based annealer outputs; Quantum Information Processing; 2022
- Domino K.; Kundu A.; Salehi Ö.; Krawiec K.; Quadratic and Higher-Order Unconstrained Binary Optimization of Railway Rescheduling for Quantum Computing; Quantum Information Processing; 2022
2021
- Wójcik B.; Żarski M.; Salamak M.; Miszczak J.; Extracting crack characteristics from RGB-D images; 2nd Workshop on Engineering Optimization – WEO 2021; 2021
- Żarski M.; Wójcik B.; Książek K.; Salamak M.; Miszczak J.; Advances in applicable deep-learning based defect detection; 2nd Workshop on Engineering Optimization – WEO 2021; 2021
- Wójcik B.; Żarski M.; The measurements of surface defect area with an RGB-D camera for a BIM-backed bridge inspection; Bulletin of the Polish Academy of Sciences: Technical Sciences; 2021
- Żarski M.; Wójcik B.; Książek K.; Miszczak J.; Finicky transfer learning—A method of pruning convolutional neural networks for cracks classification on edge devices; Computer-Aided Civil And Infrastructure Engineering; 2021
- Kruszewska N.; Domino K.; Weber P.; Water Behvaior Near the Lipid Bilayer; Gadomski A. (eds) Water in Biomechanical and Related Systems. Biologically-Inspired Systems; 2021
- Bełdowski P.; Domino K.; Bełdowski D.; Dobosz R.; Analysis of Protein Intramolecular and Solvent Bonding on Example of Major Synovial Fluid Component; Gadomski A. (eds) Water in Biomechanical and Related Systems. Biologically-Inspired Systems; 2021