Team

Włodzimierz Kasprzak

Research interests: image and speech analysis, computer vision, pattern recognition and artificial intelligence.

Selected projects list (start date):

2007

2003

MNiI: Sterowanie w systemach wielorobotowych wykonujących zadania usługowe (researcher)

Selected publications chronological list:

2020

W. Kasprzak, W. Szynkiewicz, M. Stefańczyk, W. Dudek, M. Węgierek, D. Seredyński, M. Figat, and C. Zieliński
Agent-based approach to the design of a multimodal interface for cyber-security event visualisation control
Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 68, no. No. 5 (October), pp. 1187–1205, 2020
[ BIB | DOI | abstract ]
```
@article{kasprzak2020agent,
  author = {Kasprzak, Włodzimierz and Szynkiewicz, Wojciech and Stefańczyk, Maciej and Dudek, Wojciech and Węgierek, Maciej and Seredyński, Dawid and Figat, Maksym and Zieliński, Cezary},
  journal = {Bulletin of the Polish Academy of Sciences: Technical Sciences},
  title = {Agent-based approach to the design of a multimodal interface for cyber-security event visualisation control},
  year = {2020},
  number = {No. 5 (October)},
  pages = {1187-1205},
  volume = {68},
  doi = {10.24425/bpasts.2020.134662},
  projects = {NPC},
  howpublished = {online},
  keywords = {multimodal interface, cyber security visualisation, embodied agent},
  twiki = {journal}
}
```
Convenient human-computer interaction is essential to carry out many exhausting and concentration-demanding activities. One of them is cyber-situational awareness as well as dynamic and static risk analysis. A specific design method for a multimodal human-computer interface (HCI) for cyber-security events visualisation control is presented. The main role of the interface is to support security analysts and network operators in their monitoring activities. The proposed method of designing HCIs is adapted from the methodology of robot control system design. Both kinds of systems act by acquiring information from the environment, and utilise it to drive the devices influencing the environment. In the case of robots the environment is purely physical, while in the case of HCIs it encompasses both the physical ambience and part of the cyber-space. The goal of the designed system is to efficiently support a human operator in the presentation of cyberspace events such as incidents or cyber-attacks. Especially manipulation of graphical information is necessary. As monitoring is a continuous and tiring activity, control of how the data is presented should be exerted in as natural and convenient way as possible. Hence two main visualisation control modalities have been assumed for testing: static and dynamic gesture commands and voice commands, treated as supplementary to the standard interaction. The presented multimodal interface is a component of the Operational Centre, which is a part of the National Cybersecurity Platform. Creation of the interface out of embodied agents proved to be very useful in the specification phase and facilitated the interface implementation.
W. Szynkiewicz, W. Kasprzak, C. Zieliński, W. Dudek, M. Stefańczyk, A. Wilkowski, and M. Figat
Utilisation of Embodied Agents in the Design of Smart Human–Computer Interfaces – A Case Study in Cyberspace Event Visualisation Control
Electronics, vol. 9, no. 6, p. 976, 2020
[ BIB | DOI | abstract | URL ]
```
@article{utilisation2020-twiki,
  author = {Szynkiewicz, Wojciech and Kasprzak, Włodzimierz and Zieliński, Cezary and Dudek, Wojciech and Stefańczyk, Maciej and Wilkowski, Artur and Figat, Maksym},
  title = {{Utilisation of Embodied Agents in the Design of Smart Human–Computer Interfaces -- A Case Study in Cyberspace Event Visualisation Control}},
  journal = {Electronics},
  year = {2020},
  volume = {9},
  number = {6},
  article-number = {976},
  pages = {976},
  doi = {10.3390/electronics9060976},
  projects = {npc},
  twiki = {journal},
  url = {https://www.mdpi.com/2079-9292/9/6/976}
}
```
The goal of the research reported here was to investigate whether the design methodology utilising embodied agents can be applied to produce a multi-modal human–computer interface for cyberspace events visualisation control. This methodology requires that the designed system structure be defined in terms of cooperating agents having well-defined internal components exhibiting specified behaviours. System activities are defined in terms of finite state machines and behaviours parameterised by transition functions. In the investigated case the multi-modal interface is a component of the Operational Centre which is a part of the National Cybersecurity Platform. Embodied agents have been successfully used in the design of robotic systems. However robots operate in physical environments, while cyberspace events visualisation involves cyberspace, thus the applied design methodology required a different definition of the environment. It had to encompass the physical environment in which the operator acts and the computer screen where the results of those actions are presented. Smart human–computer interaction (HCI) is a time-aware, dynamic process in which two parties communicate via different modalities, e.g., voice, gesture, eye movement. The use of computer vision and machine intelligence techniques are essential when the human is carrying an exhausting and concentration demanding activity. The main role of this interface is to support security analysts and operators controlling visualisation of cyberspace events like incidents or cyber attacks especially when manipulating graphical information. Visualisation control modalities include visual gesture- and voice-based commands.
A. Wilkowski, M. Stefańczyk, and W. Kasprzak
Training Data Extraction and Object Detection in Surveillance Scenario
Sensors, vol. 20, no. 9, p. 2689, 2020
[ BIB | DOI | abstract | URL ]
```
@article{wilkowski2020training,
  author = {Wilkowski, Artur and Stefańczyk, Maciej and Kasprzak, Włodzimierz},
  title = {{Training Data Extraction and Object Detection in Surveillance Scenario}},
  journal = {Sensors},
  year = {2020},
  volume = {20},
  number = {9},
  pages = {2689},
  article-number = {2689},
  doi = {10.3390/s20092689},
  projects = {npc},
  twiki = {journal},
  url = {https://www.mdpi.com/1424-8220/20/9/2689}
}
```
Police and various security services use video analysis for securing public space, mass events, and when investigating criminal activity. Due to a huge amount of data supplied to surveillance systems, some automatic data processing is a necessity. In one typical scenario, an operator marks an object in an image frame and searches for all occurrences of the object in other frames or even image sequences. This problem is hard in general. Algorithms supporting this scenario must reconcile several seemingly contradicting factors: training and detection speed, detection reliability, and learning from small data sets. In the system proposed here, we use a two-stage detector. The first region proposal stage is based on a Cascade Classifier while the second classification stage is based either on a Support Vector Machines (SVMs) or Convolutional Neural Networks (CNNs). The proposed configuration ensures both speed and detection reliability. In addition to this, an object tracking and background-foreground separation algorithm is used, supported by the GrabCut algorithm and a sample synthesis procedure, in order to collect rich training data for the detector. Experiments show that the system is effective, useful, and applicable to practical surveillance tasks.

