|
|
Motion Detection in Video
Polanský, Petr ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
The objective of this work is evaluate motion detection using Gaussian Mixture Model. When algorithm detects motion, it creates short video capturing this motion and visualizing it properly. Visualization is made by white pixels intensity graph. System is applicable on less busy area when motion is more noticeable. Results of this work shows how surrounding environment and camera position influence detection.
|
|
|
Mobile Application Using Deep Convolutional Neural Networks
Poliak, Sebastián ; Herout, Adam (referee) ; Sochor, Jakub (advisor)
This thesis describes a process of creating a mobile application using deep convolutional neural networks. The process starts with proposal of the main idea, followed by product and technical design, implementation and evaluation. The thesis also explores the technical background of image recognition, and chooses the most suitable options for the purpose of the application. These are object detection and multi-label classification, which are both implemented, evaluated and compared. The resulting application tries to bring value from both user and technical point of view.
|
|
|
Panoramic Photo Creation
Dospiva, Filip ; Sochor, Jakub (referee) ; Behúň, Kamil (advisor)
This thesis contains a comparison of approaches to implementation of the panoramic photos. There are analyzed partial steps to create panoramas and access methods that are used for these steps. There is a preview of the methods and schedules their advantages and disadvantages. Also included is a comparison of these methods and evaluation of their usability.
|
|
|
Road Sign Detection from Camera in Car
Dušek, Jan ; Sochor, Jakub (referee) ; Beran, Vítězslav (advisor)
This bachelor's thesis is focused on detection of traffic signs from image or video. Algorithms common for object detection will be introduced in the beginning. Description of object detection using histogram of oriented gradients and support vector machines will follow. Last part will present accomplished results.
|
|
|
Tracker of Motorcycle Trips for iOS
Pinka, Martin ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
The aim of the thesis is to create an innovative mobile application that can be used for tracking of motorcycle trips on iOS platform.The benefits include the improvement of automatic pause detection mechanism, which ignores movements that user do not want to include in the trip.Additionally, the application provides a way to organize records which helps user to find specific recorded trip. This is solved by using tags that can be added to the records. The solution greatly improves the speed of finding specific routes if the user honestly fills information about trips. The implementation part of the thesis describes the drawing of a very long colored polyline on the map where colors represent speed of passing the places.As a result of all the effort there is an innovative, functional application that is ready for real usage.
|
|
|
Fast Detection of Traffic Signs in Image
Sochor, Jakub ; Španěl, Michal (referee) ; Herout, Adam (advisor)
This bachelor thesis focuses on detection of traffic signs in real-time. First of all, algorithms used for traffic signs detection will be presented. Description of approach used in this thesis based on shapes of traffic signs and modifications of this algorithm will follow. Evaluation of accomplished results with this algorithm will be also presented.
|
|
|
Vehicle Following Distance Estimation from Mobile Phone in Vehicle
Zemánek, Ondřej ; Špaňhel, Jakub (referee) ; Sochor, Jakub (advisor)
The aim of this bachelor thesis is to create a mobile application for Android that estimates the distance of vehicles based on vehicle size in the camera image of the mobile phone. The estimation of the following distance is evaluated based on known camera parameters, the average vehicle width and the size of image area that represents detected car. Vehicles and their licences plates are detected in the image using cascade classifiers. Licence plate is detected only in the area of the detected vehicle. A training dataset for cascade classifier was created as part of this work. The cascade classifier is designed for vehicle detection. This work is extended with feature that tracks following distance in time and warns you with an acoustic signal on sudden distances change. This thesis is divided into five main parts - comparison of existing solutions for distance estimation, review of object detection methods, application design, implementation and evaluation of detectors, distance evaluation.
|
|
|
Library for Multiplatform Development of Mobile Apps
Kovařík, Michal ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This thesis addresses the issues when developing mobile applications for multiple operating systems and development environments, with the target being to create the ideal user interface library. A framework for HTML app development has been designed and implemented that is built on top of modern web standards, allowing the developer to create applications with a single codebase that will, when deployed, intelligently adapt to the device and operating system that they are being run on. Released as an open-source project and currently supporting Windows 10, Android, Chrome OS and Web. Flexus, a framework for building user interfaces, is in live use and active development.
|
|
|
License Plate Detection and Recognition
Řepka, Michal ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This paper addresses the problem of object detection and recognition from still images using methods of computer vision. The objects of detection are czech license plates and the goal of this paper was to create an automatic license plate anotation tool. Suggested solution uses edge detection and machine learned cascading classifiers. Created application was then tested on dataset taken by the author.
|
|
|
Deep Learning for Facial Recognition in Video
Jeřábek, Vladimír ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This work deals with face recognition in video using neural networks. In the beginning, there is described the process of selection and verification of convolution neural network to generate feature vectors from images of different identities. In the next part, this work deals with the aggregation of feature vectors from video frames. Aggregation takes place through aggregation neural networks. At the end of this work, the results obtained by the aggregation methods are discussed.
|
guest ::
