Hlavní stránka > Výsledky hledání: keywords:"SSDLite"
Hledej:
Tipy pro vyhledávaní :: Rozšířené hledání
Hledej ve sbírkách:
Seřadit podle: Zobrazit výsledky: Výstupní formát:
Národní úložiště šedé literatury Nalezeno 3 záznamů.  Hledání trvalo 0.00 vteřin. 
Pedestrians Detection in Traffic Environment by Machine Learning
 Tilgner, Martin ; Klečka, Jan (oponent) ; Horák, Karel (vedoucí práce)
This thesis deals with pedestrian detection using convolutional neural networks from the perspective of autonomous vehicle. Especially by testing these networks in the sense of finding a suitable practice of creating a dataset for machine learning models. A total of ten machine learning models of meta architectures Faster R-CNN with ResNet 101 as a feature extractor and SSDLite with the MobileNet_v2 feature extractor were trained. These models were trained on datasets of various sizes. The best results were achieved on a dataset of 5 000 images. In addition to these models, a new dataset aimed at pedestrians at night was created. Furthermore, a Python library was created for work with datasets and script for automatic creation of dataset.
Úplný záznam
Pedestrian Detection In Image By Machine Learning
 Tilgner, Martin
This work deals with pedestrian detection via convolutional neural network which can be used in autonomous car driving systems to improve travel safety. The work focuses on the influence of the training dataset on the resulting network behavior. The Faster R-CNN with ResNet 101 as backbone network and the SSDLite with MobileNet v2 as backbone network meta-architectures were selected for parameter testing. Both networks achieved real-time detection while accuracy was 61.92 % for the Faster R-CNN and 31.72 % for the SSDLite.
Úplný záznam
Pedestrians Detection in Traffic Environment by Machine Learning
 Tilgner, Martin ; Klečka, Jan (oponent) ; Horák, Karel (vedoucí práce)
This thesis deals with pedestrian detection using convolutional neural networks from the perspective of autonomous vehicle. Especially by testing these networks in the sense of finding a suitable practice of creating a dataset for machine learning models. A total of ten machine learning models of meta architectures Faster R-CNN with ResNet 101 as a feature extractor and SSDLite with the MobileNet_v2 feature extractor were trained. These models were trained on datasets of various sizes. The best results were achieved on a dataset of 5 000 images. In addition to these models, a new dataset aimed at pedestrians at night was created. Furthermore, a Python library was created for work with datasets and script for automatic creation of dataset.
Úplný záznam

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.
Digitální repozitář :: Hledej :: Nový záznam :: Personalizace :: Nápověda
Powered by Invenio v1.1.2
Spravuje admin.invenio@techlib.cz
Tato stránka je dostupná také v následujících jazycích:
Česky  English