2019

W. Kasprzak, W. Szynkiewicz, M. Stefańczyk, W. Dudek, M. Figat, M. Węgierek, D. Seredyński, and C. Zieliński

Agentowa struktura wielomodalnego interfejsu do Narodowej Platformy Cyberbezpieczeństwa, część 2

Pomiary Automatyka Robotyka, vol. 23, pp. 5–18, 2019

[ BIB | DOI | URL ]

@article{kasprzak2019agentowa2,
  title = {Agentowa struktura wielomodalnego interfejsu do Narodowej Platformy Cyberbezpieczeństwa, część 2},
  author = {Kasprzak, Włodzimierz and Szynkiewicz, Wojciech and Stefańczyk, Maciej and Dudek, Wojciech and Figat, Maksym and Węgierek, Maciej and Seredyński, Dawid and Zieliński, Cezary},
  journal = {Pomiary Automatyka Robotyka},
  volume = {23},
  year = {2019},
  pages = {5--18},
  doi = {10.14313/PAR_234/5},
  url = {http://www.par.pl/content/download/14939/183623/file/AgentowaStrukturaWielomodalnegoInterfejsuNarodowej_2.pdf}
}

W. Kasprzak, W. Szynkiewicz, M. Stefańczyk, W. Dudek, M. Figat, M. Węgierek, D. Seredyński, and C. Zieliński

Agentowa struktura wielomodalnego interfejsu do Narodowej Platformy Cyberbezpieczeństwa, część 1

Pomiary Automatyka Robotyka, vol. 23, pp. 41–54, 2019

[ BIB | DOI | URL ]

@article{kasprzak2019agentowa,
  title = {Agentowa struktura wielomodalnego interfejsu do Narodowej Platformy Cyberbezpieczeństwa, część 1},
  author = {Kasprzak, Włodzimierz and Szynkiewicz, Wojciech and Stefańczyk, Maciej and Dudek, Wojciech and Figat, Maksym and Węgierek, Maciej and Seredyński, Dawid and Zieliński, Cezary},
  journal = {Pomiary Automatyka Robotyka},
  volume = {23},
  year = {2019},
  pages = {41--54},
  doi = {10.14313/PAR_233/41},
  url = {http://www.par.pl/content/download/14931/183512/file/AgentowaStrukturaWielomodalnegoInterfejsuNarodowejPlatformyCyberbezpiecze%C5%84stwaCz1.pdf}
}

A. Wilkowski, W. Kasprzak, and M. Stefańczyk

Object detection in the police surveillance scenario

in Proceedings of the 2019 Federated Conference on Computer Science and Information Systems, 2019, vol. 18, pp. 363–372

[ BIB | DOI | URL ]

@inproceedings{FedCSIS2019291,
  author = {Wilkowski, Artur and Kasprzak, Włodzimierz and Stefańczyk, Maciej},
  pages = {363--372},
  title = {Object detection in the police surveillance scenario},
  booktitle = {Proceedings of the 2019 Federated Conference on Computer Science and Information Systems},
  year = {2019},
  editor = {Ganzha, Maria and Maciaszek, Leszek and Paprzycki, Marcin},
  publisher = {IEEE},
  doi = {10.15439/2019F291},
  url = {http://dx.doi.org/10.15439/2019F291},
  volume = {18},
  series = {Annals of Computer Science and Information Systems}
}

2018

M. Stefańczyk and W. Kasprzak
Model-Based 3D Object Recognition in RGB-D Images
in Bridging the Semantic Gap in Image and Video Analysis,
H. Kwaśnicka and L. C. Jain, Eds. Springer, 2018, pp. 73–96 [ BIB | DOI | abstract ]
```
@inbook{stefanczyk2018,
  author = {Stefańczyk, Maciej and Kasprzak, Włodzimierz},
  editor = {Kwaśnicka, Halina and Jain, Lakhmi C.},
  title = {Model-Based {3D} Object Recognition in {RGB-D} Images},
  booktitle = {{Bridging the Semantic Gap in Image and Video Analysis}},
  year = {2018},
  publisher = {Springer},
  pages = {73--96},
  isbn = {978-3-319-73891-8},
  doi = {10.1007/978-3-319-73891-8_5},
  twiki = {inbook}
}
```
A computational framework for 3D object recognition in RGB-D images is presented. The focus is on computer vision applications in indoor autonomous robotics, where objects need to be recognized either for the purpose of being grasped and manipulated by the robot, or where the entire scene must be recognized to allow high-level cognitive tasks to be performed. The framework integrates solutions for generic (i.e. type-based) object representation (e.g. semantic networks), trainable transformations between abstraction levels (e.g. by neural networks), reasoning under uncertain and partial data (e.g. Dynamic Bayesian Networks, Fuzzy Logic), optimized model-to-data matching (e.g. constraint optimization problems) and efficient search strategies (switching between data- and model-driven inference steps). The computational implementation of the object model and the object recognition strategy is presented in more details. Testing scenarios deal with the recognition of cups and bottles or household furniture. Conducted experiments and the chosen applications confirmed, that this approach is valid and may easily be adapted to multiple scenarios.

