National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Restoring and improving the technical quality of audio recordings using machine learning methods
Lechovský, Adam ; Peterek, Nino (advisor) ; Dušek, Ondřej (referee)
The goal of this thesis is to train an artificial neural network which will be able to improve the technical quality of audio recordings. To achieve this, three artificial audio distortions are used to train seven different deep neural networks on pairs of distorted and undistorted audio. The resulting 21 networks are then evaluated using a number of objective and subjective measures. In the end, the networks learned to remove artificial distortions very well, but they did not learn to improve the technical quality of undistorted inputs. 1
Visual tracking of multiple robots
Lechovský, Adam ; Barták, Roman (advisor) ; Obdržálek, David (referee)
The aim of this thesis is to create a program which detects a grid on a paper in a fixed webcam image, converts the grid into a graph and then tracks a group of Ozobots as they traverse the grid. Earlier works with Ozobots used them to investigate Multi-Agent Pathfinding. This work is the first in exploring their detection in image data. To achieve that, I am using the OpenCV library and the Java programming language. By training my own cascade for use in a Cascade Classifier from the objdetect OpenCV module, I was able to achieve a good rate of Ozobot detection in real time. The grid detection works by detecting lines on the color transitions in the image and their subsequent grouping into lines in the grid.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.