|
|
Hiding Moving Objects in Video Sequences
Dostál, Martin ; Zahrádka, Jiří (referee) ; Španěl, Michal (advisor)
Hiding moving objects in video sequences is an interesting topic in computer vision. In this thesis, a real-time single object tracking and removal method is proposed. An input video is assumed to be captured with static video camera. Motion detection is based on a background subtraction using Mixture of Gaussians as the representation of background. The object tracking is realized by a combination of blobs comparison and computation of optical flow using Lucas-Kanade method. Consequent object removal makes use of created background model.
|
|
|
Software for Traffic Monitoring
Tesař, Filip ; Zahrádka, Jiří (referee) ; Španěl, Michal (advisor)
This thesis deals with detection and tracking of moving objects in video sequences. The aim of this work is design and implementation of an application, which uses video sequence capturing car traffic to acquire statistical data about each vehicle, such as its speed estimate and determination of its lane. The proposed application uses background subtraction method 'Mixture of Gaussians' and enables monitoring of multiple locations at the same time using independent cameras. The output data are saved into database and users are allowed to display statistics in graphs through a simple web interface.
|
|
|
Extension of IP Cameras Control Library
Šeptun, Michal ; Rozman, Jaroslav (referee) ; Luža, Radim (advisor)
This thesis deals with the design and implementation of the extension of the existing library to control ip cameras, mainly by supporting the motion detection, multiple cameras motion synchronization and focus view at the specific point. There are also experiments performed on the speed of the system when changing the observed point of synchronized cameras.
|
|
|
Fire Detection in Images and Video
Poledník, Tomáš ; Juránková, Markéta (referee) ; Přibyl, Bronislav (advisor)
This bachelor's thesis deals with fire detection in image and video. Attention is paid to the existing methods and known approaches to fire detection. Based on the analysis of the described methods, a fire detector, monitoring the attributes of its colour and motion, is designed, implemented and tested. The implemented detector achieves true positive detection rate of up to 90%.
|
|
|
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.
|
|
|
Videocamera Based Security Guard for OS Linux
Valeš, Jan ; Herrman, Tomáš (referee) ; Škarvada, Jaroslav (advisor)
This thesis deals with the implementation of security guard software for OS Linux using an appropriate web camera. The main part of this application is process running in background using V4L application interface to communicate with web cam. Because this program uses dynamically loaded plug-ins for motion detection, it is very simple to change detection algorithm just by modifying configuration file. Application data can be saved as images or video files. Client application was created for online monitoring by user. It communicates with security guard software over network by TCP/IP protocol. Implemented application layer protocol allows simple client authentication and data encryption.
|
|
|
Hand Motion Recognition
Blaho, Juraj ; Beran, Vítězslav (referee) ; Hradiš, Michal (advisor)
The aim of this work is to design and implement a novel computer interface based on detection and tracking of a hand in an image from a single camera. The created interface doesn't require any special hardware and it is possible to use it on a common computer with standard web-camera. The implemented interface was used to create an application, which is able to synthesize keyboard and mouse input events and this way it is able to control existing programs without the need to change their source code. Another contribution of this work is a novel method of automatic data acquisition for training of hand detectors. By using this method it is possible to collect thousands of training examples in a few hours.
|
|
|
Theremin Simulation Using Leap Motion
Staurovský, Maroš ; Zahrádka, Jiří (referee) ; Najman, Pavel (advisor)
The goal of this thesis is the creation and implementation of application that simulates playing the theremin by using Leap Motion sensor and MIDI protocol. This sensor allows us to detect movement of hands and recognition of gestures in the monitored area. This is used in the aplication to simulate the same principle that is used for playing theremin. Unlike this instrument we are able to produce sound of different instruments which is accomplished by using MIDI. The Leap Motion sensor and MIDI protocol are detailed in the theoretical part of the thesis.
|
|
|
Person Identification for Surveillance
Hopjan, Tomáš ; Juránek, Roman (referee) ; Hradiš, Michal (advisor)
This project deals with camera system surveillance and identification of humans. Motion detection and identification methods are presented. The main issue is people tracking using multiple camera system. Identification of individuals is accomplished using processing of decomposed colors histograms. Based on the experiments benefits and problems are introduced.
|
|
| |
guest ::
