|
|
Camera Based Object Tracking
Psota, Michal ; Orság, Filip (referee) ; Rozman, Jaroslav (advisor)
This work focuses on theoretical description, proposal and implementation of a program for coloured object tracking by a robot. Picture processing uses wrapper of OpenCV library - EmguCV. The application communicates with the robot and guides it to track a specified coloured object. The program is implemented in C# language.
|
|
|
Online interest point detector
Přibyl, Jakub ; Rajnoha, Martin (referee) ; Mašek, Jan (advisor)
This thesis focuses on online learning detector for long-term tracking of object in video sequence. The object is defined by a bounding box. The text describes different parts of the detector: object tracking, object detection and online learning detector. The main contribution of this work is creating extension of the OpenTLD program for parallel detection and tracking of multiple objects. The parallelization is then compared on two practical examples and the processor's impact on detection is compared. The best results were achieved with parallelization, where all objects were detected. The most accurate detection was in the case of sufficiently learned objects with the smallest shape change.
|
|
|
Object Detection and Tracking Using Interest Points
Bílý, Vojtěch ; Hradiš, Michal (referee) ; Juránek, Roman (advisor)
This paper deals with object detection and tracking using iterest points. Existing approaches are described here. Inovated method based on Generalized Hough transform and iterative Hough-space searching is proposed in this paper. Generality of proposed detector is shown in various types of objects. Object tracking is designed as frame by frame detection.
|
|
|
Automated object tracking using robotic manipulator
Zelený, Miroslav ; Ligocki, Adam (referee) ; Chromý, Adam (advisor)
This diploma thesis deals with the tracking of objects using a robotic manipulator Epson C3 and a color camera. The work describes the basic qualities of the device to be used. The OpenCV library and its wrapper EmguCV are used as software tools for computer vision. It discusses the basic issues and principles of tracking objects in the image and introduces some methods of tracking. These methods have been tested and therefore their strengths and weaknesses, which appeared during testing, are listed here. Furthermore, there is a procedure for calculating the new coordinates of the camera and the manipulator effector using homogeneous transformations. The work contains the results of testing the algorithms and their evaluation. The output of the work is a test application for the Epson C3 robot.
|
|
|
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.
|
|
|
Real-Time Object Tracking in Video
Šimon, Martin ; Beran, Vítězslav (referee) ; Rozman, Jaroslav (advisor)
This thesis focuses on real-time visual object tracking with emphasis on problems caused by a long-term tracking task. Among theses problems belong primarily an occlusion problem, both the partial and the full one, and appearance changes of the object during the tracking. The work is also concerned with tracking objects of a very limited size and unsteady camera movements. These two particular problems are relatively common when tracking distant objects. A part of this work is also a summary of related work and a proposal of a system with high qualitative stability and robustness to problems mentioned. The proposed system was implemented and the evaluation demonstrated that it is capable of solving these problems partially.
|
|
|
Object Tracking in Panoramic Video
Ambrož, Vít ; Hradiš, Michal (referee) ; Čadík, Martin (advisor)
The master thesis maps the state of the art of visual object tracking in panoramic 360° video. The thesis aims to reveal the main problems related to visual object tracking and moreover focuses on their solution in panoramic videos. In the study of the existing approaches was found that very few solutions of visual object tracking in equirectangular projection of panoramic video have been implemented so far. This thesis therefore presents two improvements of object tracking methods that are based on the adaptation of equirectangular frames. In addition, this thesis brings the manually created dataset of panoramic videos with more than 9900 annotations. Finally the detailed evaluation of 12 well known and state of the art trackers has been performed for this new dataset.
|
|
|
Multimodal System for Multi-Object Tracking in Real-Time
Kučera, Adam ; Šátek, Václav (referee) ; Rozman, Jaroslav (advisor)
This thesis deals with the topic of multi-object multi-sensor tracking. A conventional track-oriented multiple hypothesis tracking (TOMHT) pipeline is implemented in C++ programming language and an implementable interface is designed, enabling to easily extend the core algorithm with arbitrary sensors and measured target attributes, making the system multimodal, i.e.\ applicable in heterogeneous systems of sensors. A novel algorithm for solving combinatorial optimization arising in TOMHT is proposed. Finally, few example implementations of the interface are provided and the system is evaluated in simulated and real-world scenarios.
|
|
|
Moving Object Detection in Video
Buchtela, Radim ; Ševcovic, Jiří (referee) ; Herout, Adam (advisor)
This thesis is devoted to detection of moving object in video sequence. In this thesis are described in detail detection methods based on principle of Background subtraction. There are indtroduced strategies of background modeling and background model updating. This thesis deal also with problems of tracking objects in video, there is introduced one of possible approaches. Part of this thesis is application for function demonstration of detection methods and tracking method. On results are showed main advantages and disadvantages of implemented methods.
|
|
|
Web Application for Inspecting Results of Automatic Video Processing and Manual Annotations
Červíček, Petr ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The thesis pursues the implementation of the web application for obtaining valuable data for anotation. Data are mainly collected from videos and images, but they can be obtained from deepfakes images and gifs as well. The YOLO - You Only Look Once is used for object detection in the videos. Whole application is developed in node.js and react. Node.js for backend and react for frontend. For a better understanding of web application, there is also historical description of the web technologies.
|
guest ::
