|
| |
|
|
The influence of first CNN layer initialization on training convergence
Krejsa, Jiří ; Věchet, Stanislav ; Chen, K.S.
During evaluation of convolution neural networks on the task of sign language single hand alphabet classification we have discovered that in small but not negligible number of cases the training of the network does not converge at all. This paper investigates the problem that we believe is independent of the application. While the true cause of training divergence was not discovered, we can offer the reader an easy solution from practical point of view – initialization of the first CNN layer using pretrained networks parameters.
|
|
|
Design and implementation of an automated robotic workplace for controlled plant cultivation
Kazda, Jan ; Adámek, Roman (referee) ; Věchet, Stanislav (advisor)
This bachelor thesis will deal with the design and implementation of a robotic workplace for controlled plant cultivation. This system will be operated by 4 robots. The communication between the robots will be provided through a Programmable Logic Automaton. Calibration processes will be developed for the robots to achieve the required working accuracy of the robot. In order to perform these calibrations, calibration marks will be created for the cassettes that house the petri dishes. The cassettes are described as carriers for the individual petri dishes. Finally, verification of the real functionality of the system will be addressed.
|
|
|
Application of NB-IoT technology
Cagáň, Juraj ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor)
The initial chapters of master’s thesis focus on NB-IoT technology and its alternatives within the field of Low-Power Wide-Area (LPWA) networks. The research is further enhanced by comparing various commercial IoT platforms, protocols, and wireless networks, that are intended for local communication between sensors and IoT devices. The subsequent section defines the goals of this project and presents the approach taken towards examining the given issue. Based on the research findings, the main parts of the technological demonstrator are outlined in greater detail. The practical section elucidates the selection of appropriate microcontrollers and sensor nodes, while also covers the design of a customized printed circuit board. Additionally, it describes the control algorithm at a higher level of abstraction. The thesis includes the design of communication for collecting sensory data through a commercial cloud platform, as well as the development of a simple user interface. Finally, the thesis concludes with practical testing of NB-IoT network parameters, followed by the implementation of a demonstrative application on a real system.
|
|
|
3D model registration with depth camera data
Boháč, Daniel ; Věchet, Stanislav (referee) ; Adámek, Roman (advisor)
Tato práce se zaměřuje na úlohu 3D rozpoznání objektu a odhadu jeho transformace na základě dat získaných z hloubkové kamery. Konkrétně jde o mračna bodů, přičemž jedinou referencí pro dané objekty jsou jejich 3D modely. Cílem práce je vybrat vhodný algoritmus na základě provedené rešerše, implementovat řešení využívající tento algoritmus, ověřit jeho funkčnost a identifikovat jeho limity. Práce představuje snadno použitelnou a rozšiřitelnou knihovnu napsanou v C++, která je dostupná také prostřednictvím Pythonu. Tato knihovna využívá postup identifikovaný během rešerše, který řeší danou úlohu pomocí globálních deskriptorů. Nakonec je řešení ověřeno na umělých i reálných datech.
|
|
|
Design of a simulation environment for testing the operation of autonomous vehicles
Šůstek, Jan ; Krejsa, Jiří (referee) ; Věchet, Stanislav (advisor)
This thesis deals with the design of simulation environment for testing autonomous vehicles. In the theoretical part, the search of available autonomous driving simulators was carried out. Furthermore, the tools commonly used in autonomous vehicles such as sensors or software modules were presented. In the practical part, the CARLA simulator was selected from the available solutions. Firstly, the installation of CARLA simulator is explained. Then, the simulation map was created by the Roadrunner to simulate a specific street in Brno. Afterwards, the work with the CARLA simulator is shown. Finally, the work with the CARLA simulator is evaluated and the concrete outputs of simulation are shown.
|
|
|
Autonomous vehicles driving simulation environments research
Žitňan, Michal ; Krejsa, Jiří (referee) ; Věchet, Stanislav (advisor)
This bachelor thesis focuses on an extensive search of simulation environments for autonomous vehicles. In the introductory section, the definition of AVs as well as the distribution of levels of autonomous driving is presented. This is followed by a description of the issues involved in simulating and testing AVs in the real world, with a focus on the use of simulators in this process. This is followed by the definition of criteria for comparing the 20 simulation environments investigated in this thesis, in terms of general information, environment, sensors and data labeling tools. The next chapters deals with a brief description of each simulation environment and other platforms involved in the AV development field, followed by a summary of the investigated information through tables. In the last section, two simulators are selected to describe the tasks required to implement an autonomous driving project in a simulator.
|
|
|
Autonomous vehicles lane detection using particle filters
Věchet, Stanislav ; Krejsa, Jiří ; Chen, K.S.
Lane detection belongs among many others crucial tasks which an autonomous vehicles traveling in urban roads need to take care of. We present a lane detection method which uses particle filters combined with visual information from onboard camera to control the vehicles direction. Our initial experiments shows promising results as applied and tested in urban roads with focus on real-time data processing.
|
|
|
Mobile Robot in the Elevator: What Floor Am i On?
Krejsa, Jiří ; Věchet, Stanislav ; Chen, K.S. ; Havelka, M. ; Černil, M.
Wheeled mobile robots in multiple stories buildings have to use elevator to access arbitrary floor of the building. To do so, the control system must be able to detect and access elevator controls and also determine on which floor the elevator stopped. The paper deals with the latter problem, using the fusion of relative floor change detected by onboard accelerometer and absolute floor number detected by the processing of elevator information screen panel image acquired by onboard camera. Bayesian filter is used for data fusion and convolution neural network for image processing. Field tests resulted in 97% correct detection.
|
|
|
Control system architecture for novel experimental microalgae photobioreactor Simbios
Věchet, Stanislav ; Krejsa, Jiří ; Chen, K. S.
Photo-bioreactors for growing biomass based on various microalgae cultures gains interests nowadays due to have possible positive impact to society because of the potential to serve as an atmospheric carbon dioxide removal (CDR) device, produce food or fuel. We present an overall architecture of a control system designed with focus to keep the photo-bioreactor alive for long term continuous operation without any human supervision needed. To test overall control system stability we design a custom build spiral photo-bioreactor (PBR) with novel hyperbolic shaped illuminated part. The shape of the illuminated part was design with the goal to increase the ratio of spiral part to volume due to the fact that the light is crucial for microalgae to grow. The control system was created from scratch while adopting reliable IoT sensors combined with highly reliable custom build embedded control system including a cloud data processing and storage. As a result we have scalable and reliable solution which is suitable for photo-bioreactors of various shapes and sizes to operate in fully autonomous mode without any human supervision needed.
|
guest ::
RSS feed.