2017

C. Zieliński, M. Stefańczyk, T. Kornuta, M. Figat, W. Dudek, W. Szynkiewicz, W. Kasprzak, J. Figat, M. Szlenk, T. Winiarski, K. Banachowicz, T. Zielińska, E. G. Tsardoulias, A. L. Symeonidis, F. E. Psomopoulos, A. M. Kintsakis, P. A. Mitkas, A. Thallas, S. E. Reppou, G. T. Karagiannis, K. Panayiotou, V. Prunet, M. Serrano, J.-P. Merlet, S. Arampatzis, A. Giokas, L. Penteridis, I. Trochidis, D. Daney, and M. Iturburu
Variable structure robot control systems: The RAPP approach
Robotics and Autonomous Systems, vol. 94, pp. 226–244, 2017
[ BIB | DOI | abstract | URL ]
```
@article{zielinski2017variable-twiki,
  author = {Zieliński, Cezary and Stefańczyk, Maciej and Kornuta, Tomasz and Figat, Maksym and Dudek, Wojciech and Szynkiewicz, Wojciech and Kasprzak, Włodzimierz and Figat, Jan and Szlenk, Marcin and Winiarski, Tomasz and Banachowicz, Konrad and Zielińska, Teresa and Tsardoulias, Emmanouil G. and Symeonidis, Andreas L. and Psomopoulos, Fotis E. and Kintsakis, Athanassios M. and Mitkas, Pericles A. and Thallas, Aristeidis and Reppou, Sofia E. and Karagiannis, George T. and Panayiotou, Konstantinos and Prunet, Vincent and Serrano, Manuel and Merlet, Jean-Pierre and Arampatzis, Stratos and Giokas, Alexandros and Penteridis, Lazaros and Trochidis, Ilias and Daney, David and Iturburu, Miren},
  title = {Variable structure robot control systems: The RAPP approach},
  journal = {Robotics and Autonomous Systems},
  year = {2017},
  volume = {94},
  pages = {226 - 244},
  issn = {0921-8890},
  doi = {10.1016/j.robot.2017.05.002},
  projects = {fp7rapp},
  publisher = {Elsevier},
  twiki = {journal},
  url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2017/rapp-ras.pdf},
  note = {Zielinski}
}
```
This paper presents a method of designing variable structure control systems for robots. As the on-board robot computational resources are limited, but in some cases the demands imposed on the robot by the user are virtually limitless, the solution is to produce a variable structure system. The task dependent part has to be exchanged, however the task governs the activities of the robot. Thus not only exchange of some task-dependent modules is required, but also supervisory responsibilities have to be switched. Such control systems are necessary in the case of robot companions, where the owner of the robot may demand from it to provide many services.

2016

A. Wilkowski, T. Kornuta, M. Stefańczyk, and W. Kasprzak
Efficient generation of 3D surfel maps using RGB-D sensors
International Journal of Applied Mathematics And Computer Science (AMCS), vol. 26, no. 1, pp. 99–122, 2016
[ BIB | DOI | abstract | URL ]
```
@article{Wilkowski2014_amcs_surfels-twiki,
  author = {Wilkowski, Artur and Kornuta, Tomasz and Stefańczyk, Maciej and Kasprzak, Włodzimierz},
  title = {Efficient generation of 3D surfel maps using RGB-D sensors},
  journal = {International Journal of Applied Mathematics And Computer Science (AMCS)},
  year = {2016},
  volume = {26},
  number = {1},
  pages = {99-122},
  doi = {10.1515/amcs-2016-0007},
  projects = {GrantRobREx},
  owner = {tkornuta},
  timestamp = {2014.11.27},
  twiki = {jcr},
  url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/14-amcs-rgbd.pdf}
}
```
The article focuses on the problem of building dense 3D occupancy maps using commercial RGB-D sensors and the SLAM approach. In particular, it addresses the problem of 3D map representations, which must be able both to store millions of points and to offer efficient update mechanisms. The proposed solution consists of two such key elements, visual odometry and surfel-based mapping, but it contains substantial improvements: storing the surfel maps in octree form and utilizing a frustum culling-based method to accelerate the map update step. The performed experiments verify the usefulness and efficiency of the developed system.
K. Przerwa, W. Kasprzak, and M. Stefańczyk
Infrared image-based 3D surface reconstruction of free-form texture-less objects
in Proceedings of the 9th International Conference on Computer Recognition Systems CORES 2015, 2016, pp. 809–820
[ BIB | DOI | abstract | URL ]
```
@inproceedings{przerwa2015infrared-twiki,
  author = {Przerwa, Karolina and Kasprzak, Włodzimierz and Stefańczyk, Maciej},
  booktitle = {Proceedings of the 9th International Conference on Computer Recognition Systems CORES 2015},
  title = {Infrared image-based 3D surface reconstruction of free-form texture-less objects},
  year = {2016},
  series = {Advances in Intelligent Systems and Computing},
  pages = {809--820},
  publisher = {Springer},
  doi = {10.1007/978-3-319-26227-7_76},
  twiki = {article},
  url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/wk-sfs-kinect.pdf}
}
```
The analysis of infrared (IR) images obtained from a robot-mounted camera is presented, with the purpose to reconstruct the 3D surface of texture-less objects located in close range to the camera. The prospective application of this approach is object’s pose recognition with the aim of object grasping by a robot hand. Algorithms are developed that rely on the analysis of the luminance distribution in the IR image (the so-called shape-from-shading approach), followed by a depth-map approximation. Laboratory tests were carried out in order to evaluate the quality of obtained depth maps on some reference objects and to compare the estimated depth maps with corresponding point clouds acquired by a MS-Kinect device.
T. Winiarski, W. Kasprzak, M. Stefańczyk, and M. Walęcki
Automated inspection of door parts based on fuzzy recognition system
in 21th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR’2016, 2016, pp. 478–483
[ BIB | DOI | abstract | URL ]
```
@inproceedings{mmar_winiarski_automated-2016-twiki,
  author = {Winiarski, Tomasz and Kasprzak, Włodzimierz and Stefańczyk, Maciej and Walęcki, Michał},
  booktitle = {21th IEEE International Conference on Methods and Models in Automation and Robotics, MMAR'2016},
  title = {{Automated inspection of door parts based on fuzzy recognition system}},
  year = {2016},
  pages = {478--483},
  publisher = {IEEE},
  doi = {10.1109/MMAR.2016.7575182},
  projects = {GrantMeDeRo},
  twiki = {article},
  url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/mmar_winiarski_automated.pdf}
}
```
The article presents a comprehensive strategy of door parts (locks, handles, doorplates etc.) examination as a paradigm of active sensing. It covers the whole process – from segmentation, through initial hypothesis generation based on fuzzy inference, to final recognition and precise localization of the keyholes in a robot base coordinate system. The strategy is a preliminary stage of a door locks opening procedure. The image analysis process is divided into three steps. First, an initial region of interest is localized using a RGB-D low resolution camera mounted on the robot’s head. It is then categorized, based on its properties, as a lock, handle, doorplate etc. Finally it is inspected using 2D camera mounted on the robot’s arm. Thanks to the preliminary localization with the head camera the robot can look at the point of interest at sight, without time-consuming thorough inspection of the whole door. The whole system was formally specified as an embodied agent. For that purpose a system modeling language was used to specify embodied agent subsystems behaviors. The proposed strategy is verified experimentally using Velma prototype service robot.
C. Zieliński, W. Szynkiewicz, W. Kasprzak, M. Stefańczyk, M. Figat, W. Dudek, J. Figat, M. Szlenk, and T. Zielińska
Sterowniki o zmiennej strukturze w zastosowaniu do robotów społecznych
in XIV Krajowa Konferencja Robotyki – Postępy robotyki, 2016, vol. 1, pp. 5–14
[ BIB | abstract | URL ]
```
@inproceedings{kkr14_rapp-twiki,
  author = {Zieliński, Cezary and Szynkiewicz, Wojciech and Kasprzak, Włodzimierz and Stefańczyk, Maciej and Figat, Maksym and Dudek, Wojciech and Figat, Jan and Szlenk, Marcin and Zielińska, Teresa},
  booktitle = {XIV Krajowa Konferencja Robotyki -- Postępy robotyki},
  title = {{Sterowniki o~zmiennej strukturze w~zastosowaniu do robotów społecznych}},
  year = {2016},
  note = {Zielinski},
  pages = {5--14},
  volume = {1},
  conference = {kkr14},
  projects = {fp7rapp},
  lang = {pl},
  twiki = {inbook},
  url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/kkr14_rapp.pdf}
}
```
Roboty społeczne współdziałają z ludźmi, a ci mogą wymagać bardzo różnorodnych usług. Trudno sobie wyobrazić pokładowy sterownik robota autonomicznego, który byłby w stanie podołać każdemu zleceniu. Sterownik pokładowy, dysponujący ograniczonymi zasobami, musi więc mieć strukturę rekonfigurowalną, umożliwiającą wymianę części oprogramowania -– w zależności od zleconego zadania. W takich systemach dodatkowe oprogramowanie pobierane jest z chmury obliczeniowej i to ono przejmuje nadzór nad robotem na czas wykonania zadania, a więc w tym przypadku nie tylko następuje wymiana oprogramowania, ale również zamiana ról –- sterownik nadrzędny staje się podrzędnym. Artykuł przedstawia zarówno ogólny sposób specyfikacji sterowników, jak i realizację przykładowego zadania.

