|
|
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.
|
|
|
Recognition of Pieces on Chessboard from Photography on Mobile Device
Tábi, Roman ; Polok, Lukáš (referee) ; Sochor, Jakub (advisor)
The aim of this bachelor thesis is a mobile application for Android platform, which recognises chessboard pieces from photography of the chessboard. Application uses photography from gallery and determine the content of every single chessboard cell, thus if it contains black or white piece, or if it is empty. The task is solved in two stages. First is the detection of chessboard lines to determine the position of chessboard cells, second is the detection of chessboard pieces. The result of this thesis is working Android application.
|
|
|
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.
|
|
|
Recognition of Pieces on Chessboard from Photography on Mobile Device
Tábi, Roman ; Polok, Lukáš (referee) ; Sochor, Jakub (advisor)
The aim of this bachelor thesis is a mobile application for Android platform, which recognises chessboard pieces from photography of the chessboard. Application uses photography from gallery and determine the content of every single chessboard cell, thus if it contains black or white piece, or if it is empty. The task is solved in two stages. First is the detection of chessboard lines to determine the position of chessboard cells, second is the detection of chessboard pieces. The result of this thesis is working Android application.
|
guest ::
