|
|
Algorithms and Methods for Fusion of Matrix Sensors Data during Mapping Inside Building
Klečka, Jan ; Hlaváč, Václav (referee) ; Železný, Miloš (referee) ; Horák, Karel (advisor)
The dissertation is aimed at methods for simultaneous processing of various type sensor data into a virtual map. Conceptually the development was focused on algorithms for simultaneous localization and mapping. In theoretical part has the problem been addressed by the probabilistic approach. The practical part deals with a new approach called as partially collective mapping whose application leads to creation map in form of a set of simple geometrical entities which represents in piecewise manner a border between obstacles and free space.
|
|
|
People tracking in sparse crowd using multiple cameras
Zimmermann, Jan ; Hlaváč, Václav (advisor) ; Suk, Tomáš (referee)
In this thesis, we introduce a new algorithm for tracking of multiple people in image sequences from surveillance cameras. The algorithm handle with trustworthiness in similarity measure of human gures in images. All decisions are made as trustworthily as possible. The algorithm nds out the number of people in the scene autonomously. It deals with potential temporary occlusions of people in image. The tracking algorithm does not suffer from the problem of human model initialization as some other methods do. The implementation of our algorithm is a part of this thesis. This implementation has veri ed the characteristics of the algorithm. We have used two different methods for the image segmentation. Both method prove successful in different conditions. We have used a color information to compare the visual similarity. Suitable future extensions are suggested at the end of this thesis.
|
|
|
Control of the industrial robot with cameras
Janda, Pavel ; Hlaváč, Václav (advisor) ; Obdržálek, David (referee)
This thesis belongs to the implementation category of diploma theses. The work contributes to the EC project COSPAL, IST-2003-004176. The main goal of the project was the creation of the system of control and processing of the camera information for the assembly task. The demonstrator is used within the scope of the COSPAL project to solve a child's game - shape sorter puzzle. For solving the puzzle, the industrial robot CRS Robotics A465 was used. The robot has been available at the supervisor's place.
|
|
|
Unsupervised learning based on images
Krupička, Radim ; Hlaváč, Václav (advisor) ; Forst, Libor (referee)
The aim of the project was to create an experimental environment for solving the children puzzle shape sorter . This environment serve as a testbed for various learning tasks of cognitive nature with image feedback. This puzzle is a demonstrator of the EU project COSPAL, IST-004176. The industrial robot CRS A-465 with six degrees of freedom and its control system is used. The scene is observed by one static camera. The system processes the images from the camera and the further robot movement is based on the reinforcement learning.
|
|
|
Online and Offline Vocabulary Correction while using a Digital Pen
Shrestha, Prajol ; Hlaváč, Václav (advisor) ; Průša, Daniel (referee)
This thesis is a requirement for the completion of my double degree with Charles University and University of Nancy (France) under the Erasmus Mundus masters program in Language and Communication Technology. The topic was provided by Prof. Abdel BelaÄd along with Actimage Company and has been completed and successfully defended at University of Nancy under their supervision. After the defense in France, I came here to Prague and worked with my co-supervisor Dr. Václav Hlaváč to improve the text of the thesis to meet the standards of Charles University in order to defend it in Prague. The aim of this work is to study some helpful handwriting correction marks and propose a system that automatically incorporates the corrections made by the writer while writing with a digital pen. The problem is complex because the corrections have to be at the same time readable by the writer and by the machine. Even detecting a free řowing line of handwritten text has not been understood completely by machines. The spatial relations between the correction marks and the text line are easily detected by the writers and readers and hence systematic to them, yet for machines this detection is a huge challenge. Humans have an intelligence that is hard to mimic by machines. This seemingly systematic writing has not been studied in...
|
|
|
Algorithms and Methods for Fusion of Matrix Sensors Data during Mapping Inside Building
Klečka, Jan ; Hlaváč, Václav (referee) ; Železný, Miloš (referee) ; Horák, Karel (advisor)
The dissertation is aimed at methods for simultaneous processing of various type sensor data into a virtual map. Conceptually the development was focused on algorithms for simultaneous localization and mapping. In theoretical part has the problem been addressed by the probabilistic approach. The practical part deals with a new approach called as partially collective mapping whose application leads to creation map in form of a set of simple geometrical entities which represents in piecewise manner a border between obstacles and free space.
|
|
|
People tracking in sparse crowd using multiple cameras
Zimmermann, Jan ; Suk, Tomáš (referee) ; Hlaváč, Václav (advisor)
In this thesis, we introduce a new algorithm for tracking of multiple people in image sequences from surveillance cameras. The algorithm handle with trustworthiness in similarity measure of human gures in images. All decisions are made as trustworthily as possible. The algorithm nds out the number of people in the scene autonomously. It deals with potential temporary occlusions of people in image. The tracking algorithm does not suffer from the problem of human model initialization as some other methods do. The implementation of our algorithm is a part of this thesis. This implementation has veri ed the characteristics of the algorithm. We have used two different methods for the image segmentation. Both method prove successful in different conditions. We have used a color information to compare the visual similarity. Suitable future extensions are suggested at the end of this thesis.
|
|
|
Online and Offline Vocabulary Correction while using a Digital Pen
Shrestha, Prajol ; Hlaváč, Václav (advisor) ; Průša, Daniel (referee)
This thesis is a requirement for the completion of my double degree with Charles University and University of Nancy (France) under the Erasmus Mundus masters program in Language and Communication Technology. The topic was provided by Prof. Abdel BelaÄd along with Actimage Company and has been completed and successfully defended at University of Nancy under their supervision. After the defense in France, I came here to Prague and worked with my co-supervisor Dr. Václav Hlaváč to improve the text of the thesis to meet the standards of Charles University in order to defend it in Prague. The aim of this work is to study some helpful handwriting correction marks and propose a system that automatically incorporates the corrections made by the writer while writing with a digital pen. The problem is complex because the corrections have to be at the same time readable by the writer and by the machine. Even detecting a free řowing line of handwritten text has not been understood completely by machines. The spatial relations between the correction marks and the text line are easily detected by the writers and readers and hence systematic to them, yet for machines this detection is a huge challenge. Humans have an intelligence that is hard to mimic by machines. This seemingly systematic writing has not been studied in...
|
|
|
Unsupervised learning based on images
Krupička, Radim ; Forst, Libor (referee) ; Hlaváč, Václav (advisor)
The aim of the project was to create an experimental environment for solving the children puzzle shape sorter . This environment serve as a testbed for various learning tasks of cognitive nature with image feedback. This puzzle is a demonstrator of the EU project COSPAL, IST-004176. The industrial robot CRS A-465 with six degrees of freedom and its control system is used. The scene is observed by one static camera. The system processes the images from the camera and the further robot movement is based on the reinforcement learning.
|
|
|
Control of the industrial robot with cameras
Janda, Pavel ; Obdržálek, David (referee) ; Hlaváč, Václav (advisor)
This thesis belongs to the implementation category of diploma theses. The work contributes to the EC project COSPAL, IST-2003-004176. The main goal of the project was the creation of the system of control and processing of the camera information for the assembly task. The demonstrator is used within the scope of the COSPAL project to solve a child's game - shape sorter puzzle. For solving the puzzle, the industrial robot CRS Robotics A465 was used. The robot has been available at the supervisor's place.
|
guest ::
RSS feed.