J. Figat and W. Kasprzak

Incremental Version Space Merging Approach to 3D Object Model Acquisition for Robot Vision

in Recent Advances in Automation, Robotics and Measuring Techniques, 2016, vol. 440, pp. 561–571

[ BIB | DOI | URL ]

@inproceedings{figat:automation-2016-twiki,
  author = {Figat, Jan and Kasprzak, Włodzimierz},
  booktitle = {Recent Advances in Automation, Robotics and Measuring Techniques},
  title = {{Incremental Version Space Merging Approach to 3D Object Model Acquisition for Robot Vision}},
  year = {2016},
  editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
  pages = {561-571},
  publisher = {Springer},
  series = {Advances in Intelligent Systems and Computing (AISC)},
  volume = {440},
  doi = {10.1007/978-3-319-29357-8_49},
  projects = {GrantRobREx},
  owner = {tkornut},
  timestamp = {2015.10.30},
  twiki = {article},
  url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2016/automation-incremental-version-space-merging.pdf}
}

2015

C. Zieliński, W. Szynkiewicz, M. Figat, K. T. Szlenk M., W. Kasprzak, M. Stefańczyk, T. Zielińska, and J. Figat
Reconfigurable control architecture for exploratory robots
in 10th International Workshop on Robot Motion and Control (RoMoCo), 2015, pp. 130–135
[ BIB | DOI | abstract | URL ]
```
@inproceedings{Zielinski:2015_RoMoCo-twiki,
  author = {Zieliński, Cezary and Szynkiewicz, Wojciech and Figat, Maksym and Szlenk, M., Kornuta T. and Kasprzak, Włodzimierz and Stefańczyk, Maciej and Zielińska, T. and Figat, Jan},
  booktitle = {10th International Workshop on Robot Motion and Control (RoMoCo)},
  title = {Reconfigurable control architecture for exploratory robots},
  year = {2015},
  editor = {K.~Kozłowski},
  pages = {130--135},
  organization = {IEEE},
  doi = {10.1109/RoMoCo.2015.7219724},
  url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2015/RoMoCo-RAPP.pdf},
  conference = {romoco15},
  projects = {fp7rapp},
  twiki = {article},
  note = {Zielinski}
}
```
Robots have to perform diverse and complex tasks. To face the limitations of the computational capabilities of robot on-board control computer, it is required to split the control systems between the robot embedded and the cloud computational resources. This paper presents a reconfigurable control architecture for a robot designed to meet this requirement. The embedded computer hosts a core agent, which provides the task-independent robot capabilities. The task dependent part called the dynamic agent is loaded from the cloud when required. The two mentioned agents execute the task, additionally utilising the capabilities of the cloud. Once the task is finished the dynamic agent is destroyed and the core agent awaits new user demands, upon which it reacts by downloading a new dynamic agent. Thus a reconfigurable system results, limited only by the resources provided by the cloud. The system is presented on an example of a humanoid robot exploring a home environment in search for hazards resulting from negligence of people suffering from mild dementia.

A. Wilkowski, T. Kornuta, and W. Kasprzak

Point-Based Object Recognition in RGB-D Images

in Proceedings of the 7th IEEE International Conference Intelligent Systems IS’2014, 2015, vol. 323, pp. 593–604

[ BIB | DOI | URL ]

@inproceedings{Wilkowski:2014_IS_point_models-twiki,
  author = {Wilkowski, Artur and Kornuta, Tomasz and Kasprzak, Włodzimierz},
  booktitle = {Proceedings of the 7th IEEE International Conference Intelligent Systems IS’2014},
  title = {{Point-Based Object Recognition in RGB-D Images}},
  year = {2015},
  editor = {Filev, D. and Jabłkowski, J. and Kacprzyk, J. and Krawczak, M. and Popchev, I. and Rutkowski, L. and Sgurev, V. and Sotirova, E. and Szynkarczyk, P. and Zadrozny, S.},
  pages = {593-604},
  publisher = {Springer},
  series = {Advances in Intelligent Systems and Computing (AISC)},
  volume = {323},
  doi = {10.1007/978-3-319-11310-4_51},
  projects = {GrantRobREx},
  isbn = {978-3-319-11309-8},
  owner = {tkornuta},
  timestamp = {2014.05.28},
  twiki = {inbook},
  url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/IS-point-model_v2.pdf}
}

