|
|
Stereo Reconstruction with Deep Neural Networks
Letanec, Richard ; Herout, Adam (referee) ; Španěl, Michal (advisor)
The aim of this thesis is to design and train a neural network model capable of estimating a disparity map from a pair of images. It will then be possible to create a depth map and point cloud from the estimated disparity map. Such a process is called stereo reconstruction. Solving this task consists of two steps -- choosing a suitable dataset and choosing a suitable neural network architecture. In my work, I compared two neural network architectures that I trained on the DrivingStereo dataset, consisting of paired images photographed from the roof of a car, and retrained and evaluated on the KITTI 2015 dataset, consisting of images of the same type. As the first neural network architecture, I chose ES-Net, which uses an approach based on a sequence of residual blocks and convolutional layers. As the second architecture, I chose CREStereo, which uses an iterative approach based on recurrent layers to predict the disparity map. In all benchmark tests, the CREStereo architecture achieves better accuracy.
|
|
| |
|
|
Head pose estimation via stereoscopic reconstruction
Hříbková, Veronika ; Jakubíček, Roman (referee) ; Kolář, Radim (advisor)
The thesis deals with head pose estimation in stereo data. The theoretical part provides the basis for understanding the geometry of the camera, its parameters and the method of calibration. The following describes the principles of stereo analysis and creating of disparity maps. In the research section, the methods used for head pose modelling are presented and an analysis of selected published articles is given. In the course of the master’s thesis, a system of two cameras for stereoscopic acquisition of motion of the head was designed and several measurements were carried out. The obtained data was prepared for creation of disparity maps and further processing. Based on the detection of facial features, in particular the inner and outer corners of the eyes and corners of the mouth, and their correspondences, a simple geometric model in shape of triangle was created to illustrate the inclination of the facial plane in space. By computing the angle of inclination in three axes, the current head pose is obtained. Motion is modelled by tracking detected points during video sequences.
|
|
| |
|
|
Calculating disparity map from color stereo images
Kulíková, Barbora ; Nováček, Petr (referee) ; Klečka, Jan (advisor)
This bachelor’s thesis deals with a creation of the depth maps. The first chapter concerns with the physiology of a human space perception and the methods of displaying the 3D content which are the topics closely related to the depth map, its creation and practical usage. Subsequently, there is a chapter focused on the description of the used methods of the image processing. The fundamental theoretical chapter deals with the methods of computing the disparity and used principles. In the practical part of the thesis an application has been made with a user interface in the Matlab environment. The application enables the user to create the disparity maps through the local and global methods. The functionalism of the application and the implementation of the methods are experimentaly verified. An experiment comparing the methods and analyzing influence of the local method parameters on the quality of the depth map has been made. The last part of the thesis was to create a simple stereopicture database.
|
|
|
LIDAR and Stereocamera in Localization of Mobile Robots
Vyroubalová, Jana ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
LIDAR (2D) has been widely used for mapping, localization and navigation in mobile robotics. However, its usage is limited to simple environments. This problem can be solved by adding more sensors and processing these data together. This paper explores a method how measurements from a stereo camera and LIDAR are fused to dynamical mapping. An occupancy grid map from LIDAR data is used as prerequisite and extended by a 2D grid map from stereo camera. This approach is based on the ground plane estimation in disparity map acquired from the stereo vision. For the ground plane detection, RANSAC and Least Squares methods are used. After obstacles determination, 2D occupancy map is generated. The output of this method is 2D map as a fusion of complementary maps from LIDAR and camera. Experimental results obtained from RUDA robot and MIT Stata Center Data Set are good enough to determine that this method is a benefit, although my implementation is still a prototype. In this paper, we present the applied methods, analyze the results and discuss the modifications and possible extensions to get better results.
|
|
| |
|
|
3D scene reconstruction using passive camera strereo-pair
Fronc, Leoš ; Zatočilová, Aneta (referee) ; Hurník, Jakub (advisor)
This bachelor thesis presents an overview of current methods for the 3D reconstruction of the scene using a passive stereo camera. Two main approaches are described and compared in this thesis – the feature points triangulation and the disparity map. The following methods are described below and compared with their qualities. On the basis of this comparison, conclusions are drawn about the choice of suitable approaches and methods for specific applications. Finally, a simple example is created which illustrates the use of these methods in practice.
|
|
|
Disparity Map Estimation from Stereo Image
Tábi, Roman ; Maršík, Lukáš (referee) ; Španěl, Michal (advisor)
The master thesis focuses on disparity map estimation using convolutional neural network. It discusses the problem of using convolutional neural networks for image comparison and disparity computation from stereo image as well as existing approaches of solutions for given problem. It also proposes and implements system that consists of convolutional neural network that measures the similarity between two image patches, and filtering and smoothing methods to improve the result disparity map. Experiments and results show, that the most quality disparity maps are computed using CNN on input patches with the size of 9x9 pixels combined with matching cost agregation and correction algorithm and bilateral filter.
|
|
|
Design of a New Method for Stereovision
Kopečný, Josef ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
This thesis covers with the problems of photogrammetry. It describes the instruments, theoretical background and procedures of acquiring, preprocessing, segmentation of input images and of the depth map calculating. The main content of this thesis is the description of the new method of stereovision. Its algorithm, implementation and evaluation of experiments. The covered method belongs to correlation based methods. The main emphasis lies in the segmentation, which supports the depth map calculation.
|
guest ::
