National Repository of Grey Literature 13 records found  1 - 10next  jump to record: Search took 0.01 seconds. 
Clean photo out of corrupted videosequence
Berky, Martin ; Záviška, Pavel (referee) ; Rajmic, Pavel (advisor)
This diploma thesis deals with separation of moving objects from static unchanging background in video sequence. Thesis contains description of common method of separation and approach based sparse signal representation. In the practical part of thesis, there were created video sequences, which are used to verify designed algorithm implemented in Matlab interface, disegned to obtain separated background from damaged video frames.
The Database of Moving Objects
Vališ, Jaroslav ; Chmelař, Petr (referee) ; Zendulka, Jaroslav (advisor)
This work treats the representation of moving objects and operations over these objects. Intro­duces the support for spatio-temporal data in Oracle Database 10g and presents two designs of moving objects database structure. Upon these designs a database was implemented using the user-defined data types. Sample application provides a graphical output of stored spatial data and allows us to call an implemented spatio-temporal operations. Finally, an evaluation of achieved results is done and possible extensions of project are discussed.
Separation of background and moving objects in videosequence
Komůrková, Lucia ; Veselý, Vítězslav (referee) ; Rajmic, Pavel (advisor)
This diploma thesis deals with separation of backgroud and moving objects in video. Video can be represented as series of frames and each frame represented as low - rank structure - matrix. This thesis describe sparse representation of signals and robust principal component analysis. It also presents and implements algorithms - models for reconstruction of real video.
Clean photo out of corrupted videosequence
Berky, Martin ; Záviška, Pavel (referee) ; Rajmic, Pavel (advisor)
This diploma thesis deals with separation of moving objects from static unchanging background in video sequence. In this thesis are described common method of separation and access using sparse signal representation. In the practical part of thesis was created video sequences, on which is verified the designed algorithm, implemented in Matlab, for obtaining background from damaged video frames and comparing this methods.
Querying Spatio-Temporal Data of Moving Objects
Dvořáček, Ondřej ; Kolář, Dušan (referee) ; Zendulka, Jaroslav (advisor)
This master's thesis is devoted to the studies of possibilities, which can be used for representation of moving objects data and for querying such spatio-temporal data. It also shows results of the master's thesis created by Ing. Jaroslav Vališ, that should be used for the solution of this master's thesis. But based on the theoretical grounds defined at the beginning of this work was designed and implemented new database extension for saving and querying spatio-temporal data. Special usage of this extension is demonstrated in an example application. This application uses the database extension for the implementation of its own database functions that are domain specific. At the conclusion, there are presented ways of the farther development of this database extension and the results of this master's thesis are there set into the context of the following project, doctoral thesis "Moving objects database".
Separation of background and moving objects in videosequence
Komůrková, Lucia ; Veselý, Vítězslav (referee) ; Rajmic, Pavel (advisor)
This diploma thesis deals with separation of backgroud and moving objects in video. Video can be represented as series of frames and each frame represented as low - rank structure - matrix. This thesis describe sparse representation of signals and robust principal component analysis. It also presents and implements algorithms - models for reconstruction of real video.
Clean photo out of corrupted videosequence
Berky, Martin ; Záviška, Pavel (referee) ; Rajmic, Pavel (advisor)
This diploma thesis deals with separation of moving objects from static unchanging background in video sequence. Thesis contains description of common method of separation and approach based sparse signal representation. In the practical part of thesis, there were created video sequences, which are used to verify designed algorithm implemented in Matlab interface, disegned to obtain separated background from damaged video frames.
Clean photo out of corrupted videosequence
Berky, Martin ; Záviška, Pavel (referee) ; Rajmic, Pavel (advisor)
This diploma thesis deals with separation of moving objects from static unchanging background in video sequence. In this thesis are described common method of separation and access using sparse signal representation. In the practical part of thesis was created video sequences, on which is verified the designed algorithm, implemented in Matlab, for obtaining background from damaged video frames and comparing this methods.
Separation of background and moving objects in videosequence
Komůrková, Lucia ; Veselý, Vítězslav (referee) ; Rajmic, Pavel (advisor)
This diploma thesis deals with separation of backgroud and moving objects in video. Video can be represented as series of frames and each frame represented as low - rank structure - matrix. This thesis describe sparse representation of signals and robust principal component analysis. It also presents and implements algorithms - models for reconstruction of real video.
Separation of background and moving objects in videosequence
Martincová, Lucia ; Veselý, Vítězslav (referee) ; Rajmic, Pavel (advisor)
This diploma thesis deals with separation of backgroud and moving objects in video. Video can be represented as series of frames and each frame represented as low - rank structure - matrix. This thesis describe sparse representation of signals and robust principal component analysis. It also presents and implements algorithms - models for reconstruction of real video.

National Repository of Grey Literature : 13 records found   1 - 10next  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.