E. G. Tsardoulias, C. Zieliński, W. Kasprzak, S. Reppou, A. L. Symeonidis, P. A. Mitkas, and G. Karagiannis

Merging Robotics and AAL ontologies: The RAPP methodology

in Progress in Automation, Robotics and Measuring Techniques. Vol. 2 Robotics., 2015, vol. 351, pp. 285–298

[ BIB | DOI ]

@inproceedings{Tsardoulias:2014_Automation-twiki,
  author = {Tsardoulias, E.G. and Zieliński, Cezary and Kasprzak, Włodzimierz and Reppou, S. and Symeonidis, A.L. and Mitkas, P.A. and Karagiannis, G.},
  booktitle = {Progress in Automation, Robotics and Measuring Techniques. Vol. 2 Robotics.},
  title = {Merging Robotics and AAL ontologies: The RAPP methodology},
  year = {2015},
  editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
  volume = {351},
  series = {Advances in Intelligent Systems and Computing (AISC)},
  pages = {285--298},
  publisher = {Springer},
  doi = {10.1007/978-3-319-15847-1_28},
  affiliation = {Institute of Control and Computation Engineering, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland},
  projects = {fp7rapp},
  isbn = {978-3-319-15846-4},
  owner = {tkornuta},
  timestamp = {2014.12.04},
  twiki = {inbook},
  note = {Zielinski}
}

W. Kasprzak, M. Stefańczyk, and A. Wilkowski
Printed steganography applied for the authentication of identity photos in face verification
in Cybernetics (CYBCONF), 2015 IEEE 2nd International Conference on, 2015, pp. 512–517
[ BIB | DOI | abstract | URL ]
```
@inproceedings{kasprzak2015printed,
  author = {Kasprzak, Włodzimierz and Stefańczyk, Maciej and Wilkowski, Artur},
  booktitle = {Cybernetics (CYBCONF), 2015 IEEE 2nd International Conference on},
  title = {Printed steganography applied for the authentication of identity photos in face verification},
  year = {2015},
  pages = {512-517},
  keywords = {biometrics (access control);face recognition;steganography;Digimarc tool;Fujitsu method;ICAO-consistent travel document;biometric SDK-s;biometric verification;electronic image;face image authentication;face verification;identity photo authentication;print-scan process;printed steganography;triangle net method;Authentication;Biomedical imaging;Correlation;Distortion;Face;Testing;Watermarking;face biometrics;image authentication;printed steganography},
  doi = {10.1109/CYBConf.2015.7175987},
  month = jun,
  twiki = {article},
  url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2015/cybconf.pdf}
}
```
Steganography methods are proposed for the authentication of the holder’s photo in an ICAO-consistent (travel) document. The embedded message is heavily influenced by the print-scan process, as the electronic image is first printed to be included into the document (or identity card) and is scanned next to constitute the reference template in an automatic face verification procedure. Two sufficiently robust steganography methods are designed, modifications of the “Fujitsu method” and the “triangle net” method. A third method, a commercial Digimarc tool is also applied. The methods are tested w.r.t. to face image authentication ability in a face verification procedure, using two commercial biometric SDK-s. Test results demonstrate the feasibility in biometric verification and high authentication quality of proposed approach.

W. Kasprzak, R. Pietruch, K. B. A. Wilkowski, and T. Kornuta

Integrating Data- and Model-Driven Analysis of RGB-D Images

in Proceedings of the 7th IEEE International Conference Intelligent Systems IS’2014, 2015, vol. 323, pp. 605–616

[ BIB | DOI | URL ]

@inproceedings{Kasprzak:2014_IS_integration-twiki,
  author = {Kasprzak, Włodzimierz and Pietruch, Rafał and Wilkowski, Konrad Bojarand Artur and Kornuta, Tomasz},
  booktitle = {Proceedings of the 7th IEEE International Conference Intelligent Systems IS’2014},
  title = {{Integrating Data- and Model-Driven Analysis of RGB-D Images}},
  year = {2015},
  editor = {Filev, D. and Jabłkowski, J. and Kacprzyk, J. and Krawczak, M. and Popchev, I. and Rutkowski, L. and Sgurev, V. and Sotirova, E. and Szynkarczyk, P. and Zadrozny, S.},
  pages = {605-616},
  publisher = {Springer},
  series = {Advances in Intelligent Systems and Computing (AISC)},
  volume = {323},
  doi = {10.1007/978-3-319-11310-4_52},
  projects = {GrantRobREx},
  isbn = {978-3-319-11309-8},
  owner = {tkornuta},
  timestamp = {2014.05.28},
  twiki = {inbook},
  url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/IS-object-modelling_v2.pdf}
}

J. Figat and W. Kasprzak

NAO-mark vs QR-code Recognition by Nao Robot Vision

in Progress in Automation, Robotics and Measuring Techniques. Vol. 2 Robotics., 2015, vol. 351, pp. 55–64

[ BIB | DOI | URL ]

@inproceedings{Figat2015QRcode-twiki,
  author = {Figat, Jan and Kasprzak, Włodzimierz},
  booktitle = {Progress in Automation, Robotics and Measuring Techniques. Vol. 2 Robotics.},
  title = {NAO-mark vs QR-code Recognition by Nao Robot Vision},
  year = {2015},
  editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
  volume = {351},
  series = {Advances in Intelligent Systems and Computing (AISC)},
  pages = {55--64},
  publisher = {Springer},
  doi = {10.1007/978-3-319-15847-1_6},
  url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2015/Figat2015QRcode.pdf},
  projects = {fp7rapp},
  isbn = {978-3-319-15846-4},
  owner = {jfigat},
  twiki = {inbook}
}

2014

T. Zielińska, W. Kasprzak, W. Szynkiewicz, and C. Zieliński

Path Planning for Robotized Mobile Supports

Journal of Mechanism and Machine Theory, vol. 78, pp. 51–64, 2014

[ BIB | DOI ]

@article{zielinska:2014_path,
  author = {Zielińska, Teresa and Kasprzak, Włodzimierz and Szynkiewicz, Wojciech and Zieliński, Cezary},
  title = {Path Planning for Robotized Mobile Supports},
  journal = {Journal of Mechanism and Machine Theory},
  year = {2014},
  volume = {78},
  pages = {51--64},
  doi = {https://doi.org/10.1016/j.mechmachtheory.2014.03.004},
  note = {Zielinski}
}

W. Kasprzak, T. Kornuta, and C. Zieliński

A Virtual Receptor in a Robot Control Framework

in Recent Advances in Automation, Robotics and Measuring Techniques, Cham, 2014, pp. 399–408

