|
|
Use of Mobile Device Sensors in a Car
Aron, Lukáš ; Široký, Vít (referee) ; Žák, Pavel (advisor)
This thesis analyses the use of an accelerometer commonly present in a mobile device for the measuring of vibration in a vehicle. Such measurements are used to map the quality of the road surface. The signal from the accelerometer and the current travelling speed of the vehicle are evaluated according to a threshold function. This function allows for a determination of whether the signal reported by the device signifies a pot-hole or another type of defect on the road surface. If the defect is determined to pose a threat to a vehicle travelling at higher speeds, then this fact is saved into the memory of the device. The second part of this thesis deals with the design of an internet and a mobile application, which is able to collect all measured data processes using cluster analysis and then shares the results with other participating devices. Tha practical results is that a map of road surface defect is thus created, which is then displayed to road users. This thesis deals with theory of mobile device sensors, including signal processing, as well as the design creation of the internet and mobile application.
|
|
|
Recognizing Faces within Image
Svoboda, Pavel ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
The essence of face recognition within the image is generally computer vision, which provides methods and algorithms for the implementation. Some of them are described just in this work. Whole process is split in to three main phases. These are detection, aligning of detected faces and finally its recognition. Algorithms which are used to applied in given issue and which are still in progress from todays view are mentioned in every phase. Implementation is build up on three main algorithms, AdaBoost to obtain the classifier for detection, method of aligning face by principal features and method of Eigenfaces for recognizing. There are theoretically described except already mentioned algorithms neural networks for detection, ASM - Active Shape Models algorithm for aligning and AAM - Active Appearance Model for recognition. In the end there are tables of data retrieved by implemented system, which evaluated the main implementation.
|
|
|
Neural Network Based Edge Detection
Janda, Miloš ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
Aim of this thesis is description of neural network based edge detection methods that are substitute for classic methods of detection using edge operators. First chapters generally discussed the issues of image processing, edge detection and neural networks. The objective of the main part is to show process of generating synthetic images, extracting training datasets and discussing variants of suitable topologies of neural networks for purpose of edge detection. The last part of the thesis is dedicated to evaluating and measuring accuracy values of neural network.
|
|
|
3D Monitor Based on Head Pose Detection
Zivčák, Jan ; Žák, Pavel (referee) ; Beran, Vítězslav (advisor)
With the development of posibilities of image processing, stereoscopy, prices of web cameras and power of computers an opportunity to multiply an experience with working with 3D programs showed. From the picture from webcamera an estimation of a pose of user's head can be made. According to this pose a view on 3D scene can be changed. Then, when user moves his head, he will have a feeling as if monitor was a window through which one can see the scene behind. With the system which is the result of this project it will be possible to easily and cheaply add this kind of behaviour to any 3D application.
|
|
|
Neural Network Based Image Segmentation
Vrábelová, Pavla ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
This paper deals with application of neural networks in image segmentation. First part is an introduction to image processing and neural networks, second part describes an implementation of segmentation system and presents results of experiments. The segmentation system enables to use different types of classifiers, various image features extraction and also to evaluate the success of segmentation. Two classifiers were created - a neural network (self-organizing map) and an algorithm K-means. Colour (RGB and HSV) and texture features and their combinations were used for classification. Texture features were extracted using a set of Gabor filters. Experiments with designed classifiers and feature extractors were carried out and results were compared.
|
|
|
3D Application for Mobile Phones
Slavotínek, Tomáš ; Žák, Pavel (referee) ; Láník, Aleš (advisor)
This bachelor thesis deals with 3D graphics representation on Java ME platform. The general architecture of this platform is described first. Consideration is given to description of API interfaces JSR 184 and MascotCapsule. Practical part is about application implemented with usage of MascotCapsule interface - simple game based on 2D Dyna Blaster.
|
|
|
SMART CAR: Automatic Car Detection
Burkot, Martin ; Žák, Pavel (referee) ; Beran, Vítězslav (advisor)
This bachelor thesis deals with the detection of moving vehicles in image sequence. In the introduction is made a brief analysis of current methods for detecting the movement of vehicles and the scene in general. In subsequent chapters is designed and described the implementation of the detector moving vehicles in an image based on the determination of optical flow. At the end there review of proposed solution.
|
|
|
Rule-Based Melody Harmonization
Kuchár, Pavol ; Žák, Pavel (referee) ; Fapšo, Michal (advisor)
Bachelor thesis deals with the issue of computer aided composition. The aim of the thesis was to create the program, which implements several rules of music theory and using of CSP determines appropriate tones for harmonization of melody. The result is presented in score and MIDI file.
|
|
|
Android vs Bada
Obořil, Radek ; Bartoň, Radek (referee) ; Žák, Pavel (advisor)
This thesis deals with comparison of two mobile device platforms Samsung bada and Google Android, primarily from a point of view of native application development. Native applications features, graphics and media support as well as developer tools are compared. As a part of this thesis, an application was created - a variety of a classic Snake game. This text describes design of this application, differences in the implementation, and discusses possibilities of application porting between the platforms.
|
|
|
Optical Character Recognition
Bílek, Jan ; Žák, Pavel (referee) ; Zuzaňák, Jiří (advisor)
This work describes problems of optical character recognition and methods which are used to improve its results. It specializes in problems of image spam and its adjustment for its recognition. This work describes methods of processing an image which leads to better results of text recognition and also some methods used to the character recognition. There is also described a scheme and an implementation of a system which processes an image spam and detects a text within it.
|
guest ::
RSS feed.