|
|
Mobile Robot Localization in Indoor Scenarios
Sýkora, Tomáš ; Brejcha, Jan (referee) ; Beran, Vítězslav (advisor)
The goal of this project was to create a software for an autonomous mobile robot capable of navigation in indoor scenarios and of detection and recognition of the objects on its way. An important condition that the final software had to meet was to find the cheapest solution possible. I achieved the given goal and its conditions using an open source software framework Robotic Operating System (ROS) and its tools. The final system is a set of ROS modules communicating with each other, using a single sensor as an input data stream and a small motor which is able to send information about its velocity and rotations to the control part of the system. This mobile robot can, without any significant problems, navigate through a mapped area while trying to find trained objects. Such a robot could be easily used (after adding specific mechanical parts) to help retired or disabled people, to cooperate with industry workers or in many other fields.
|
|
|
Detectors of image objects and their implementation
Gregor, Michal ; Kohoutek, Michal (referee) ; Kyselý, František (advisor)
Image processing puts more construction on various application areas these days. One of these days vision, which would use picture operations, is producing an autonomic car. It would manager traffic operations on its own. There is often quickly need to image processing for example in evolutions doctors´ or sattelites´ dates. The computer vision is science about digital image processing. This science tries simulate human eye by technical instrument. The man will get information source about surrounding world throught his eyes. It´s necessary connect up gain knowledge and experiences from surrounding world to evolution informations. In the same ways computer´s vision tries to solve the image processing too. This work described processes, which are used to detection 2D objects in the picture. The process of image recognition is engaged in several steps. First, the digital picture is put into the computer and than the picture preprocessing picture partitioning into objects and describe obtain objects follws. At least their classificattion follows. This work is engaged in these problems. The main task of this bachelor effort is evalution primary detector objects. In practically part there is implementation of application in Matlab program. This implementation detects objects in the picture. And makes it possible to test of designed detektor.
|
|
|
Rain Prediction Using Meteo-Radar
Gerych, Petr ; Hradiš, Michal (referee) ; Szőke, Igor (advisor)
This paper deal with the rain prediction in the short time interval. The static pictures from meteo-radar serves as input data. The principle of meteo-radar is explained. The possible methods of the object detection and registration, motion interpolation and extrapolation is described. The flood fill algorithm and Lagrange extrapolation is applied to rain prediction. Application is written in C++ language under OS Linux. The example of the software application results is included.
|
|
|
Mobile Robot Localization in Indoor Scenarios
Sýkora, Tomáš ; Brejcha, Jan (referee) ; Beran, Vítězslav (advisor)
The goal of this project was to create a software for an autonomous mobile robot capable of navigation in indoor scenarios and of detection and recognition of the objects on its way. An important condition that the final software had to meet was to find the cheapest solution possible. I achieved the given goal and its conditions using an open source software framework Robotic Operating System (ROS) and its tools. The final system is a set of ROS modules communicating with each other, using a single sensor as an input data stream and a small motor which is able to send information about its velocity and rotations to the control part of the system. This mobile robot can, without any significant problems, navigate through a mapped area while trying to find trained objects. Such a robot could be easily used (after adding specific mechanical parts) to help retired or disabled people, to cooperate with industry workers or in many other fields.
|
|
|
Rain Prediction Using Meteo-Radar
Gerych, Petr ; Hradiš, Michal (referee) ; Szőke, Igor (advisor)
This paper deal with the rain prediction in the short time interval. The static pictures from meteo-radar serves as input data. The principle of meteo-radar is explained. The possible methods of the object detection and registration, motion interpolation and extrapolation is described. The flood fill algorithm and Lagrange extrapolation is applied to rain prediction. Application is written in C++ language under OS Linux. The example of the software application results is included.
|
|
|
Detectors of image objects and their implementation
Gregor, Michal ; Kohoutek, Michal (referee) ; Kyselý, František (advisor)
Image processing puts more construction on various application areas these days. One of these days vision, which would use picture operations, is producing an autonomic car. It would manager traffic operations on its own. There is often quickly need to image processing for example in evolutions doctors´ or sattelites´ dates. The computer vision is science about digital image processing. This science tries simulate human eye by technical instrument. The man will get information source about surrounding world throught his eyes. It´s necessary connect up gain knowledge and experiences from surrounding world to evolution informations. In the same ways computer´s vision tries to solve the image processing too. This work described processes, which are used to detection 2D objects in the picture. The process of image recognition is engaged in several steps. First, the digital picture is put into the computer and than the picture preprocessing picture partitioning into objects and describe obtain objects follws. At least their classificattion follows. This work is engaged in these problems. The main task of this bachelor effort is evalution primary detector objects. In practically part there is implementation of application in Matlab program. This implementation detects objects in the picture. And makes it possible to test of designed detektor.
|
guest ::
