|
Crowd Counting in Video
Kuřátko, Jiří ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This master's thesis prepared the programme which is able to follow the trajectories of the movement of people and based on this to create various statistics. In practice it is an effective marketing tool which can be used for instance for customer flow analyses, optimal evaluation of opening hours, visitor traffic analyses and for a lot of other benefits. Histograms of oriented gradients, SVM classificator and optical flow monitoring were used to solve this problem. The method of multiple hypothesis tracking was selected for the association data. The system's quality was evaluated from the video footage of the street with the large concentration of pedestrians and from the school's camera system, where the movement in the corridor was monitored and the number of people counted.
|
|
Deep Neural Networks for Classifying Objects in an Image
Mlynarič, Tomáš ; Zemčík, Pavel (referee) ; Hradiš, Michal (advisor)
This paper deals with classifying objects using deep neural networks. Whole scene segmentation was used as main algorithm for the classification purpose which works with video sequences and obtains information between two video frames. Optical flow was used for getting information from the video frames, based on which features maps of a~neural network are warped. Two neural network architectures were adjusted to work with videos and experimented with. Results of the experiments show, that using videos for image segmentation improves accuracy (IoU) compared to the same architecture working with images.
|
|
Optical measurement system
Opravil, Jan ; Horák, Karel (referee) ; Richter, Miloslav (advisor)
This diploma thesis deals with the creation and testing of optical measurement system. There are basic parts of computer vision. Some ways of image preprocessing and templates matching are discussed. Everything is directed to a particular practical task. Selected methods for templates matching are the Correlation Method, the Classical and Hybrid Hausdorff Distance, Radial and Circular Sampling Space. These methods are programmed in C++ and they are compared with function for searching templates from specific library.
|
|
Visual head motion monitoring
Sieber, Lukáš ; Babinec, Tomáš (referee) ; Richter, Miloslav (advisor)
This bachelor thesis is based on finding of head rotation and position against stationary shoulders from frames captured by web camera in real time. Furthermore the thesis adverts to benefits of using Open CV. It is also included some Open CV function overview, such as optical flow, 3D-2D points corresponding calculation and among others operations with rotation matrix. The end of this thesis provides outcomes evaluation and future work proposals.
|
|
Fast Re-Calibration of PTZ Camera for Traffic Analysis
Dřevo, Aleš ; Juránek, Roman (referee) ; Sochor, Jakub (advisor)
This thesis deals with problematics of PTZ-camera re-calibration during movement. The objective of this work is to keep the camera in calibration mode from default status when the known positions of Vanishing Points are in the image. With their use during movement, which is changing with motion of the camera, their positions are kept with help of two implemented methods. The first method is based on the principle of homography, the second on the principle of cross ratio. The results show that both of these methods work especially for keeping the positions of First Vanishing Points. In the case of the Second Vanishing Points there appear various problems and the results are often quite inaccurate.
|
|
Image Motion Detection
Zítka, Michal ; Richter, Miloslav (referee) ; Horák, Karel (advisor)
This bachelor project dissert on detection of motion in image. Also sumary basic methods for detection of motion in image and method of segmentation using active contour. In practical section is attention paid to detection of motion in video camera screenshots.
|
|
Image registration using Optical Flow method
Bistrý, Jan ; Provazník, Ivo (referee) ; Malínský, Miloš (advisor)
Registration of medical images is technique, which is developing with new hybrid diagnostic imaging systems. Nowadays is a trend in image registration focused on monomodality and multimodality images registration. The first part of this master’s thesis is intent on present basic information about image registration. Concretely is intending on image transformation, interpolation, criteria function and at optimalization. Further part present realized Optical Flow technique and used “Demon” algorithm for image registration. The next part is focused on presentation of program solution and GUI. In the last section of this master’s thesis is verifying of created program on usual images and real CT images.
|
|
moving objects tracking
Bradáč, František ; Gogol, František (referee) ; Richter, Miloslav (advisor)
The thesis deals with founding and tracking of moving objects inside of visual field and prediction of their future position. The created methods combine few approaches for solution this problem. First, the most probable of the static part of the observed scene is created. Then this model is used to detect moving objects. The correspondence of objects between two consecutive pictures is performed by analyzing of motion of these objects. For analyzing of motion of the objects optical flow is used. Prediction of the future position is performed by Kalman filter. Providing suitable condition these methods are able to track the moving objects even if these objects are passing closely or colliding. The methods are implemented in language C++ and their functionality was verified by sample with scanned non static scene.
|
|
Quadrocopter Navigation and Control
Doležal, Karel ; Orság, Filip (referee) ; Herman, David (advisor)
This paper focuses on autonomous navigation of AR.Drone quadrocopter in outdoor environment. The goal is to follow a specified route and land autonomously on a platform placed at the destination. Firstly, the AR.Drone platform, its development kit and sensor extension with GPS and a magnetic compass are described. Then, the navigation architecture of a control program is presented describing important blocks and its' individual tactics. Localization of the landing platform is based on its color. The video is also used to detect nearby obstacles using optical flow calculation suppressing the quadrocopter movements and to avoid the greater changes in the image. The control program implementation is then tested in real environment and the results are presented.
|
|
Browse the Map on Your Mobile Device by Moving the Device
Pohrebniak, Yehor ; Milet, Tomáš (referee) ; Beran, Vítězslav (advisor)
This thesis focuses on the creation of a mobile application that presents a map and based on the movement of a mobile device in space, represents a sliding map camera. The theoretical part is focused on acquaintance with available technologies and design of a system of data processing methods from inertial measuring units of mobile devices and video from the smartphone camera. The practical part is focused on the implementation of mobile application that obtain data from motion sensors and move the map.
|