|
|
Steps Towards Improvements of Computer Vision Methods for Traffic Analysis
Špaňhel, Jakub ; Sablatnig, Robert (referee) ; Šikudová, Elena (referee) ; Herout, Adam (advisor)
Rostoucí urbanizace a zvyšující se počet vozidel na silnicích přetěžují tradiční systémy řízení dopravy na hranici jejich možností. Řešení nabízejí inteligentní dopravní systémy (ITS), které využívají pokročilé technologie ke zvýšení plynulosti a bezpečnosti dopravy. Zásadní oblastí, kterou je třeba zlepšit, však zůstává robustnost metod počítačového vidění v rámci ITS, které jsou nezbytné pro analýzu dopravy. Tato práce přispívá k této oblasti, konkrétně se zaměřuje na přesné (fine-grained) rozpoznávání vozidel, reidentifikaci vozidel, rozpoznávání registračních značek a monokulární měření rychlosti vozidel. Bylo představeno několik nových datových sad, vysoce ceněných výzkumnou komunitou, které rozšiřují hodnocení a zkoumání v každé z výše uvedených oblastí. Hlavní přínosy lze shrnout následovně: Nové technicky augmentace pro přesné rozpoznávání vozidel & rozšíření dříve publikované datové sady. Nová metoda agregace vizuálních znaků pro re-identifikaci vozidel & datová sada. Inovativní přístup k rozpoznávání registračních značek pomocí zarovnání registrační značky a holistického rozpoznávání & tři publikované datové sady. Největší datová sada pro měření rychlosti vozidel & stanovení výchozího vyhodnocení s dostupnými metodami vizuálního meření rychlosti. Klíčová zjištění této práce prokazují významné zvýšení přesnosti, účinnosti a robustnosti metod počítačového vidění aplikovaných na analýzu dopravy. Přínosy tohoto výzkumu byly oceněny na nejvýznamnějších konferencích a v časopisech v oblasti ITS a stanovují nové standardy pro budoucí práci. Tím, že tato práce posunula současný stav ITS a přispěla cennými zdroji pro probíhající výzkum, představuje zásadní krok směrem k udržitelnějším, efektivnějším a inteligentnějším dopravním systémům. Má důsledky pro řízení dopravy a širší společenský cíl vytvořit citlivější a přizpůsobivější městské prostředí.
|
|
|
Movement Analysis of Vehicles on Crossroads
Benček, Vladimír ; Juránek, Roman (referee) ; Sochor, Jakub (advisor)
This thesis proposes and implements a system for movement analysis of vehicles on crossroads. It detects and tracks the movement of vehicles in the video, gained from the stationary video camera, which has the view of some crossroad. The trajectories are stored and their number and directions are analysed. The detection was made using cascade classifier. A dataset of 10500 positive and 10500 negative samples has been created to train the classifier. Vehicles are tracked using KCF method. For trajectory clustering, needed by analysis, the Mean Shift method is used. Testing showed, that the overall success of vehicle movement analysis is 92.77%.
|
|
|
Image Segmentation with Deep Neural Network
Pazderka, Radek ; Šůstek, Martin (referee) ; Rozman, Jaroslav (advisor)
This master's thesis is focused on segmentation of the scene from traffic environment. The solution to this problem is segmentation neural networks, which enables classification of every pixel in the image. In this thesis is created segmentation neural network, that has reached better results than present state-of-the-art architectures. This work is also focused on the segmentation of the top view of the road, as there are no freely available annotated datasets. For this purpose, there was created automatic tool for generation of synthetic datasets by using PC game Grand Theft Auto V. The work compares the networks, that have been trained solely on synthetic data and the networks that have been trained on both real and synthetic data. Experiments prove, that the synthetic data can be used for segmentation of the data from the real environment. There has been implemented a system, that enables work with segmentation neural networks.
|
|
|
Potential calculation of mutual information from a time series
Hubr, Ivo ; Smékal, Zdeněk (referee) ; Mekyska, Jiří (advisor)
Mutual information is one of the factors used in traffic analysis and preparation phase space. Begin of this work deal with information theory, focusing on the calculation of mutual information. To calculate this parameter has been available for many algorithms which are analyzing in this final work. Two of the algorithms (Fraser-Swinney and calculation of mutual information using adaptive XY subdivision) are applied to the input data Rössler’ attractor, as shown in the output tables and graphs. The third consideration method is the computational Dinh-Tuan-Pham algorithm. The main goal of this work is a comparison of efficiency, speed and accuracy of the calculation of these algorithms.
