Home > Search Results: keywords:"trénování neuronových sítí"
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Fire and smoke detection in video
 Buzovský, Viktor ; Říha, Kamil (referee) ; Přinosil, Jiří (advisor)
Thesis deals with possibilities regarding detection of fire and smoke in real enviroment video. The main task is to choose suitable model, train this model, and improve detection capabilities of the model afterwards. First part of thesis is summary of theoritical knowledge needed to have understanding of discussed technical necessities. The second, practical part presents the learned model and its subsequent attempts at improvement, firstly using optical flow and then using additional classification networks. The work is concluded with a final implementation for the detector of fire and smoke, and a proposal for its potential improvement is presented. The work also includes the datasets used and created, among other things.
Detailed record
Physical aspects of digital image and object detection using convolutional neural networsk
 ŠTINDLOVÁ, Lucie
The thesis is focused on computer vision and the comparison of trained deep learning models. In the theoretical part, a detailed overview of the physical properties of the visible electromagnetic spectrum and the principles of the digital image, including it, is processed. This is followed by a review of image processing methods, where conventional methods and then convolutional neural networks are briefly characterized. The practical part is focused on creating a suitable dataset with annotations, which is further applied for training selected models. The variability and accuracy of the obtained results is analyzed from the point of view of the selected evaluation metrics, as well as based on the experimental determination of input parameters for training.
Detailed record

Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English