|
|
Moving Persons Surveillance System
Hochman, Zdeněk ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This thesis is devoted to detect moving person in video sequence. It is dealed with detect motion primarily and it is determinated by place of motion. The thesis introduces relatively new method of detection motion Local Binary Patterns, which allow quick and exact detect of motion. Inhere of this thesis is also application for detect person. The thesis publishes tests of this application detailed and it mentiones positives and negatives of different settings application which reader can finally use at work with application.
|
|
|
Motion Detection in Video Sequences
Jelínek, Tomáš ; Herout, Adam (referee) ; Španěl, Michal (advisor)
This thesis is dedicated to techniques for motion detection in video sequences. There is summary of several possible approaches to solve this matter in theoretical and practical point of view. Principles of motion detection based on difference between frames are discussed in details. Great attention is made for image description by new method Local Binary Patterns which allows creating of incredibly fast and accurate motion detector. Vital part of this thesis is application for monitoring and testing motion algorithms on video sequences in different environments. Results of measuring enables to determine best approaches for concrete place and reader might find it useful in case of designing his own motion detectors.
|
|
|
Moving Objects Detection in Video Sequences
Musil, Jakub ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This publication is dedicated to creating appliaction for motion detection in video sequence. There is summary of several possible methods to solve this matter in theoretical and practical point of view with postive and negative properties. This methods are histograms subtraction and subtraction of each pixel in the tested frame. Fundamental part of this publication is application for motion detection. There are many of tests for created detector for several type moving object included in input video sequence. Results are intimately describe.
|
|
|
Texture Characteristics
Zahradnik, Roman ; Šiler, Ondřej (referee) ; Švub, Miroslav (advisor)
Aim of this project is to evaluate effectivity of various texture features within the context of image processing, particulary the task of texture recognition and classification. My work focuses on comparing and discussion of usage and efficiency of texture features based on local binary patterns and co- ccurence matrices. As classification algorithm is concerned, cluster analysis was choosen.
|
|
|
Detecting Objects in Images
Kubínek, Jiří ; Beran, Vítězslav (referee) ; Hradiš, Michal (advisor)
This work is dedicated to methods used for object detection in images. There is a summary of several approaches and algorithms to solve this matter, especially AdaBoost algorithm with its improvement, WaldBoost and several features used for object detection. Vital part of this work is dedicated to extending training datasets for classifier training and extending the current object detection framework with histogram of gradients features implementation. Integral part of this work is analysis of results by experiments evaluation.
|
|
|
Gender Recognition from Photograph
Kałuża, Marian ; Beran, Vítězslav (referee) ; Herout, Adam (advisor)
This paper presents a multiresolution approach for gender recognition based on Histogram of Oriented Gradients and Local Binary Patterns. The experiment showed that gender recog- nition accuracy can be improved not only by aquiring different features on the same image resolution but even by gathering just a single feature at different image scales. The pre- sented approach is quite competitive with above 95% accuracy in both evaluated datasets.
|
|
|
Copy Detection
Kletzander, Martin ; Zemčík, Pavel (referee) ; Hradiš, Michal (advisor)
This thesis describes content-search methods. Chosen method is applied on finding similar images and video frames. Thesis also qualifies methods used for acceleration of this search. Methods \ are then evauated and their results discussed. Proposal of commonly used enhancements for these methods is made.
|
|
|
Exploitation of Graphics Processor as Accelerator - OpenCL Technology
Hrubý, Michal ; Jošth, Radovan (referee) ; Zemčík, Pavel (advisor)
This work deals with the OpenCL technology and its use for the task of object detection. The introduction is devoted to description of OpenCL fundamentals, as well as basic theory of object detection. Next chapter of the work is analysis, with design proposal which takes into consideration the possibilities of OpenCL. Further, there's description of implementation of detection application and experimental evaluation of detector's performance. The last chapter summarizes the achieved results.
|
|
|
Texture Features Evaluation
Průša, Petr ; Hradiš, Michal (referee) ; Šiler, Ondřej (advisor)
The bachelor's thesis deals with statistical description of textures by methods LBP and co-occurence matrix. The co-occurence matrix is evalueted by Haralick's texture features. The implementation is in C++ language with using CImg.h library.
|
|
|
Texture-Based Object Recognition
Hutárek, Jiří ; Šilhavá, Jana (referee) ; Španěl, Michal (advisor)
This thesis focuses on texture detection through the use of Local binary patterns (LBP). The LBP histogram extracted from the image is used as the texture feature and the image is classified by an artificial neural network. By using these methods, an universal texture detector is implemented, which is then specialized for the aerial image object recognition.
|
guest ::