[ BIB | DOI ]

@inproceedings{kasprzak:2014_vr,
  author = {Kasprzak, Włodzimierz and Kornuta, Tomasz and Zieliński, Cezary},
  editor = {Szewczyk, Roman and Zieli{\'{n}}ski, Cezary and Kaliczy{\'{n}}ska, Ma{\l}gorzata},
  title = {A Virtual Receptor in a Robot Control Framework},
  booktitle = {Recent Advances in Automation, Robotics and Measuring Techniques},
  year = {2014},
  publisher = {Springer International Publishing},
  address = {Cham},
  pages = {399--408},
  isbn = {978-3-319-05353-0},
  doi = {https://doi.org/10.1007/978-3-319-05353-0_38},
  note = {Zielinski}
}

T. Zielińska, W. Kasprzak, C. Zieliński, and W. Szynkiewicz
Distributing the Supporting Heads for Robotized Machining
in Advances on Theory and Practice of Robots and Manipulators, Cham, 2014, pp. 509–517
[ BIB | DOI | abstract ]
```
@inproceedings{zielinska:2014,
  author = {Zielińska, Teresa and Kasprzak, Włodzimierz and Zieliński, Cezary and Szynkiewicz, Wojciech},
  editor = {Ceccarelli, Marco and Glazunov, Victor A.},
  title = {Distributing the Supporting Heads for Robotized Machining},
  booktitle = {Advances on Theory and Practice of Robots and Manipulators},
  year = {2014},
  publisher = {Springer International Publishing},
  address = {Cham},
  pages = {509--517},
  isbn = {978-3-319-07058-2},
  doi = {https://doi.org/10.1007/978-3-319-07058-2_57},
  note = {Zielinski}
}
```
The paper presents a method of placement for the movable supporting heads of a self-reconfigurable robotic fixture system. The whole system consists of two mobile platforms carrying parallel type manipulators equipped with deformable heads. The heads are providing the dynamic support for large flexible workpieces during machining. The two heads consecutively relocate and affix themselves to the supported thin metal sheet, so that one of them supports the workpiece while the other relocates itself in such a way as to precede the working tool. The method for heads positioning for circular contours is presented. Formulas are derived and the results are summarized.
T. Kornuta, M. Stefańczyk, and W. Kasprzak
Basic 3D solid recognition in RGB-D images
in Recent Advances in Automation, Robotics and Measuring Techniques, 2014, vol. 267, pp. 421–430
[ BIB | DOI | abstract | URL ]
```
@inproceedings{Kornuta:2014_automation_solid_recognition-twiki,
  author = {Kornuta, Tomasz and Stefańczyk, Maciej and Kasprzak, Włodzimierz},
  booktitle = {Recent Advances in Automation, Robotics and Measuring Techniques},
  title = {{Basic 3D solid recognition in RGB-D images}},
  year = {2014},
  editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
  pages = {421-430},
  publisher = {Springer},
  series = {Advances in Intelligent Systems and Computing (AISC)},
  volume = {267},
  doi = {10.1007/978-3-319-05353-0_40},
  projects = {GrantRobREx},
  owner = {tkornuta},
  timestamp = {2014.01.25},
  twiki = {inbook},
  url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/2014_automation_object-recognition.pdf}
}
```
The paper deals with the problem of recognition of 3D objects for the purpose of their subsequent grasping and manipulation by a two-handed robot. We describe the idea of a general framework for object recognition rooted in the compositional model of the world. This approach threats complex objects as entities constructed of simpler, elementary ones, termed solids. In particular, we focus on recognition of two types of such solids: cuboids and generalized cones. We present details of their operation, starting from the low-level processing of RGB-D images and ending with the generation of hypotheses regarding the presence and parameters of those types of solids.

W. Kasprzak, T. Kornuta, and C. Zieliński

A virtual receptor in a robot control framework

in Recent Advances in Automation, Robotics and Measuring Techniques, 2014, vol. 267, pp. 399–408

[ BIB | URL ]

@inproceedings{Kasprzak:2014_automation_virtual_receptor-twiki,
  author = {Kasprzak, Włodzimierz and Kornuta, Tomasz and Zieliński, Cezary},
  booktitle = {Recent Advances in Automation, Robotics and Measuring Techniques},
  title = {A virtual receptor in a~robot control framework},
  year = {2014},
  editor = {Szewczyk, Roman and Zieliński, Cezary and Kaliczyńska, Małgorzata},
  volume = {267},
  series = {Advances in Intelligent Systems and Computing (AISC)},
  pages = {399-408},
  publisher = {Springer},
  url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/2014_automation_virtual-receptor.pdf},
  projects = {GrantRobREx},
  owner = {tkornuta},
  timestamp = {2014.01.25},
  twiki = {inbook},
  zadanie = {pw12},
  note = {Zielinski}
}

J. Figat, T. Kornuta, and W. Kasprzak

Performance Evaluation of Binary Descriptors of Local Features

in Proceedings of the International Conference on Computer Vision and Graphics, 2014, vol. 8671, pp. 187–194

[ BIB | DOI | URL ]

@inproceedings{Figat:2014_ICCVG,
  author = {Figat, Jan and Kornuta, Tomasz and Kasprzak, Włodzimierz},
  booktitle = {Proceedings of the International Conference on Computer Vision and Graphics},
  title = {Performance Evaluation of Binary Descriptors of Local Features},
  year = {2014},
  editor = {Chmielewski, Leszek and Kozera, Ryszard and Shin, Bok-Suk and Wojciechowski, Konrad},
  pages = {187--194},
  publisher = {Springer Berlin / Heidelberg},
  series = {Lecture Notes in Computer Science},
  volume = {8671},
  affiliation = {Institute of Control and Computation Engineering, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland},
  doi = {10.1007/978-3-319-11331-9_23},
  projects = {fp7rapp},
  owner = {jfigat},
  timestamp = {2014.05.28},
  twiki = {inbook},
  url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2014/feature-comparison.pdf}
}