|
|
|
Analysis and solution of transport in Znojmo
Kovaříková, Ilona ; Radimský, Michal (referee) ; Matuszková, Radka (advisor)
The thesis focuses on the traffic situation in the district town of Znojmo in the South Moravian Region. The thesis deals with individual traffic modes, especially road traffic and cycling, but also with static traffic (traffic at rest), where parking and optimization design is addressed. The thesis also marginally deals with rail and bus public transport. The first part of the thesis is devoted to the existing state of the individual modes of transport in the entire cadastral area of Znojmo, but since the cadastral area of Znojmo also includes transport in the extravilan, the thesis is mainly focused on transport in the intravilan. The traffic load according to the National Traffic Census of the Regional Directorate of Transport and the degree of motorization from the databases of the Road Vehicle Register of the Ministry of Transport are analysed. In the second part of the thesis, selected problem spots in Znojmo are addressed, and measures for improving the comfort and safety of road users are proposed. Furthermore, parking is addressed, where the city was divided into areas according to functional use and the shortcomings were found and then the optimal solution was proposed.
|
|
|
Synthetic Dataset Generator for Traffic Analysis
Svoreň, Ondrej ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This bachelor thesis deals with the creation and customization of synthetic dataset genera tor for traffic analysis. It focuses on traffic analysis by means of computer vision, methods and conditions of creating the generator of synthetic dataset, possible application of achie ved results in machine learning and additional development opportunities. Using available automobile photographs from the Czech Republic, Slovakia, Poland and Hungary, a synthe tic license plate number generator was created, which, after graphical adjustment and after joining with the vehicle photographs creates the resulting dataset for machine learning. The solution itself is divided into the three scripts written in Python using the OpenCV library. The resulting dataset serves as an input for the machine learning system to re-identify the license plate numbers from photographs captured in the flow of traffic.
|
|
|
Modification of the intersection of Palackého and Krátká streets in Holešov
Dlhopolček, Michal ; Patočka, Miroslav (referee) ; Smělý, Martin (advisor)
The subject of this bachelor study is to design renovation of a T intersection of roads II/432 and II/438 in city Holešov. The intersection is on the west side of the city Holešov, which is located twenty kilometers north from regional city Zlín. Solution of the intersection are not convenient, especially for trucks connecting from street Krátká to center of city Holešov. Which creates traffic jams long around 175 m and reach near rail crossing, thereby creating an additional traffic risk. From three variations, was choosen one that fulfils all requests, like smoother conection to intersection, safety ride in roundabout. Increasing the capacity and ensuring sufficient quality of the intersection from the side way and even the main roads.
|
|
|
Malware Detection Using DNS Traffic Analysis
Daniš, Daniel ; Ovšonka, Daniel (referee) ; Kováčik, Michal (advisor)
This master thesis deals with the design and implementation of a tool for malware detection using DNS traffic analysis. Text of the thesis is divided into theoretical and practical part. In theoretical part the reader will be acknowledged with the domain of malware and botnet detection. Consequently, various options and methods of malware detection will be described. Practical part of the thesis contains description of malware detection tool architecture as well as key aspects of its implementation. Moreover, the emphasis is being placed on testing and experiments. The result of the thesis is a tool, written in python, for malware detection using DNS traffic analysis, that uses a combination of several methods of detection.
|
|
|
Synthetic Data Set Generator for Traffic Analysis
Šlosár, Peter ; Juránková, Markéta (referee) ; Herout, Adam (advisor)
This Master's thesis deals with the design and development of tools for generating a synthetic dataset for traffic analysis purposes. The first part contains a brief introduction to the vehicle detection and rendering methods. Blender and the set of scripts are used to create highly customizable training images dataset and synthetic videos from a single photograph. Great care is taken to create very realistic output, that is suitable for further processing in field of traffic analysis. Produced images and videos are automatically richly annotated. Achieved results are tested by training a sample car detector and evaluated with real life testing data. Synthetic dataset outperforms real training datasets in this comparison of the detection rate. Computational demands of the tools are evaluated as well. The final part sums up the contribution of this thesis and outlines some extensions of the tools for the future.
|
|
|
Optimalization of Web Pages and Strategy of Selling
Úradníček, Lukáš ; Měřička, Radim (referee) ; Koch, Miloš (advisor)
The thesis deals with the optimization of website of thai massage studio. This work includes evaluation of the initial state, a proposed amendment, keyword analysis, optimization of texts and support through building backlinks. Evaluation of success is done through the analysis of traffic and tracking the position of the primary keywords on major search engines in the Czech Republic - Google.cz and Seznam.cz.
|
guest ::