2013

C. Zieliński, P. Trojanek, T. Kornuta, T. Winiarski, M. Walęcki, W. Kasprzak, W. Szynkiewicz, and T. Zielińska
Wielorobotowa rekonfigurowalna forma mocująca obrabiane detale – program sterujący
Pomiary Automatyka Robotyka, no. 3, pp. 96–102, 2013
[ BIB | abstract | URL ]
```
@article{zielinski-swarm-par-13-p2-eng-twiki,
  author = {Zieliński, Cezary and Trojanek, Piotr and Kornuta, Tomasz and Winiarski, Tomasz and Walęcki, Michał and Kasprzak, Włodzimierz and Szynkiewicz, Wojciech and Zielińska, T.},
  journal = {Pomiary Automatyka Robotyka},
  title = {{Wielorobotowa rekonfigurowalna forma mocująca obrabiane detale – program sterujący}},
  year = {2013},
  note = {Multi-Robot-Based Reconfigurable Fixture - Plan Generation - Zielinski},
  number = {3},
  pages = {96--102},
  projects = {fp7swarm},
  twiki = {journal},
  url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2013/par-swarm-12-cz2.pdf}
}
```
Formy mocujące muszą być idealnie dopasowane do detali, które mają podpierać. Nawet mała modyfikacja kształtu w projekcie detalu powoduje, że kosztowna forma staje się bezużyteczna. Stąd duże zainteresowanie przemysłu formami rekonfigurowalnymi. Zastąpienie tradycyjnych form przez wiele robotów stanowiących ruchome podpory wymaga zaprojektowania specjalnego układu sterowania takim systemem oraz dedykowanej metody programowania umożliwiającej szybką rekonfigurację tego systemu. W pierwszej części artykułu przedstawiono problemy związane z konstrukcją form podpierających oraz zaprezentowano strukturę układu sterowania systemu wielorobotowego, natomiast w części drugiej skoncentrowano się na programie planującym działania poszczególnych robotów. Artykuł przedstawia sposób programowania rekonfigurowalnej formy. Programowanie w tym przypadku polega na zaplanowaniu czynności wykonywanych przez roboty podpierające. Plan układany jest automatycznie z wykorzystaniem sposobu rozwiązywania problemów wymagających spełnienia ograniczeń. Program planujący bierze pod uwagę ograniczenia fizyczne, geometryczne oraz te związane z upływem czasu. Dane wejściowe dla programu planującego są tożsame z rysunkami CAD detali oraz dane CAM sposobu ich obróbki. Na podstawie tych danych powstaje plan rozstawienia głowic, ruchów manipulatorów oraz translokacji baz mobilnych. Układ sterowania na podstawie otrzymanego planu steruje zachowaniem robotów, umożliwiając maszynie CNC wiercenie otworów bądź frezowanie. Eksperymenty przeprowadzone w fabryce wykazały, że zaprojektowany system usztywnia detal na tyle, aby wynik obróbki mechanicznej był zadowalający. Jeżeli liczba różnych detali podlegających obróbce jest znaczna, to zaprojektowany system stanowi względnie tanią alternatywę dla wytworzenia i późniejszego magazynowania wielu form.
C. Zieliński, P. Trojanek, T. Kornuta, T. Winiarski, M. Walęcki, W. Kasprzak, W. Szynkiewicz, and T. Zielińska
Wielorobotowa rekonfigurowalna forma mocująca obrabiane detale – układ sterowania
Pomiary Automatyka Robotyka, no. 2, pp. 79–85, 2013
[ BIB | abstract | URL ]
```
@article{zielinski-swarm-par-13-p1-eng-twiki,
  author = {Zieliński, Cezary and Trojanek, Piotr and Kornuta, Tomasz and Winiarski, Tomasz and Walęcki, Michał and Kasprzak, Włodzimierz and Szynkiewicz, Wojciech and Zielińska, T.},
  journal = {Pomiary Automatyka Robotyka},
  title = {{Wielorobotowa rekonfigurowalna forma mocująca obrabiane detale – układ sterowania}},
  year = {2013},
  note = {Multi-Robot-Based Reconfigurable Fixture - Control System - Zielinski},
  number = {2},
  pages = {79-85},
  projects = {fp7swarm},
  twiki = {journal},
  url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2013/par-swarm-12-cz1.pdf}
}
```
Formy mocujące muszą być idealnie dopasowane do detali, które maja podpierać. Nawet mała modyfikacja kształtu w projekcie detalu powoduje, że kosztowna forma staje się bezużyteczna. Stąd duże zainteresowanie przemysłu formami rekonfigurowalnymi. Zastąpienie tradycyjnych form przez wiele robotów stanowiących ruchome podpory wymaga zaprojektowania specjalnego układu sterowania oraz dedykowanej metody programowania umożliwiającej szybką rekonfigurację takiego systemu. Układ sterowania systemu wielorobotowego został zaprojektowany na podstawie formalnej specyfikacji definiującej strukturę tego układu za pomocą agentów, których zachowanie określane jest za pomocą funkcji przejścia. W ten sposób stworzono system modularny, umożliwiający parametryzację oprogramowania ułatwiające wprowadzanie zmian przy sprawdzaniu różnych rozwiązań technicznych, co jest nieodzowne przy konstrukcji systemu prototypowego. Eksperymenty przeprowadzone w fabryce wykazały, że zaprojektowany system usztywnia detal na tyle, aby wynik obróbki mechanicznej był zadowalający. Jeżeli liczba różnych detali podlegających obróbce jest znaczna, to zaprojektowany system stanowi względnie tanią alternatywę dla wytworzenia i późniejszego magazynowania wielu form. Ponadto zaprojektowany układ sterowania może sterować zespołami robotów o różnej liczności oraz dopuszcza zmiany konstrukcyjne poszczególnych części robotów. Pierwsza część artykułu przedstawia problemy związane z konstrukcją form podpierających oraz prezentuje strukturę układu sterowania systemu wielorobotowego, natomiast część druga koncentruje się na programie planującym działania robotów.
C. Zieliński, W. Kasprzak, T. Kornuta, W. Szynkiewicz, P. Trojanek, M. Walęcki, T. Winiarski, and T. Zielińska
Control and Programming of a Multi-Robot-Based Reconfigurable Fixture
Industrial Robot: An International Journal, vol. 40, no. 4, pp. 329–336, 2013
[ BIB | DOI | abstract | URL ]
```
@article{zielinski12ir-swarm-twiki,
  author = {Zieliński, Cezary and Kasprzak, Włodzimierz and Kornuta, Tomasz and Szynkiewicz, Wojciech and Trojanek, Piotr and Walęcki, Michał and Winiarski, Tomasz and Zielińska, T.},
  title = {Control and Programming of a~Multi-Robot-Based Reconfigurable Fixture},
  journal = {Industrial Robot: An International Journal},
  year = {2013},
  volume = {40},
  number = {4},
  pages = {329--336},
  url = {http://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2013/13-ir-swarm.pdf},
  doi = {10.1108/01439911311320831},
  projects = {fp7swarm},
  twiki = {jcr},
  note = {Zielinski}
}
```
Machining fixtures must fit exactly the work piece to support it appropriately. Even slight change in the design of the work piece renders the costly fixture useless. Substitution of traditional fixtures by a programmable multi-robot system supporting the work pieces requires a specific control system and a specific programming method enabling its quick reconfiguration.
M. Stefańczyk, K. Bojar, and W. Kasprzak
Utilization of Depth and Color Information in Mobile Robotics
in Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013, 2013, vol. 226, pp. 845–854
[ BIB | DOI | abstract | URL ]
```
@inproceedings{stefanczyk2013utilization-twiki,
  author = {Stefańczyk, Maciej and Bojar, Konrad and Kasprzak, Włodzimierz},
  booktitle = {Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013},
  title = {Utilization of Depth and Color Information in Mobile Robotics},
  year = {2013},
  volume = {226},
  series = {Advances in Intelligent Systems and Computing},
  pages = {845--854},
  publisher = {Springer},
  projects = {GrantRobREx},
  twiki = {inbook},
  doi = {10.1007/978-3-319-00969-8_83},
  url = {https://gitlab-stud.elka.pw.edu.pl/robotyka/rpmpg_pubs/-/raw/main/2013/cores13mobile.pdf}
}
```
Computer vision plays an increasing role in robotics, as the computing power of modern computers grows year by year allowing more advanced algorithms to be implemented. Along with visual information, depth is also widely used in navigation of mobile robots, for example for obstacle detection. As cheap depth sensors become popular nowadays, there is a possibility to use data from both sources to further enhance the processes of navigation and object detection. This article presents some possibilities of utilizing in mobile robotics the integrated video and depth images - by performing image segmentation for environment description, optical flow estimation for obstacle avoidance and object detection for semantic map creation. All of the presented examples are based on real, working applications, which additionally proves validity of proposed methods.
W. Kasprzak, M. Stefańczyk, and J. Popiołkiewicz
The Print-Scan Problem in Printed Steganography of Face Images
in Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013, 2013, vol. 226, pp. 491–500
[ BIB | DOI | abstract ]
```
@inproceedings{kasprzak2013print-twiki,
  author = {Kasprzak, Włodzimierz and Stefańczyk, Maciej and Popiołkiewicz, Jan},
  booktitle = {Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013},
  title = {The Print-Scan Problem in Printed Steganography of Face Images},
  year = {2013},
  volume = {226},
  series = {Advances in Intelligent Systems and Computing},
  pages = {491--500},
  publisher = {Springer},
  twiki = {article},
  doi = {10.1007/978-3-319-00969-8_48}
}
```
The use of steganography and watermarking techniques for a secure identification and automatic authentication of the holder’s photo in an ICAO-consistent (travel) document is proposed. A specific distortion of the hidden watermarks is caused by the print-scan process, as a printed photo is scanned to constitute the reference pattern in face verification. The main distortions induced by this process are identified - image rotation and cropping, nonlinear intensity change and additive color quantization noise. Three steganography methods are selected and adapted for this application. They provide hidden watermark insertion in the image domain, the Fourier-Mellin transform domain or in a net of normalized triangle regions. Test results induce the conditions for the proper use of these methods.

2012

M. Stefańczyk and W. Kasprzak

Multimodal segmentation of dense depth maps and associated color information

in Proceedings of the International Conference on Computer Vision and Graphics, 2012, vol. 7594, pp. 626–632

[ BIB | DOI | abstract | URL ]

@inproceedings{stefanczyk2012multimodal-twiki,
  author = {Stefańczyk, Maciej and Kasprzak, Włodzimierz},
  booktitle = {Proceedings of the International Conference on Computer Vision and Graphics},
  title = {Multimodal segmentation of dense depth maps and associated color information},
  year = {2012},
  volume = {7594},
  series = {Lecture Notes in Computer Science},
  pages = {626--632},
  publisher = {Springer Berlin / Heidelberg},
  doi = {10.1007/978-3-642-33564-8_75},
  url = {https://robotyka.ia.pw.edu.pl/rpmpg_pubs/2012/iccvg_12_multimodal.pdf},
  affiliation = {Institute of Control and Computation Engineering, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland},
  twiki = {article}
}

W. Kasprzak and M. Stefańczyk
3D semantic map computation based on depth map and video image
in Proceedings of the International Conference on Computer Vision and Graphics, 2012, vol. 7594, pp. 441–448
[ BIB | DOI | abstract | URL ]
```
@inproceedings{kasprzak2012semantic-twiki,
  author = {Kasprzak, Włodzimierz and Stefańczyk, Maciej},
  booktitle = {Proceedings of the International Conference on Computer Vision and Graphics},
  title = {{3D semantic map computation based on depth map and video image}},
  year = {2012},
  editor = {Bolc, L. and Tadeusiewicz, R. and Chmielewski, L. and Wojciechowski, K.},
  pages = {441--448},
  publisher = {Springer Berlin / Heidelberg},
  series = {Lecture Notes in Computer Science},
  volume = {7594},
  affiliation = {Institute of Control and Computation Engineering, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland},
  doi = {10.1007/978-3-642-33564-8_53},
  twiki = {article},
  url = {https://robotyka.ia.pw.edu.pl/rpmpg_pubs/2012/iccvg_12_semantic.pdf}
}
```
A model-based object recognition in video and depth images is proposed for the purpose of semantic map creation in mobile robotics. Three types of objects are modeled: a human silhouette, a chair/table and corridor walls. A bi-driven hypothesis generation and verification strategy is outlined. The object model includes a hierarchic semantic nets, combined with a graph of constraints and a Bayesian network for hypothesis generation and evaluation. For the purpose of model-to-image matching we define an incomplete constraint satisfaction problem and solve it. Our CSP-search allows partial assignment solutions and uses a stochastic inference to provide judgments of such solutions. The verification of hypotheses is due to a top-down occlusion propagation process, that explains why some object parts are hidden or occluded.

Selected projects list (start date):

2020

2018

2017

2016

2014

2013

2012

2008

2007

2003

Selected publications chronological list:

2020

2019

2018

2017

2016

2015

2014

2013

2012